AionLabs: Aion 3.5Aion Labstext → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$3.00Output / 1M$6.00
AionLabs: Aion 3.5 MiniAion Labstext → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.700Output / 1M$1.40
AionLabs: Aion-2.0Aion Labstext → text131,072 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.800Output / 1M$1.60
AionLabs: Aion-3.0-MiniAion Labstext → text131,072 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.700Output / 1M$1.40
AionLabs: Aion-RP 1.0 (8B)Aion Labstext → text32,768 context windowupdated 10/18/2026max tokenstemperaturetop pInput / 1M$0.800Output / 1M$1.60
Gemma-SEA-LION-v4-27B-ITAisingaporetext → textContext unavailableupdated 10/18/2026structured outputInput / 1M—Output / 1M—
Qwen-SEA-LION-v4-32B-ITAisingaporetext → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
WizardLM-2-8x22BAlpindaletext → text65,535 context windowupdated 10/18/2026Input / 1M$0.620Output / 1M$0.620
Amazon: Nova 2 LiteAmazontext, image, video, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningstopInput / 1M$0.300Output / 1M$2.50
Amazon: Nova Lite 1.0Amazontext, image → text300,000 context windowupdated 10/18/2026max tokensstoptemperatureTools / function callingInput / 1M$0.060Output / 1M$0.240
Amazon: Nova Micro 1.0Amazontext → text128,000 context windowupdated 10/18/2026max tokensstoptemperatureTools / function callingInput / 1M$0.035Output / 1M$0.140
Amazon: Nova Premier 1.0Amazontext, image → text1,000,000 context windowupdated 10/18/2026max tokensstoptemperatureTools / function callingInput / 1M$2.50Output / 1M$12.50
Amazon: Nova Pro 1.0Amazontext, image → text300,000 context windowupdated 10/18/2026max tokensstoptemperatureTools / function callingInput / 1M$0.800Output / 1M$3.20
Magnum v4 72BAnthracite Orgtext → text32,768 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$2.50Output / 1M$5.00
Anthropic: Claude 3 HaikuAnthropictext, image → text200,000 context windowupdated 9/26/2026max tokensstoptemperaturetool choiceInput / 1M$0.250Output / 1M$1.25
Anthropic: Claude Fable 5Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$10.00Output / 1M$50.00
Anthropic: Claude Fable 5 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$5.00Output / 1M$25.00
Anthropic: Claude Fable 5.1Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$10.00Output / 1M$50.00
Anthropic: Claude Fable 5.1 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$5.00Output / 1M$25.00
Anthropic: Claude Haiku 4.5Anthropictext, image, file → text200,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$1.00Output / 1M$5.00
Anthropic: Claude Haiku 4.5 (batch)Anthropictext, image, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.500Output / 1M$2.50
Anthropic: Claude Haiku 5.5Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.100Output / 1M$0.500
Anthropic: Claude Haiku 5.5 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.050Output / 1M$0.250
Anthropic: Claude Opus 4Anthropicimage, text, file → text200,000 context windowupdated 9/21/2026include reasoningmax tokensReasoningstopInput / 1M$15.00Output / 1M$75.00
Anthropic: Claude Opus 4.1Anthropicimage, text, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningstopInput / 1M$15.00Output / 1M$75.00
Anthropic: Claude Opus 4.1 (batch)Anthropicimage, text, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$7.50Output / 1M$37.50
Anthropic: Claude Opus 4.5Anthropicfile, image, text → text200,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$5.00Output / 1M$25.00
Anthropic: Claude Opus 4.5 (batch)Anthropicfile, image, text → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$2.50Output / 1M$12.50
Anthropic: Claude Opus 4.6Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$5.00Output / 1M$25.00
Anthropic: Claude Opus 4.6 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.50Output / 1M$12.50
Anthropic: Claude Opus 4.7Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$5.00Output / 1M$25.00
Anthropic: Claude Opus 4.7 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.50Output / 1M$12.50
Anthropic: Claude Opus 4.8Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$5.00Output / 1M$25.00
Anthropic: Claude Opus 4.8 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.50Output / 1M$12.50
Anthropic: Claude Opus 5Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$5.00Output / 1M$25.00
Anthropic: Claude Opus 5 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.50Output / 1M$12.50
Anthropic: Claude Opus 5.5Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$4.00Output / 1M$20.00
Anthropic: Claude Opus 5.5 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.00Output / 1M$10.00
Anthropic: Claude Sonnet 4Anthropicimage, text, file → text200,000 context windowupdated 10/15/2026include reasoningmax tokensReasoningstopInput / 1M$3.00Output / 1M$15.00
Anthropic: Claude Sonnet 4.5Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$3.00Output / 1M$15.00
Anthropic: Claude Sonnet 4.5 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$1.50Output / 1M$7.50
Anthropic: Claude Sonnet 4.6Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$3.00Output / 1M$15.00
Anthropic: Claude Sonnet 4.6 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.50Output / 1M$7.50
Anthropic: Claude Sonnet 5Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$10.00
Anthropic: Claude Sonnet 5 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$5.00
Anthropic: Claude Sonnet 5.5Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$10.00
Anthropic: Claude Sonnet 5.5 (batch)Anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$5.00
Apodex: Apodex 1.1 Mini (free)Apodextext → text262,144 context windowupdated 10/13/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.000Output / 1M$0.000
Arcee AI: Trinity Large ThinkingArcee Aitext → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningtemperatureInput / 1M$0.250Output / 1M$0.800
Baidu: ERNIE 4.5 VL 424B A47B Baiduimage, text → text123,000 context windowupdated 10/8/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.420Output / 1M$1.25
ERNIE-4.5-VL-424B-A47B-Base-PTBaidutext, image → text123,000 context windowupdated 10/8/2026Input / 1M—Output / 1M—
ByteDance: UI-TARS 7B Bytedanceimage, text → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.100Output / 1M$0.200
ByteDance Seed: Seed 1.6Bytedance Seedimage, text, video → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.250Output / 1M$2.00
ByteDance Seed: Seed 1.6 FlashBytedance Seedimage, text, video → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.075Output / 1M$0.300
ByteDance Seed: Seed 2.1 TurboBytedance Seedtext, image, video → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.500Output / 1M$2.50
ByteDance Seed: Seed-2.0-CodeBytedance Seedtext, image, video → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.500Output / 1M$3.00
ByteDance Seed: Seed-2.0-LiteBytedance Seedtext, image, video → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.250Output / 1M$2.00
ByteDance Seed: Seed-2.0-MiniBytedance Seedtext, image, video → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.100Output / 1M$0.400
Venice: UncensoredCognitivecomputationstext → text128,000 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.200Output / 1M$0.900
Cohere: Command ACoheretext → text256,000 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$2.50Output / 1M$10.00
Cohere: Command A+Coheretext, image → text192,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.300Output / 1M$1.50
Cohere: Command R (08-2024)Coheretext → text128,000 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.150Output / 1M$0.600
Cohere: Command R+ (08-2024)Coheretext → text128,000 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$2.50Output / 1M$10.00
Cohere: Command R7B (12-2024)Coheretext → text128,000 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.0375Output / 1M$0.150
Cohere: North Mini Code (free)Coheretext → text256,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.000Output / 1M$0.000
aya-vision-32bCohereLabstext, image → textContext unavailableupdated 10/18/2026Input / 1M—Output / 1M—
c4ai-command-a-03-2025CohereLabstext → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
c4ai-command-r-08-2024CohereLabstext → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
c4ai-command-r7b-12-2024CohereLabstext → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
c4ai-command-r7b-arabic-02-2025CohereLabstext → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
command-a-plus-05-2026-bf16CohereLabstext, image → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
command-a-plus-05-2026-fp8CohereLabstext, image → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
command-a-plus-05-2026-w4a4CohereLabstext, image → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
command-a-reasoning-08-2025CohereLabstext → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
command-a-translate-08-2025CohereLabstext → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
command-a-vision-07-2025CohereLabstext, image → textContext unavailableupdated 10/18/2026structured outputInput / 1M—Output / 1M—
DeepSeek: DeepSeek V3DeepSeektext → text163,840 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.320Output / 1M$0.890
DeepSeek: DeepSeek V3 0324DeepSeektext → text163,840 context windowupdated 10/18/2026frequency penaltylogprobsmax tokensresponse formatInput / 1M$0.290Output / 1M$1.14
DeepSeek: DeepSeek V3.1DeepSeektext → text163,840 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.250Output / 1M$0.950
DeepSeek: DeepSeek V3.1 TerminusDeepSeektext → text163,840 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.270Output / 1M$1.00
DeepSeek: DeepSeek V3.2DeepSeektext → text163,840 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.280Output / 1M$0.420
DeepSeek: DeepSeek V3.2 ExpDeepSeektext → text163,840 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.270Output / 1M$0.410
DeepSeek: DeepSeek V4 Flash 0423DeepSeektext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.091Output / 1M$0.182
DeepSeek: DeepSeek V4 Flash 0731DeepSeektext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.0065Output / 1M$0.450
DeepSeek: DeepSeek V4 Flash 0731 (batch)DeepSeektext → text1,048,576 context windowupdated 9/22/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.110Output / 1M$0.330
DeepSeek: DeepSeek V4 Flash 0731 (free)DeepSeektext → text1,048,576 context windowupdated 9/20/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.000Output / 1M$0.000
DeepSeek: DeepSeek V4 Flash Vision ExpDeepSeektext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.2156Output / 1M$0.6468
DeepSeek: DeepSeek V4 Flash Vision Exp (batch)DeepSeektext, image → text1,048,576 context windowupdated 9/22/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.110Output / 1M$0.330
DeepSeek: DeepSeek V4 Pro 0423DeepSeektext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.2088Output / 1M$0.4176
DeepSeek: DeepSeek V4 Pro 0813DeepSeektext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.660Output / 1M$1.98
DeepSeek: DeepSeek V4 Pro 0813 (batch)DeepSeektext → text1,048,576 context windowupdated 9/22/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.660Output / 1M$1.98
DeepSeek: DeepSeek V4.1 FlashDeepSeektext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.060Output / 1M$0.120
DeepSeek: DeepSeek V4.1 Flash (batch)DeepSeektext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.050Output / 1M$0.150
DeepSeek: DeepSeek V4.1 Flash 1017DeepSeektext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.150Output / 1M$0.600
DeepSeek: R1DeepSeektext → text64,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.700Output / 1M$2.50
DeepSeek: R1 0528DeepSeektext → text163,840 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.500Output / 1M$2.15
DeepSeek: R1 Distill Llama 70BDeepSeektext → text8,192 context windowupdated 9/28/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.800Output / 1M$0.800
DeepSeek-R1Deepseek Aitext → text64,000 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.700Output / 1M$2.50
DeepSeek-R1-0528Deepseek Aitext → text163,840 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.500Output / 1M$2.15
DeepSeek-R1-Distill-Llama-70BDeepseek Aitext → text8,192 context windowupdated 9/28/2026Input / 1M—Output / 1M—
DeepSeek-R1-Distill-Llama-8BDeepseek Aitext → text131,072 context windowupdated 10/18/2026structured outputInput / 1M$0.050Output / 1M$0.050
DeepSeek-R1-Distill-Qwen-14BDeepseek Aitext → text131,072 context windowupdated 10/18/2026structured outputInput / 1M$0.200Output / 1M$0.200
DeepSeek-R1-Distill-Qwen-7BDeepseek Aitext → text131,072 context windowupdated 10/18/2026Input / 1M$0.150Output / 1M$0.150
DeepSeek-V3Deepseek Aitext → text163,840 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.320Output / 1M$0.890
DeepSeek-V3-0324Deepseek Aitext → text163,840 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.240Output / 1M$0.900
DeepSeek-V3.1Deepseek Aitext → text163,840 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.250Output / 1M$0.950
DeepSeek-V3.1-TerminusDeepseek Aitext → text163,840 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.270Output / 1M$0.950
DeepSeek-V3.2Deepseek Aitext → text163,840 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.260Output / 1M$0.380
DeepSeek-V3.2-ExpDeepseek Aitext → text163,840 context windowupdated 9/28/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
DeepSeek-V4-FlashDeepseek Aitext → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.090Output / 1M$0.180
DeepSeek-V4-Flash-0731Deepseek Aitext → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.060Output / 1M$0.180
DeepSeek-V4-Flash-Vision-ExpDeepseek Aitext, image → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.440Output / 1M$1.32
DeepSeek-V4-ProDeepseek Aitext → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$1.30Output / 1M$2.60
DeepSeek-V4-Pro-0813Deepseek Aitext → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$1.30Output / 1M$2.60
DeepSeek-V4.1-FlashDeepseek Aitext, image → text1,048,576 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.200Output / 1M$0.600
Dots Studio: Dots3-Note Preview (free)Dots Studiotext, image → text512,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.000Output / 1M$0.000
Elorian: GlimpseEloriantext, image, video → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.600Output / 1M$3.00
Fireworks: Ember-1Fireworkstext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$3.00Output / 1M$15.00
Google: Gemini 2.5 FlashGooglefile, image, text, audio, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.300Output / 1M$2.50
Google: Gemini 2.5 Flash (batch)Googlefile, image, text, audio, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.150Output / 1M$1.25
Google: Gemini 2.5 Flash LiteGoogletext, image, file, audio, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.100Output / 1M$0.400
Google: Gemini 2.5 Flash Lite (batch)Googletext, image, file, audio, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.050Output / 1M$0.200
Google: Gemini 2.5 ProGoogletext, image, file, audio, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$1.25Output / 1M$10.00
Google: Gemini 2.5 Pro (batch)Googletext, image, file, audio, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.625Output / 1M$5.00
Google: Gemini 2.5 Pro Preview 05-06Googletext, image, file, audio, video → text1,048,576 context windowupdated 9/14/2026include reasoningmax tokensReasoningresponse formatInput / 1M$1.25Output / 1M$10.00
Google: Gemini 2.5 Pro Preview 06-05Googlefile, image, text, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$1.25Output / 1M$10.00
Google: Gemini 3 Flash PreviewGoogletext, image, file, audio, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.500Output / 1M$3.00
Google: Gemini 3 Flash Preview (batch)Googletext, image, file, audio, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.250Output / 1M$1.50
Google: Gemini 3.1 Flash LiteGoogletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.250Output / 1M$1.50
Google: Gemini 3.1 Flash Lite (batch)Googletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.125Output / 1M$0.750
Google: Gemini 3.1 Flash Lite PreviewGoogletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.250Output / 1M$1.50
Google: Gemini 3.1 Pro PreviewGoogleaudio, file, image, text, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.00Output / 1M$12.00
Google: Gemini 3.1 Pro Preview (batch)Googleaudio, file, image, text, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$6.00
Google: Gemini 3.1 Pro Preview Custom ToolsGoogletext, audio, image, video, file → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.00Output / 1M$12.00
Google: Gemini 3.5 FlashGoogletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.50Output / 1M$9.00
Google: Gemini 3.5 Flash (batch)Googletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.750Output / 1M$4.50
Google: Gemini 3.5 Flash LiteGoogletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.300Output / 1M$2.50
Google: Gemini 3.5 Flash Lite (batch)Googletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.150Output / 1M$1.25
Google: Gemini 3.6 FlashGoogletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.750Output / 1M$3.75
Google: Gemini 3.6 Flash (batch)Googletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.375Output / 1M$1.88
Google: Gemini 3.7 FlashGoogletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.750Output / 1M$3.75
Google: Gemini 3.7 Flash (batch)Googletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.375Output / 1M$1.88
Google: Gemini 3.8 FlashGoogletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.825Output / 1M$4.13
Google: Gemini 3.8 Flash (batch)Googletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.375Output / 1M$1.88
Google: Gemini 4 ArgonGoogleaudio, file, image, text, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.00Output / 1M$10.00
Google: Gemini 4 Argon (batch)Googleaudio, file, image, text, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$5.00
Google: Gemma 2 27BGoogletext → text8,192 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyrepetition penaltyInput / 1M$0.650Output / 1M$0.650
Google: Gemma 3 12BGoogletext, image → text131,072 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.050Output / 1M$0.150
Google: Gemma 3 27BGoogletext, image → text131,072 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.080Output / 1M$0.160
Google: Gemma 3 4BGoogletext, image → text131,072 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.050Output / 1M$0.100
Google: Gemma 4 26B A4B Googletext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.0675Output / 1M$0.225
Google: Gemma 4 26B A4B (free)Googleimage, text, video → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.000Output / 1M$0.000
Google: Gemma 4 31BGoogletext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.140Output / 1M$0.400
Google: Gemma 4 31B (batch)Googleimage, text, video → text262,144 context windowupdated 9/15/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.390Output / 1M$0.970
Google: Gemma 4 31B (free)Googleimage, text, video → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.000Output / 1M$0.000
Google: Lyria 3 Clip PreviewGoogletext, image → text, audio1,048,576 context windowupdated 10/18/2026max tokensresponse formatseedtemperatureInput / 1M$0.000Output / 1M$0.000
Google: Lyria 3 Pro PreviewGoogletext, image → text, audio1,048,576 context windowupdated 10/18/2026max tokensresponse formatseedtemperatureInput / 1M$0.000Output / 1M$0.000
Google: Nano Banana (Gemini 2.5 Flash Image)Googleimage, text → image, text32,768 context windowupdated 10/18/2026max tokensresponse formatseedstopInput / 1M$0.300Output / 1M$2.50
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)Googleimage, text → image, text65,536 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.500Output / 1M$3.00
Google: Nano Banana 2 (Gemini 3.1 Flash Image)Googleimage, text → image, text131,072 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.500Output / 1M$3.00
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Googleimage, text → image, text65,536 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.250Output / 1M$1.50
Google: Nano Banana 2.1Googleimage, text → image, text65,536 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.50Output / 1M$7.50
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)Googleimage, text → image, text65,536 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$2.00Output / 1M$12.00
Google: Nano Banana Pro (Gemini 3 Pro Image)Googleimage, text → image, text131,072 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$2.00Output / 1M$12.00
gemma-3n-E4B-itGoogletext, image → text32,768 context windowupdated 9/14/2026structured outputInput / 1M—Output / 1M—
MythoMax 13BGryphetext → text8,192 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.080Output / 1M$0.110
IBM: Granite 4.0 MicroIbm Granitetext → text131,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.017Output / 1M$0.112
IBM: Granite 4.2 8BIbm Granitetext → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.060Output / 1M$0.250
granite-4.2-30bIbm Granitetext → text131,072 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.160Output / 1M$0.650
granite-4.2-3bIbm Granitetext → text131,072 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.030Output / 1M$0.120
Inception: Mercury 2Inceptiontext → text128,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.250Output / 1M$0.750
Inception: Mercury 2.5Inceptiontext → text260,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.040Output / 1M$0.150
Inception: Mercury 2.5 PreviewInceptiontext → text260,000 context windowupdated 9/8/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.040Output / 1M$0.150
inclusionAI: Ling 3.0 FlashInclusionaitext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.021Output / 1M$0.063
inclusionAI: Ling 3.0 Flash FinInclusionaitext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.042Output / 1M$0.1232
inclusionAI: Ling 3.0 Flash Fin (free)Inclusionaitext → text262,144 context windowupdated 9/28/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.000Output / 1M$0.000
inclusionAI: Ling 3.0 Flash SanteInclusionaitext → text262,144 context windowupdated 10/13/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.042Output / 1M$0.1232
inclusionAI: Ling 3.0 Flash Sante (free)Inclusionaitext → text262,144 context windowupdated 10/8/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.000Output / 1M$0.000
inclusionAI: Ling 3.0 Flash VLInclusionaitext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.060Output / 1M$0.180
inclusionAI: Ling 3.0 Flash VL (free)Inclusionaitext, image, video → text262,144 context windowupdated 9/23/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.000Output / 1M$0.000
inclusionAI: Ling 3.1 FlashInclusionaitext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.075Output / 1M$0.225
Inference.net: Schematron V2 SmallInference Nettext → text128,000 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.050Output / 1M$0.230
Inference.net: Schematron V2 TurboInference Nettext → text128,000 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.030Output / 1M$0.150
Kwaipilot: KAT-Coder-Pro V2Kwaipilottext → text262,144 context windowupdated 9/22/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.300Output / 1M$1.20
Kwaipilot: KAT-Coder-Pro V2.5Kwaipilottext → text262,144 context windowupdated 10/7/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.740Output / 1M$2.96
LiquidAI: LFM2.5-2.6B (free)Liquidtext → text65,536 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax completion tokensInput / 1M$0.000Output / 1M$0.000
LiquidAI: LFM2.5-24B-A2BLiquidtext → text128,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax completion tokensInput / 1M$0.050Output / 1M$0.700
Mancer: Weaver (alpha)Mancertext → text8,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.400Output / 1M$0.750
Meituan: LongCat 2.0Meituantext → text1,048,756 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.300Output / 1M$1.20
Meta: Muse Glimmer 30BMetatext, image → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.300Output / 1M$1.20
Meta: Muse Glimmer 30B (batch)Metatext, image → text131,072 context windowupdated 9/22/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.175Output / 1M$0.750
Meta: Muse Spark 1.1Metatext, image, video, file → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.25Output / 1M$4.25
Meta: Muse Spark 1.2Metatext, image, video, file → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.25Output / 1M$4.25
Meta: Muse Spark 1.2 ContributorMetatext, image, video, file → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.100Output / 1M$0.200
Meta: Muse Spark 1.3Metatext, image, video, file → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.25Output / 1M$4.25
Meta: Muse Spark 1.3 ContributorMetatext, image, video, file → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.100Output / 1M$0.200
Meta: Muse Spark OpenMetatext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$1.25Output / 1M$4.25
Meta: Muse WonderMetatext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$4.00Output / 1M$20.00
Llama-4-Maverick-17B-128E-Instruct-FP8Meta Llamatext, image → text1,048,576 context windowupdated 10/18/2026structured outputInput / 1M$0.270Output / 1M$0.850
Llama-4-Scout-17B-16E-InstructMeta Llamatext, image → text890,000 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.090Output / 1M$0.290
Meta: Llama 3.1 70B InstructMeta Llamatext → text131,072 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.400Output / 1M$0.400
Meta: Llama 3.1 8B InstructMeta Llamatext → text131,072 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.020Output / 1M$0.050
Meta: Llama 3.2 1B InstructMeta Llamatext → text60,000 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.027Output / 1M$0.201
Meta: Llama 3.2 3B InstructMeta Llamatext → text131,072 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.0509Output / 1M$0.335
Meta: Llama 3.3 70B InstructMeta Llamatext → text131,072 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.100Output / 1M$0.320
Meta: Llama 4 MaverickMeta Llamatext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.1875Output / 1M$0.6525
Meta: Llama 4 ScoutMeta Llamatext, image → text1,310,720 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.100Output / 1M$0.300
Meta: Llama Guard 4 12BMeta Llamatext, image → text163,840 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.180Output / 1M$0.180
Muse-Glimmer-30BMeta Modelstext, image → text131,072 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.300Output / 1M$1.20
Muse-Spark-Open-816B-A42BMeta Modelstext, image → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$1.25Output / 1M$4.25
Microsoft: Phi 4Microsofttext → text16,384 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.070Output / 1M$0.140
WizardLM-2 8x22BMicrosofttext → text65,535 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyrepetition penaltyInput / 1M$0.620Output / 1M$0.620
MiniMax-M1-80kMiniMaxAItext → text1,000,000 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.550Output / 1M$2.20
MiniMax-M2MiniMaxAItext → text204,800 context windowupdated 10/8/2026Tools / function callingInput / 1M—Output / 1M—
MiniMax-M2.1MiniMaxAItext → text204,800 context windowupdated 10/8/2026Tools / function callingInput / 1M—Output / 1M—
MiniMax-M2.5MiniMaxAItext → text204,800 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.300Output / 1M$1.20
MiniMax-M2.7MiniMaxAItext → text204,800 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.250Output / 1M$1.00
MiniMax-M3MiniMaxAItext, image → text1,000,000 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.280Output / 1M$1.10
MiniMax: MiniMax M1Minimaxtext → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.550Output / 1M$2.20
MiniMax: MiniMax M2Minimaxtext → text204,800 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.255Output / 1M$1.02
MiniMax: MiniMax M2-herMinimaxtext → text65,536 context windowupdated 10/18/2026max tokenstemperaturetop pInput / 1M$0.300Output / 1M$1.20
MiniMax: MiniMax M2.1Minimaxtext → text204,800 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.300Output / 1M$1.20
MiniMax: MiniMax M2.5Minimaxtext → text204,800 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.270Output / 1M$0.950
MiniMax: MiniMax M2.7Minimaxtext → text204,800 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.300Output / 1M$1.20
MiniMax: MiniMax M2.7 (free)Minimaxtext → text196,608 context windowupdated 9/7/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.000Output / 1M$0.000
MiniMax: MiniMax M3Minimaxtext, image, video → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.300Output / 1M$1.20
MiniMax: MiniMax M3 (batch)Minimaxtext, image, video → text524,288 context windowupdated 9/21/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.300Output / 1M$1.20
MiniMax: MiniMax M3 (free)Minimaxtext, image, video → text1,048,576 context windowupdated 9/7/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.000Output / 1M$0.000
MiniMax: MiniMax-01Minimaxtext, image → text1,000,192 context windowupdated 10/18/2026max tokenstemperaturetop pInput / 1M$0.200Output / 1M$1.10
Mistral LargeMistral AItext, file → text128,000 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$2.00Output / 1M$6.00
Mistral Large 2407Mistral AItext, file → text131,072 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$2.00Output / 1M$6.00
Mistral: Codestral 2508Mistral AItext, file → text256,000 context windowupdated 10/18/2026frequency penaltymax tokenspredictionpresence penaltyInput / 1M$0.300Output / 1M$0.900
Mistral: Codestral 2508 (batch)Mistral AItext, file → text256,000 context windowupdated 10/18/2026frequency penaltymax tokenspredictionpresence penaltyInput / 1M$0.150Output / 1M$0.450
Mistral: Devstral 2 2512Mistral AItext, file → text262,144 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.400Output / 1M$2.00
Mistral: Ministral 3 14B 2512Mistral AItext, image → text262,144 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.200Output / 1M$0.200
Mistral: Ministral 3 3B 2512Mistral AItext, image → text131,072 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.100Output / 1M$0.100
Mistral: Ministral 3 8B 2512Mistral AItext, image → text262,144 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.150Output / 1M$0.150
Mistral: Ministral 3 8B 2512 (batch)Mistral AItext, image → text262,144 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.075Output / 1M$0.075
Mistral: Mistral Large 3 2512Mistral AItext, image, file → text262,144 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.500Output / 1M$1.50
Mistral: Mistral Large 3 2512 (batch)Mistral AItext, image, file → text262,144 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.250Output / 1M$0.750
Mistral: Mistral Large 4Mistral AItext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.680Output / 1M$2.09
Mistral: Mistral Medium 3Mistral AItext, image, file → text131,072 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.400Output / 1M$2.00
Mistral: Mistral Medium 3.1Mistral AItext, image, file → text131,072 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.400Output / 1M$2.00
Mistral: Mistral Medium 3.1 (batch)Mistral AItext, image, file → text131,072 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.200Output / 1M$1.00
Mistral: Mistral Medium 3.5Mistral AItext, image, file → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$1.50Output / 1M$7.50
Mistral: Mistral Medium 3.5 (batch)Mistral AItext, image, file → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.750Output / 1M$3.75
Mistral: Mistral NemoMistral AItext → text131,072 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.029Output / 1M$0.030
Mistral: Mistral Small 3Mistral AItext → text32,768 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.050Output / 1M$0.080
Mistral: Mistral Small 3.1 24BMistral AItext, image → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.351Output / 1M$0.555
Mistral: Mistral Small 3.2 24BMistral AIimage, text → text256,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.0938Output / 1M$0.250
Mistral: Mistral Small 4Mistral AItext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.150Output / 1M$0.600
Mistral: Mistral Small 4 (batch)Mistral AItext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.075Output / 1M$0.300
Mistral: Mixtral 8x22B InstructMistral AItext, file → text65,536 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$2.00Output / 1M$6.00
Mistral: SabaMistral AItext, file → text32,768 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.200Output / 1M$0.600
Mistral: Voxtral Small 24B 2507Mistral AItext, audio, file → text32,768 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyresponse formatInput / 1M$0.100Output / 1M$0.300
Moondream: Moondream 3 PreviewMoondreamtext, image → text32,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.300Output / 1M$2.50
Moondream: Moondream 3.1Moondreamtext, image → text32,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.300Output / 1M$2.50
Kimi-K2-InstructMoonshotaitext → text131,072 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.570Output / 1M$2.30
Kimi-K2-Instruct-0905Moonshotaitext → text262,144 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.600Output / 1M$2.50
MoonshotAI: Kimi K2 0711Moonshotaitext → text131,072 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyrepetition penaltyInput / 1M$0.570Output / 1M$2.30
MoonshotAI: Kimi K2 0905Moonshotaitext → text262,144 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltyrepetition penaltyInput / 1M$0.600Output / 1M$2.50
MoonshotAI: Kimi K2 ThinkingMoonshotaitext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.600Output / 1M$2.50
MoonshotAI: Kimi K2.5Moonshotaitext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.450Output / 1M$2.25
MoonshotAI: Kimi K2.6Moonshotaitext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.650Output / 1M$3.41
MoonshotAI: Kimi K2.7 CodeMoonshotaitext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.6712Output / 1M$3.35
MoonshotAI: Kimi K3Moonshotaitext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.249Output / 1M$11.94
MoonshotAI: Kimi K3 (batch)Moonshotaitext, image, video → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$2.28Output / 1M$11.40
Morph: Morph V3 FastMorphtext → text262,144 context windowupdated 10/18/2026logprobsmax tokensresponse formatstopInput / 1M$0.800Output / 1M$1.20
Morph: Morph V3 LargeMorphtext → text262,144 context windowupdated 10/18/2026logprobsmax tokensresponse formatstopInput / 1M$0.900Output / 1M$1.90
Nex AGI: Nex-N2-MiniNex Agitext, image → text262,144 context windowupdated 9/8/2026include reasoninglogprobsmax tokensReasoningInput / 1M$0.025Output / 1M$0.100
Nex AGI: Nex-N2-ProNex Agitext, image → text262,144 context windowupdated 9/8/2026include reasoninglogprobsmax tokensReasoningInput / 1M$0.250Output / 1M$1.00
Nex AGI: Nex-N2.5-MiniNex Agitext, image → text262,144 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$0.025Output / 1M$0.100
Nex AGI: Nex-N2.5-Mini (free)Nex Agitext, image → text262,144 context windowupdated 9/25/2026include reasoninglogprobsmax tokensReasoningInput / 1M$0.000Output / 1M$0.000
Nex AGI: Nex-N2.5-ProNex Agitext, image → text262,144 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$0.075Output / 1M$0.250
Nex AGI: Nex-N2.5-Pro (free)Nex Agitext, image → text262,144 context windowupdated 9/25/2026include reasoninglogprobsmax tokensReasoningInput / 1M$0.000Output / 1M$0.000
Nous: Hermes 3 405B InstructNousresearchtext → text131,072 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$1.00Output / 1M$1.00
Nous: Hermes 3 70B InstructNousresearchtext → text131,072 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.700Output / 1M$0.700
Nous: Hermes 4 405BNousresearchtext → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$1.00Output / 1M$3.00
Nous: Hermes 4 70BNousresearchtext → text131,072 context windowupdated 9/9/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.130Output / 1M$0.400
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16Nvidiatext → text262,144 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$1.00Output / 1M$5.00
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4Nvidiatext → text262,144 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.600Output / 1M$2.40
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16Nvidiatext → text262,144 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4Nvidiatext, image → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.200Output / 1M$0.500
NVIDIA: Nemotron 3 Nano 30B A3BNvidiatext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.060Output / 1M$0.240
NVIDIA: Nemotron 3 Nano Omni (free)Nvidiatext, audio, image, video → text256,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningseedInput / 1M$0.000Output / 1M$0.000
NVIDIA: Nemotron 3 SuperNvidiatext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.080Output / 1M$0.450
NVIDIA: Nemotron 3 Super (free)Nvidiatext → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.000Output / 1M$0.000
NVIDIA: Nemotron 3 UltraNvidiatext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.600Output / 1M$2.40
NVIDIA: Nemotron 3 Ultra (free)Nvidiatext → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.000Output / 1M$0.000
NVIDIA: Nemotron 3.5 Content SafetyNvidiatext, image → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.200Output / 1M$0.200
NVIDIA: Nemotron 3.5 Content Safety (free)Nvidiatext, image → text128,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningseedInput / 1M$0.000Output / 1M$0.000
NVIDIA: Nemotron 3.5 LightningNvidiatext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.070Output / 1M$0.200
NVIDIA: Nemotron 3.5 Lightning (free)Nvidiatext → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningseedInput / 1M$0.000Output / 1M$0.000
NVIDIA: Nemotron 3.5 Super VLNvidiatext, image, video → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.100Output / 1M$0.400
NVIDIA: Nemotron 3.5 Super VL (free)Nvidiatext, image, video → text1,000,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.000Output / 1M$0.000
OpenAI: GPT AudioOpenAItext, audio → text, audio128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$2.50Output / 1M$10.00
OpenAI: GPT Audio MiniOpenAItext, audio → text, audio128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.600Output / 1M$2.40
OpenAI: GPT Chat LatestOpenAItext, image, file → text400,000 context windowupdated 10/18/2026max tokensresponse formatseedStructured outputsInput / 1M$5.00Output / 1M$30.00
OpenAI: GPT-3.5 TurboOpenAItext → text16,385 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.500Output / 1M$1.50
OpenAI: GPT-3.5 Turbo (batch)OpenAItext → text16,385 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.250Output / 1M$0.750
OpenAI: GPT-3.5 Turbo (older v0613)OpenAItext → text4,095 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax completion tokensInput / 1M$1.00Output / 1M$2.00
OpenAI: GPT-3.5 Turbo 16kOpenAItext → text16,385 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax completion tokensInput / 1M$3.00Output / 1M$4.00
OpenAI: GPT-3.5 Turbo InstructOpenAItext → text4,095 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$1.50Output / 1M$2.00
OpenAI: GPT-4OpenAItext → text8,191 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax completion tokensInput / 1M$30.00Output / 1M$60.00
OpenAI: GPT-4 TurboOpenAItext, image → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$10.00Output / 1M$30.00
OpenAI: GPT-4 Turbo (batch)OpenAItext, image → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$5.00Output / 1M$15.00
OpenAI: GPT-4 Turbo PreviewOpenAItext → text128,000 context windowupdated 9/14/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$10.00Output / 1M$30.00
OpenAI: GPT-4.1OpenAIimage, text, file → text1,047,576 context windowupdated 10/18/2026max completion tokensmax tokensresponse formatseedInput / 1M$2.00Output / 1M$8.00
OpenAI: GPT-4.1 (batch)OpenAIimage, text, file → text1,047,576 context windowupdated 10/18/2026max tokensresponse formatseedStructured outputsInput / 1M$1.00Output / 1M$4.00
OpenAI: GPT-4.1 MiniOpenAIimage, text, file → text1,047,576 context windowupdated 10/18/2026max completion tokensmax tokensresponse formatseedInput / 1M$0.400Output / 1M$1.60
OpenAI: GPT-4.1 Mini (batch)OpenAIimage, text, file → text1,047,576 context windowupdated 10/18/2026max tokensresponse formatseedStructured outputsInput / 1M$0.200Output / 1M$0.800
OpenAI: GPT-4.1 NanoOpenAIimage, text, file → text1,047,576 context windowupdated 10/18/2026max completion tokensmax tokensresponse formatseedInput / 1M$0.100Output / 1M$0.400
OpenAI: GPT-4.1 Nano (batch)OpenAIimage, text, file → text1,047,576 context windowupdated 10/18/2026max tokensresponse formatseedStructured outputsInput / 1M$0.050Output / 1M$0.200
OpenAI: GPT-4oOpenAItext, image, file → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax completion tokensInput / 1M$2.50Output / 1M$10.00
OpenAI: GPT-4o (2024-05-13)OpenAItext, image, file → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax completion tokensInput / 1M$5.00Output / 1M$15.00
OpenAI: GPT-4o (2024-08-06)OpenAItext, image, file → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax completion tokensInput / 1M$2.50Output / 1M$10.00
OpenAI: GPT-4o (2024-11-20)OpenAItext, image, file → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$2.50Output / 1M$10.00
OpenAI: GPT-4o (batch)OpenAItext, image, file → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$1.25Output / 1M$5.00
OpenAI: GPT-4o-miniOpenAItext, image, file → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax completion tokensInput / 1M$0.150Output / 1M$0.600
OpenAI: GPT-4o-mini (2024-07-18)OpenAItext, image, file → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.150Output / 1M$0.600
OpenAI: GPT-4o-mini (batch)OpenAItext, image, file → text128,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.075Output / 1M$0.300
OpenAI: GPT-5OpenAItext, image, file → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$1.25Output / 1M$10.00
OpenAI: GPT-5 (batch)OpenAItext, image, file → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.625Output / 1M$5.00
OpenAI: GPT-5 ImageOpenAIimage, text, file → image, text400,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$10.00Output / 1M$10.00
OpenAI: GPT-5 Image MiniOpenAIfile, image, text → image, text400,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$2.50Output / 1M$2.00
OpenAI: GPT-5 MiniOpenAItext, image, file → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.250Output / 1M$2.00
OpenAI: GPT-5 Mini (batch)OpenAItext, image, file → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.125Output / 1M$1.00
OpenAI: GPT-5 NanoOpenAItext, image, file → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.050Output / 1M$0.400
OpenAI: GPT-5 Nano (batch)OpenAItext, image, file → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.025Output / 1M$0.200
OpenAI: GPT-5 ProOpenAIimage, text, file → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$15.00Output / 1M$120.00
OpenAI: GPT-5 Pro (batch)OpenAIimage, text, file → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$7.50Output / 1M$60.00
OpenAI: GPT-5.1OpenAIimage, text, file → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$1.25Output / 1M$10.00
OpenAI: GPT-5.1 (batch)OpenAIimage, text, file → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.625Output / 1M$5.00
OpenAI: GPT-5.1-CodexOpenAItext, image → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensReasoningreasoning effortInput / 1M$1.25Output / 1M$10.00
OpenAI: GPT-5.1-Codex-MaxOpenAItext, image → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensReasoningreasoning effortInput / 1M$1.25Output / 1M$10.00
OpenAI: GPT-5.1-Codex-MiniOpenAIimage, text → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensReasoningreasoning effortInput / 1M$0.250Output / 1M$2.00
OpenAI: GPT-5.2OpenAIfile, image, text → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$1.75Output / 1M$14.00
OpenAI: GPT-5.2 (batch)OpenAIfile, image, text → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.875Output / 1M$7.00
OpenAI: GPT-5.2 ChatOpenAIfile, image, text → text128,000 context windowupdated 10/18/2026max completion tokensresponse formatseedStructured outputsInput / 1M$1.75Output / 1M$14.00
OpenAI: GPT-5.2 ProOpenAIimage, text, file → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$21.00Output / 1M$168.00
OpenAI: GPT-5.2 Pro (batch)OpenAIimage, text, file → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$10.50Output / 1M$84.00
OpenAI: GPT-5.2-CodexOpenAItext, image → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensReasoningreasoning effortInput / 1M$1.75Output / 1M$14.00
OpenAI: GPT-5.3-CodexOpenAItext, image, file → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$1.75Output / 1M$14.00
OpenAI: GPT-5.4OpenAItext, image, file → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.50Output / 1M$15.00
OpenAI: GPT-5.4 (batch)OpenAItext, image, file → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.25Output / 1M$7.50
OpenAI: GPT-5.4 Image 2OpenAIimage, text, file → image, text272,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$8.00Output / 1M$15.00
OpenAI: GPT-5.4 MiniOpenAIfile, image, text → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.750Output / 1M$4.50
OpenAI: GPT-5.4 Mini (batch)OpenAIfile, image, text → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.375Output / 1M$2.25
OpenAI: GPT-5.4 NanoOpenAIfile, image, text → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.200Output / 1M$1.25
OpenAI: GPT-5.4 Nano (batch)OpenAIfile, image, text → text400,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.100Output / 1M$0.625
OpenAI: GPT-5.4 ProOpenAItext, image, file → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$30.00Output / 1M$180.00
OpenAI: GPT-5.4 Pro (batch)OpenAItext, image, file → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$15.00Output / 1M$90.00
OpenAI: GPT-5.5OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$5.00Output / 1M$30.00
OpenAI: GPT-5.5 (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.50Output / 1M$15.00
OpenAI: GPT-5.5 ProOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$30.00Output / 1M$180.00
OpenAI: GPT-5.5 Pro (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$15.00Output / 1M$90.00
OpenAI: GPT-5.6 LunaOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.200Output / 1M$1.20
OpenAI: GPT-5.6 Luna (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.100Output / 1M$0.600
OpenAI: GPT-5.6 Luna ProOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.200Output / 1M$1.20
OpenAI: GPT-5.6 Luna Pro (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.100Output / 1M$0.600
OpenAI: GPT-5.6 SolOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$4.00Output / 1M$20.00
OpenAI: GPT-5.6 Sol (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.00Output / 1M$10.00
OpenAI: GPT-5.6 Sol ProOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$4.00Output / 1M$20.00
OpenAI: GPT-5.6 Sol Pro (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.00Output / 1M$10.00
OpenAI: GPT-5.6 TerraOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$12.00
OpenAI: GPT-5.6 Terra (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$6.00
OpenAI: GPT-5.6 Terra ProOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$12.00
OpenAI: GPT-5.6 Terra Pro (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$6.00
OpenAI: GPT-6 AstraOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$10.00Output / 1M$50.00
OpenAI: GPT-6 Astra (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$5.00Output / 1M$25.00
OpenAI: GPT-6 Astra ProOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$10.00Output / 1M$50.00
OpenAI: GPT-6 Astra Pro (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$5.00Output / 1M$25.00
OpenAI: GPT-6 LunaOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.100Output / 1M$0.500
OpenAI: GPT-6 Luna (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.050Output / 1M$0.250
OpenAI: GPT-6 Luna ProOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.100Output / 1M$0.500
OpenAI: GPT-6 Luna Pro (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.050Output / 1M$0.250
OpenAI: GPT-6 SolOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$10.00
OpenAI: GPT-6 Sol (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$5.00
OpenAI: GPT-6 Sol ProOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$10.00
OpenAI: GPT-6 Sol Pro (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$5.00
OpenAI: GPT-6.1 SolOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$10.00
OpenAI: GPT-6.1 Sol (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$5.00
OpenAI: GPT-6.1 Sol ProOpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$10.00
OpenAI: GPT-6.1 Sol Pro (batch)OpenAIfile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.00Output / 1M$5.00
OpenAI: gpt-oss-120bOpenAItext → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.037Output / 1M$0.170
OpenAI: gpt-oss-120b (batch)OpenAItext → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.0296Output / 1M$0.136
OpenAI: gpt-oss-20bOpenAItext → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.018Output / 1M$0.090
OpenAI: gpt-oss-20b (batch)OpenAItext → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.024Output / 1M$0.112
OpenAI: gpt-oss-safeguard-20bOpenAItext → text131,072 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.075Output / 1M$0.300
OpenAI: o1OpenAItext, image, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$15.00Output / 1M$60.00
OpenAI: o1-proOpenAItext, image, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$150.00Output / 1M$600.00
OpenAI: o3OpenAIimage, text, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$2.00Output / 1M$8.00
OpenAI: o3 (batch)OpenAIimage, text, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$1.00Output / 1M$4.00
OpenAI: o3 MiniOpenAItext, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$1.10Output / 1M$4.40
OpenAI: o3 Mini (batch)OpenAItext, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.550Output / 1M$2.20
OpenAI: o3 Mini HighOpenAItext, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.10Output / 1M$4.40
OpenAI: o3 ProOpenAItext, file, image → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$20.00Output / 1M$80.00
OpenAI: o4 MiniOpenAIimage, text, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$1.10Output / 1M$4.40
OpenAI: o4 Mini (batch)OpenAIimage, text, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.550Output / 1M$2.20
OpenAI: o4 Mini HighOpenAIimage, text, file → text200,000 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$1.10Output / 1M$4.40
Auto RouterOpenroutertext, image, audio, file, video → text, image2,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M—Output / 1M—
Auto Router (Beta)Openroutertext, image, audio, file, video → text, image2,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M—Output / 1M—
Body Builder (beta)Openroutertext → text128,000 context windowupdated 10/18/2026Input / 1M—Output / 1M—
Free Models RouterOpenroutertext, image → text200,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax completion tokensInput / 1M$0.000Output / 1M$0.000
OpenRouter: FusionOpenroutertext → text1,000,000 context windowupdated 10/18/2026Input / 1M—Output / 1M—
Pareto Code RouterOpenroutertext → text2,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M—Output / 1M—
Perceptron: Perceptron Mk1Perceptrontext, image, video → text32,768 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.150Output / 1M$1.50
Perceptron: Perceptron Mk1.5Perceptrontext, image, video, audio → text36,864 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.150Output / 1M$1.50
Perplexity: SonarPerplexitytext, image → text127,072 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltytemperatureInput / 1M$1.00Output / 1M$1.00
Perplexity: Sonar Deep ResearchPerplexitytext → text128,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$2.00Output / 1M$8.00
Perplexity: Sonar ProPerplexitytext, image → text200,000 context windowupdated 10/18/2026frequency penaltymax tokenspresence penaltytemperatureInput / 1M$3.00Output / 1M$15.00
Perplexity: Sonar Pro SearchPerplexitytext, image → text200,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$3.00Output / 1M$15.00
Perplexity: Sonar Reasoning ProPerplexitytext, image → text128,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$2.00Output / 1M$8.00
Poolside: Laguna S 2.1Poolsidetext → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningtemperatureInput / 1M$0.090Output / 1M$0.180
Poolside: Laguna S 2.1 (free)Poolsidetext → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningtemperatureInput / 1M$0.000Output / 1M$0.000
Poolside: Laguna XS 2.1Poolsidetext → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningtemperatureInput / 1M$0.060Output / 1M$0.120
Poolside: Laguna XS 2.1 (free)Poolsidetext → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningtemperatureInput / 1M$0.000Output / 1M$0.000
PrismML: Ternary Bonsai 2 27BPrism Mltext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.075Output / 1M$0.500
Ternary-Bonsai-27B-AWQ-4bitPrism Mltext, image → text262,144 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.000Output / 1M$0.000
Ternary-Bonsai-27B-ggufPrism Mltext → text262,144 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.000Output / 1M$0.000
Qwen2.5 72B InstructQwentext → text32,768 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.360Output / 1M$0.400
Qwen2.5 Coder 32B InstructQwentext → text32,768 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.660Output / 1M$1.00
Qwen2.5-72B-InstructQwentext → text32,768 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.360Output / 1M$0.400
Qwen2.5-7B-InstructQwentext → text32,768 context windowupdated 9/14/2026Tools / function callingInput / 1M—Output / 1M—
Qwen2.5-Coder-32B-InstructQwentext → text131,072 context windowupdated 10/18/2026Input / 1M$0.060Output / 1M$0.200
Qwen2.5-Coder-3B-InstructQwentext → text32,768 context windowupdated 10/18/2026structured outputInput / 1M$0.010Output / 1M$0.030
Qwen2.5-Coder-7B-InstructQwentext → text131,072 context windowupdated 10/18/2026structured outputInput / 1M$0.010Output / 1M$0.030
Qwen3-235B-A22B-Instruct-2507Qwentext → text262,144 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.090Output / 1M$0.550
Qwen3-4B-Instruct-2507Qwentext → text262,144 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.010Output / 1M$0.030
Qwen3-4B-Thinking-2507Qwentext → text262,144 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.010Output / 1M$0.030
Qwen3-Coder-480B-A35B-InstructQwentext → text262,144 context windowupdated 10/8/2026Tools / function callingInput / 1M—Output / 1M—
Qwen: Qwen Plus 0728Qwentext → text1,000,000 context windowupdated 10/9/2026frequency penaltylogprobsmax tokenspresence penaltyInput / 1M$0.260Output / 1M$0.780
Qwen: Qwen-PlusQwentext → text1,000,000 context windowupdated 10/18/2026frequency penaltylogprobsmax tokenspresence penaltyInput / 1M$0.260Output / 1M$0.780
Qwen: Qwen2.5 7B InstructQwentext → text32,768 context windowupdated 10/18/2026frequency penaltymax tokensmin ppresence penaltyInput / 1M$0.100Output / 1M$0.200
Qwen: Qwen2.5 VL 72B InstructQwentext, image → text32,768 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.800Output / 1M$1.00
Qwen: Qwen3 14BQwentext → text40,960 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.070Output / 1M$0.200
Qwen: Qwen3 235B A22BQwentext → text32,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.200Output / 1M$0.600
Qwen: Qwen3 235B A22B Instruct 2507Qwentext → text262,144 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.090Output / 1M$0.550
Qwen: Qwen3 235B A22B Thinking 2507Qwentext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.230Output / 1M$2.30
Qwen: Qwen3 30B A3BQwentext → text40,960 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.120Output / 1M$0.500
Qwen: Qwen3 30B A3B Instruct 2507Qwentext → text262,144 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.090Output / 1M$0.300
Qwen: Qwen3 30B A3B Thinking 2507Qwentext → text81,920 context windowupdated 10/9/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.200Output / 1M$2.40
Qwen: Qwen3 32BQwentext → text40,960 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.080Output / 1M$0.250
Qwen: Qwen3 8BQwentext → text40,960 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.070Output / 1M$0.180
Qwen: Qwen3 Coder 30B A3B InstructQwentext → text262,144 context windowupdated 10/18/2026frequency penaltymax tokensresponse formatstopInput / 1M$0.070Output / 1M$0.280
Qwen: Qwen3 Coder 480B A35BQwentext → text262,144 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.300Output / 1M$1.00
Qwen: Qwen3 Coder FlashQwentext → text1,000,000 context windowupdated 10/18/2026frequency penaltylogprobsmax tokenspresence penaltyInput / 1M$0.195Output / 1M$0.975
Qwen: Qwen3 Coder NextQwentext → text262,144 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.120Output / 1M$0.800
Qwen: Qwen3 Coder PlusQwentext → text1,000,000 context windowupdated 10/9/2026frequency penaltylogprobsmax tokenspresence penaltyInput / 1M$0.650Output / 1M$3.25
Qwen: Qwen3 MaxQwentext → text262,144 context windowupdated 10/9/2026frequency penaltylogprobsmax tokenspresence penaltyInput / 1M$0.780Output / 1M$3.90
Qwen: Qwen3 Max ThinkingQwentext → text262,144 context windowupdated 10/9/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.780Output / 1M$3.90
Qwen: Qwen3 Next 80B A3B InstructQwentext → text262,144 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.090Output / 1M$1.10
Qwen: Qwen3 Next 80B A3B ThinkingQwentext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.150Output / 1M$1.20
Qwen: Qwen3 VL 235B A22B InstructQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.200Output / 1M$0.880
Qwen: Qwen3 VL 235B A22B ThinkingQwentext, image → text131,072 context windowupdated 10/9/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.400Output / 1M$4.00
Qwen: Qwen3 VL 30B A3B InstructQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.150Output / 1M$0.600
Qwen: Qwen3 VL 30B A3B ThinkingQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.290Output / 1M$1.00
Qwen: Qwen3 VL 32B InstructQwentext, image → text131,072 context windowupdated 10/9/2026frequency penaltylogprobsmax tokenspresence penaltyInput / 1M$0.104Output / 1M$0.416
Qwen: Qwen3 VL 8B InstructQwenimage, text → text262,144 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.250Output / 1M$0.750
Qwen: Qwen3 VL 8B ThinkingQwenimage, text → text131,072 context windowupdated 10/9/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.180Output / 1M$2.10
Qwen: Qwen3.5 397B A17BQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.450Output / 1M$3.00
Qwen: Qwen3.5 Plus 2026-02-15Qwentext, image, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.260Output / 1M$1.56
Qwen: Qwen3.5 Plus 2026-04-20Qwentext, image, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.300Output / 1M$1.80
Qwen: Qwen3.5-122B-A10BQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.260Output / 1M$2.08
Qwen: Qwen3.5-27BQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.300Output / 1M$2.40
Qwen: Qwen3.5-35B-A3BQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.140Output / 1M$1.00
Qwen: Qwen3.5-9BQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.100Output / 1M$0.150
Qwen: Qwen3.5-9B (batch)Qwentext, image, video → text262,144 context windowupdated 9/21/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.170Output / 1M$0.250
Qwen: Qwen3.5-FlashQwentext, image, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.065Output / 1M$0.260
Qwen: Qwen3.6 27BQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.250Output / 1M$2.00
Qwen: Qwen3.6 35B A3BQwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.100Output / 1M$0.950
Qwen: Qwen3.6 FlashQwentext, image, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.1875Output / 1M$1.13
Qwen: Qwen3.6 Max PreviewQwentext → text262,144 context windowupdated 10/9/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$1.03Output / 1M$6.16
Qwen: Qwen3.6 PlusQwentext, image, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.325Output / 1M$1.95
Qwen: Qwen3.7 FlashQwentext, image, video → text1,000,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokenspresence penaltyInput / 1M$0.030Output / 1M$0.130
Qwen: Qwen3.7 MaxQwentext → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$1.48Output / 1M$4.43
Qwen: Qwen3.7 PlusQwentext, image → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.320Output / 1M$1.28
Qwen: Qwen3.7 Plus (batch)Qwentext, image → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.230Output / 1M$0.920
Qwen: Qwen3.8 2.4T A95BQwentext → text1,010,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$2.00Output / 1M$6.00
Qwen: Qwen3.8 2.4T A95B (batch)Qwentext → text1,010,000 context windowupdated 9/21/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$2.00Output / 1M$6.00
Qwen: Qwen3.8 27BQwentext, image → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.240Output / 1M$2.20
Qwen: Qwen3.8 27B (free)Qwentext, image, video → text262,144 context windowupdated 10/5/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.000Output / 1M$0.000
Qwen: Qwen3.8 FlashQwentext, image, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.150Output / 1M$0.470
Qwen: Qwen3.8 Max (0902)Qwentext, image, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$2.00Output / 1M$6.00
Qwen: Qwen3.8 Max PrimeQwentext, image, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$4.00Output / 1M$12.00
Qwen: Qwen3.8 Omni FlashQwentext, image, audio, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.150Output / 1M$0.470
Reflection: Beam 1.0 501B A23BReflectiontext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$1.00Output / 1M$3.00
Reka EdgeRekaaiimage, text, video → text16,384 context windowupdated 10/18/2026frequency penaltylogprobsmax tokenspresence penaltyInput / 1M$0.100Output / 1M$0.100
Reka Flash 3Rekaaitext → text65,536 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.100Output / 1M$0.200
Relace: Relace Apply 3Relacetext → text256,000 context windowupdated 10/18/2026max tokensseedstopInput / 1M$0.850Output / 1M$1.25
Relace: Relace SearchRelacetext → text256,000 context windowupdated 10/18/2026max tokensresponse formatseedstopInput / 1M$1.00Output / 1M$3.00
Sakana: Fugu MaxSakanatext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningReasoningreasoning effortStructured outputsInput / 1M$2.00Output / 1M$6.00
Sakana: Fugu UltraSakanatext, image → text1,000,000 context windowupdated 10/18/2026include reasoningReasoningreasoning effortStructured outputsInput / 1M$5.00Output / 1M$30.00
Sakana: Fugu Ultra v2Sakanatext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningReasoningreasoning effortStructured outputsInput / 1M$5.00Output / 1M$30.00
Sakana: Sakana NamazuSakanatext, image, file → text262,144 context windowupdated 10/18/2026include reasoningReasoningreasoning effortStructured outputsInput / 1M$0.950Output / 1M$4.00
L3-8B-Stheno-v3.2Sao10ktext → text8,192 context windowupdated 10/18/2026Input / 1M$0.050Output / 1M$0.050
Sao10K: Llama 3 8B LunarisSao10ktext → text8,192 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.040Output / 1M$0.050
Sao10K: Llama 3.1 Euryale 70B v2.2Sao10ktext → text131,072 context windowupdated 10/18/2026frequency penaltylogit biasmax tokensmin pInput / 1M$0.850Output / 1M$0.850
Sao10K: Llama 3.3 Euryale 70BSao10ktext → text131,072 context windowupdated 10/18/2026frequency penaltylogprobsmax tokenspresence penaltyInput / 1M$0.650Output / 1M$0.750
ScaleDown: ExtractScaledowntext, image, file → text1,000,000 context windowupdated 10/18/2026max tokensInput / 1M$0.040Output / 1M$0.000
ScaleDown: SummarizeScaledowntext, image, file → text1,000,000 context windowupdated 10/18/2026max tokensInput / 1M$0.040Output / 1M$0.000
Bielik-11B-v3.0-InstructSpeakleashtext → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.400Output / 1M$0.400
Space Bunny AlphaStealthtext, image, video → text1,000,000 context windowupdated 10/5/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.000Output / 1M$0.000
Union AlphaStealthtext, image → text262,144 context windowupdated 9/17/2026max tokensresponse formattemperaturetool choiceInput / 1M$0.000Output / 1M$0.000
StepFun: Step 3.5 FlashStepfuntext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.100Output / 1M$0.300
StepFun: Step 3.7 FlashStepfuntext, image, video → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.200Output / 1M$1.15
StepFun: Step 5 PreviewStepfuntext, image, video → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$1.00Output / 1M$2.70
Step-3.5-FlashStepfun Aitext → text262,144 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.100Output / 1M$0.300
Step-3.7-FlashStepfun Aitext, image → text262,144 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.200Output / 1M$1.15
Apertus-70B-Instruct-2509Swiss Aitext → textContext unavailableupdated 9/30/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
Apertus-8B-Instruct-2509Swiss Aitext → textContext unavailableupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.100Output / 1M$0.200
Apertus-v1.5-70BSwiss Aitext, image → textContext unavailableupdated 9/30/2026Tools / function callingInput / 1M—Output / 1M—
Apertus-v1.5-8BSwiss Aitext, image → textContext unavailableupdated 9/21/2026Tools / function callingstructured outputInput / 1M—Output / 1M—
Tencent: Hunyuan A13B InstructTencenttext → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensReasoningInput / 1M$0.140Output / 1M$0.570
Tencent: Hy-MT2-1.8BTencenttext → text8,192 context windowupdated 10/18/2026max completion tokensmax tokensstoptemperatureInput / 1M$0.044Output / 1M$0.177
Tencent: Hy-MT2-30B-A3BTencenttext → text8,192 context windowupdated 10/18/2026max completion tokensmax tokensresponse formatstopInput / 1M$0.074Output / 1M$0.295
Tencent: Hy-MT2-7BTencenttext → text8,192 context windowupdated 10/18/2026max completion tokensmax tokensresponse formatstopInput / 1M$0.074Output / 1M$0.295
Tencent: Hy3Tencenttext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax completion tokensInput / 1M$0.0825Output / 1M$0.330
Tencent: Hy3 previewTencenttext → text262,144 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.180Output / 1M$0.600
Tencent: Hy4 previewTencenttext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax completion tokensInput / 1M$0.7506Output / 1M$2.25
TheDrummer: Cydonia 24B V4.1Thedrummertext → text131,072 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.300Output / 1M$0.500
TheDrummer: Skyfall 36B V2Thedrummertext → text32,768 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.550Output / 1M$0.800
TheDrummer: UnslopNemo 12BThedrummertext → text1,024,000 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.400Output / 1M$0.400
Thinking Machines: InklingThinkingmachinestext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.950Output / 1M$4.05
Thinking Machines: Inkling (batch)Thinkingmachinestext, image, audio → text524,288 context windowupdated 9/21/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$1.00Output / 1M$4.05
Thinking Machines: Inkling (free)Thinkingmachinestext, image, audio → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.000Output / 1M$0.000
Thinking Machines: Inkling SmallThinkingmachinestext, image → text524,288 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.450Output / 1M$1.20
Thinking Machines: Inkling Small (batch)Thinkingmachinestext, image, audio → text524,288 context windowupdated 9/15/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.500Output / 1M$1.20
Thinking Machines: Inkling Small (free)Thinkingmachinestext, image, audio → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.000Output / 1M$0.000
TypeSafe: Jev RouterTypesafeaudio, file, image, text, video → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M—Output / 1M—
ParetoUnbiasedtext, image → text262,144 context windowupdated 10/14/2026max tokensresponse formattemperaturetool choiceInput / 1M$2.50Output / 1M$7.50
Pareto 26.10Unbiasedtext, image → text1,048,576 context windowupdated 10/18/2026max tokenstemperaturetool choiceTools / function callingInput / 1M$0.800Output / 1M$3.20
Pareto 26.10 PreviewUnbiasedtext, image → text1,048,576 context windowupdated 10/15/2026max tokenstemperaturetool choiceTools / function callingInput / 1M$0.800Output / 1M$3.20
Pareto 26.9Unbiasedtext, image → text262,144 context windowupdated 10/18/2026max tokensresponse formattemperaturetool choiceInput / 1M$2.50Output / 1M$7.50
ReMM SLERP 13BUndi95text → text6,144 context windowupdated 10/18/2026frequency penaltylogit biaslogprobsmax tokensInput / 1M$0.350Output / 1M$0.650
Upstage: Solar Mini 4Upstagetext → text524,288 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensparallel tool callsInput / 1M$0.050Output / 1M$0.200
Upstage: Solar Pro 3Upstagetext → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensparallel tool callsInput / 1M$0.150Output / 1M$0.600
Upstage: Solar Pro 4Upstagetext → text524,288 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensparallel tool callsInput / 1M$0.090Output / 1M$0.360
Writer: Palmyra X5Writertext → text1,040,000 context windowupdated 10/18/2026max tokensstoptemperaturetop kInput / 1M$0.600Output / 1M$6.00
SpaceXAI: Grok 4.20X Aitext, image, file → text2,000,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$1.25Output / 1M$2.50
SpaceXAI: Grok 4.20 Multi-AgentX Aitext, image, file → text2,000,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$1.25Output / 1M$2.50
SpaceXAI: Grok 4.3X Aitext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$1.25Output / 1M$2.50
SpaceXAI: Grok 4.3 (batch)X Aitext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$1.00Output / 1M$2.00
SpaceXAI: Grok 4.5X Aitext, image, file → text500,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$2.00Output / 1M$6.00
SpaceXAI: Grok 4.6X Aitext, image, file → text500,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$2.00Output / 1M$6.00
SpaceXAI: Grok 4.7X Aitext, image, file → text500,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$2.00Output / 1M$6.00
SpaceXAI: Grok Build 0.1X Aitext, image, file → text256,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$1.00Output / 1M$2.00
Xiaomi: MiMo-V2.5Xiaomitext, audio, image, video → text1,050,000 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.140Output / 1M$0.280
Xiaomi: MiMo-V2.5-ProXiaomitext → text1,050,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$0.435Output / 1M$0.870
Xiaomi: MiMo-V2.6-FlashXiaomitext, image, video, audio → text1,050,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.140Output / 1M$0.280
Xiaomi: MiMo-V2.6-ProXiaomitext, image, video, audio → text1,050,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.435Output / 1M$0.870
Xiaomi: MiMo-V2.6-Pro-UltraSpeedXiaomitext, image, video, audio → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$4.35Output / 1M$8.70
MiMo-V2.5XiaomiMiMotext → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.140Output / 1M$0.280
MiMo-V2.5-ProXiaomiMiMotext → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.522Output / 1M$1.04
MiMo-V2.6-Flash-RLXiaomiMiMotext → text1,048,576 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.140Output / 1M$0.280
MiMo-V2.6-Pro-RLXiaomiMiMotext → text1,048,576 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.435Output / 1M$0.870
XingChen: Xing4.0 29B A4B (free)Xingchen Agitext → text262,144 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokensmin pInput / 1M$0.000Output / 1M$0.000
Z.ai: GLM 4.5Z Aitext → text131,072 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$0.600Output / 1M$2.20
Z.ai: GLM 4.5 AirZ Aitext → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.130Output / 1M$0.850
Z.ai: GLM 4.5VZ Aitext, image → text65,536 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.600Output / 1M$1.80
Z.ai: GLM 4.6Z Aitext → text204,800 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.500Output / 1M$2.00
Z.ai: GLM 4.6VZ Aiimage, text, video → text131,072 context windowupdated 10/18/2026frequency penaltyinclude reasoningmax tokenspresence penaltyInput / 1M$0.300Output / 1M$0.900
Z.ai: GLM 4.7Z Aitext → text204,800 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.540Output / 1M$1.98
Z.ai: GLM 4.7 FlashZ Aitext → text200,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.0605Output / 1M$0.400
Z.ai: GLM 5Z Aitext → text204,800 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$1.00Output / 1M$3.20
Z.ai: GLM 5 TurboZ Aitext → text202,752 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$1.20Output / 1M$4.00
Z.ai: GLM 5.1Z Aitext → text204,800 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.966Output / 1M$3.04
Z.ai: GLM 5.2Z Aitext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.620Output / 1M$2.42
Z.ai: GLM 5.2 (batch)Z Aitext → text1,048,576 context windowupdated 9/22/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.700Output / 1M$2.20
Z.ai: GLM 5.2 (free)Z Aitext → text131,072 context windowupdated 9/25/2026frequency penaltyinclude reasoningmax tokensmin pInput / 1M$0.000Output / 1M$0.000
Z.ai: GLM 5.3Z Aitext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.079Output / 1M$1.40
Z.ai: GLM 5.3 (batch)Z Aitext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biasmax tokensInput / 1M$0.450Output / 1M$2.00
Z.ai: GLM 5.3 FlashZ Aitext, image, video → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.048Output / 1M$0.200
Z.ai: GLM 5.3 Flash (batch)Z Aitext, image, video → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.050Output / 1M$0.180
Z.ai: GLM 5.3 FlashXZ Aitext, image, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.370Output / 1M$1.25
Z.ai: GLM 5.3 PrimeZ Aitext → text1,000,000 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogprobsmax tokensInput / 1M$2.80Output / 1M$8.80
Z.ai: GLM 5V TurboZ Aiimage, text, video → text202,752 context windowupdated 10/18/2026include reasoningmax tokensReasoningresponse formatInput / 1M$1.20Output / 1M$4.00
AutoGLM-Phone-9B-MultilingualZai Orgtext, image → text65,536 context windowupdated 10/18/2026Input / 1M$0.035Output / 1M$0.138
GLM-4.5Zai Orgtext → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
GLM-4.5-AirZai Orgtext → text131,072 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.130Output / 1M$0.850
GLM-4.5VZai Orgtext, image → text65,536 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.600Output / 1M$1.80
GLM-4.5V-FP8Zai Orgtext, image → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
GLM-4.6Zai Orgtext → text204,800 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.500Output / 1M$2.00
GLM-4.6-FP8Zai Orgtext → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
GLM-4.6VZai Orgtext, image → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
GLM-4.6V-FP8Zai Orgtext, image → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
GLM-4.6V-FlashZai Orgtext, image → text131,072 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.300Output / 1M$0.900
GLM-4.7Zai Orgtext → text204,800 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.400Output / 1M$1.75
GLM-4.7-FP8Zai Orgtext → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
GLM-4.7-FlashZai Orgtext → text202,752 context windowupdated 10/18/2026Tools / function callingInput / 1M$0.060Output / 1M$0.400
GLM-5Zai Orgtext → text202,800 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.600Output / 1M$2.08
GLM-5.1Zai Orgtext → text202,752 context windowupdated 10/18/2026Tools / function callingInput / 1M$1.05Output / 1M$3.50
GLM-5.1-FP8Zai Orgtext → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
GLM-5.2Zai Orgtext → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.750Output / 1M$2.40
GLM-5.2-FP8Zai Orgtext → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
GLM-5.3Zai Orgtext → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.900Output / 1M$4.00
GLM-5.3-BF16Zai Orgtext → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
GLM-5.3-FlashZai Orgtext, image → text1,048,576 context windowupdated 10/18/2026Tools / function callingstructured outputInput / 1M$0.075Output / 1M$0.250
GLM-5.3-Flash-BF16Zai Orgtext, image → textContext unavailableupdated 10/18/2026Tools / function callingInput / 1M—Output / 1M—
Anthropic: Claude Fable Latest~anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$10.00Output / 1M$50.00
Anthropic: Claude Haiku Latest~anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.100Output / 1M$0.500
Anthropic: Claude Opus Latest~anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$4.00Output / 1M$20.00
Anthropic: Claude Sonnet Latest~anthropictext, image, file → text1,000,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$10.00
DeepSeek: DeepSeek Flash Latest~deepseektext, image → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.050Output / 1M$0.600
DeepSeek: DeepSeek Pro Latest~deepseektext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.120Output / 1M$8.00
DeepSeek: DeepSeek V4 Flash Latest~deepseektext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.0052Output / 1M$0.120
Google: Gemini Flash Latest~googletext, image, video, file, audio → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$0.750Output / 1M$3.75
Google: Gemini Pro Latest~googleaudio, file, image, text, video → text1,048,576 context windowupdated 10/18/2026include reasoningmax tokensReasoningreasoning effortInput / 1M$2.00Output / 1M$10.00
MoonshotAI: Kimi Latest~moonshotaitext, image, video → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.249Output / 1M$11.94
OpenAI GPT Latest~openaifile, image, text → text1,050,000 context windowupdated 9/11/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$10.00
OpenAI: GPT Astra Latest~openaifile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$10.00Output / 1M$50.00
OpenAI: GPT Luna Latest~openaifile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.100Output / 1M$0.500
OpenAI: GPT Mini Latest~openaifile, image, text → text400,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$0.750Output / 1M$4.50
OpenAI: GPT Sol Latest~openaifile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$10.00
OpenAI: GPT Terra Latest~openaifile, image, text → text1,050,000 context windowupdated 10/18/2026include reasoningmax completion tokensmax tokensReasoningInput / 1M$2.00Output / 1M$12.00
Pareto Latest~unbiasedtext, image → text1,048,576 context windowupdated 10/18/2026max tokenstemperaturetool choiceTools / function callingInput / 1M$0.800Output / 1M$3.20
xAI: Grok Latest~x Aitext, image, file → text500,000 context windowupdated 10/18/2026include reasoninglogprobsmax tokensReasoningInput / 1M$2.00Output / 1M$6.00
Z.ai: GLM Flash Latest~z Aitext, image, video → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.048Output / 1M$0.200
Z.ai: GLM Latest~z Aitext → text1,048,576 context windowupdated 10/18/2026frequency penaltyinclude reasoninglogit biaslogprobsInput / 1M$0.075Output / 1M$2.20