Offerings

Every active offering: a model as served by one host, with its current canonical price. Sort by clicking a column header; filter with the row below. Prices are USD per 1M tokens unless the unit toggle is set to per 1M characters (an approximation using a measured, blended tokens-per-character ratio).

Showing every active offering, including the long tail. Show curated models only

More columns: - Vendor + Region + Cache + Batch - Tokenizer - Last change + Source All columns Default columns

ModelVendorHostVariantRegionInputOutputBlended ↑?ContextTokenizerLast changeConfidence?
Mistral Small 3Mistral AIOpenRouter––0.05000.08000.057532,768mistral–api
gpt-oss-20b 3 sourcesOpenAIDeepInfra––0.03000.1400.0575131,072o200k2026-08-27 ↓api
Mistral Small 3Mistral AIDeepInfrafp8–0.05000.08000.057532,768mistral–api
Llama 3.1 8B InstructMetaGroq––0.05000.08000.0575131,072llama3–api
Mistral Small 3 3 sourcesMistral AIDeepInfra––0.05000.08000.057532,768mistral–official
Llama 3.1 8BMetaGroq––0.05000.08000.0575131,072–2024-10-08 ↓aggregator
Schematron V2 TurboOpenRouterOpenRouter––0.03000.1500.0600128,000––api
Schematron V2 TurboOpenRouterInference.net––0.03000.1500.0600128,000––api
gpt-oss-20bOpenAIParasailfp4–0.03000.1500.0600131,072o200k–api
Mistral-Nemo-Instruct-2407Mistral AINebius AI Studio––0.04000.1200.0600131,072––aggregator
Llama 3.2 1B InstructMetaTogether AI––0.06000.06000.060060,000llama3–aggregator
Llama 3.2 3B InstructMetaTogether AI––0.06000.06000.0600131,072llama3–aggregator
ideogram-40Together AITogether AI–––0.06000.0600–––official
ideogram-3-0Together AITogether AI–––0.06000.0600–––official
Gemma 4 E2B ITGoogleAWS Bedrock–us-gov-west-10.04800.09600.0600128,000––aggregator
gpt-oss-120bOpenAIVeniceint4–0.03000.1500.0600131,072o200k–api
Gemma 3 12BGoogleDeepInfraflex–0.04000.1200.0600131,072gemini–api
gpt-oss-120bOpenAINEAR AIfp4–0.03000.1500.0600131,072o200k–api
Schematron V2 TurboOpenRouterInference.net–us0.03000.1500.0600128,000––api
gpt-oss-120bOpenAIio.netfp4–0.03000.1500.0600131,072o200k–api
Gemma 3 4BGoogleAWS Bedrock–ap-south-10.05000.09000.0600131,072gemini–aggregator
Gemma 3 4BGoogleAWS Bedrock–ap-southeast-30.04800.09600.0600131,072gemini–aggregator
Gemma 3 4BGoogleAWS Bedrock–eu-central-10.04800.09600.0600131,072gemini–aggregator
Gemma 3 4BGoogleAWS Bedrock–eu-north-10.04800.09600.0600131,072gemini–aggregator
Gemma 3 4BGoogleAWS Bedrock–eu-south-10.05000.09000.0600131,072gemini–aggregator
Gemma 3 4BGoogleAWS Bedrock–eu-west-10.05000.09000.0600131,072gemini–aggregator
Gemma 4 E2B ITGoogleAWS Bedrock–eu-central-10.04800.09600.0600128,000––aggregator
AutoGLM Phone 9B Multilingual 2 sourcesZhipu AI (Z.ai)Novita AI––0.03500.1380.060865,536–2026-01-13 ↓aggregator
Qwen3 8B 2 sourcesAlibaba CloudNovita AI––0.03500.1380.0608128,000–2026-01-13 ↓aggregator
Nova Micro 1.0AmazonOpenRouter––0.03500.1400.0613128,000––api
Nova Micro 1.0AmazonAWS Bedrock–eu-west-10.03500.1400.0613128,000––api
Nova Micro 1.0AmazonAWS Bedrock––0.03500.1400.0613128,000––api
Amazon Nova Micro 2 sourcesAmazonAWS Bedrock––0.03500.1400.0613128,000––aggregator
Amazon Nova MicroAmazonAmazon––0.03500.1400.0613128,000––aggregator
Amazon Nova MicroAmazonAWS Bedrock–us0.03500.1400.0613128,000––aggregator
Hy4 flashTencent CloudOpenRouter––0.03500.1410.06141,048,576––api
Gemma 3 4BGoogleOpenRouter––0.05000.1000.0625131,072gemini–api
Gemma 3 4B 4 sourcesGoogleDeepInfra––0.05000.1000.0625131,072gemini2026-08-27 ↑official
Llama 4 MaverickMetaLambda discontinued––0.05000.1000.06251,000,000llama3–aggregator
Llama 4 ScoutMetaLambda discontinued––0.05000.1000.062510,000,000llama3–aggregator
Qwen3 32BAlibaba CloudLambda discontinued––0.05000.1000.062540,960––aggregator
Gemma 3 12B 2 sourcesGoogleNovita AI––0.05000.1000.0625131,072gemini2026-01-13 ↓aggregator
Qwen3.5-9BAlibaba CloudPrime Intellect––0.05600.08200.0625262,144qwen2–api
Gemma 3 4BGoogleAWS Bedrock–ap-northeast-10.05000.1000.0625131,072gemini–aggregator
Gemma 3 4BGoogleAWS Bedrock–sa-east-10.05000.1000.0625131,072gemini–aggregator
Qwen3.7 FlashAlibaba CloudAlibaba Cloud–us-east-10.03450.1500.06331,000,000qwen2–api
Amazon Nova MicroAmazonAWS Bedrock–apac0.03700.1480.0648128,000––aggregator
gpt-oss-120bOpenAICoreWeavefp4–0.03000.1700.0650131,072o200k–api
Command R7B (12-2024)CohereOpenRouter––0.03750.1500.0656128,000––api
Command R7B (12-2024) 3 sourcesCohereCohere––0.03750.1500.0656128,000–2026-06-18 ↕api

Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence