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 ↑?Cache readCache writeContextConfidence?
Mistral Small 3Mistral AIOpenRouter––0.05000.08000.0575––32,768api
gpt-oss-20b 3 sourcesOpenAIDeepInfra––0.03000.1400.05750.0150–131,072api
Mistral Small 3Mistral AIDeepInfrafp8–0.05000.08000.0575––32,768api
Llama 3.1 8B InstructMetaGroq––0.05000.08000.05750.0250–131,072api
Mistral Small 3 3 sourcesMistral AIDeepInfra––0.05000.08000.0575––32,768official
Llama 3.1 8BMetaGroq––0.05000.08000.0575––131,072aggregator
Schematron V2 TurboOpenRouterOpenRouter––0.03000.1500.06000.0300–128,000api
Schematron V2 TurboOpenRouterInference.net––0.03000.1500.06000.0300–128,000api
gpt-oss-20bOpenAIParasailfp4–0.03000.1500.06000.0200–131,072api
Mistral-Nemo-Instruct-2407Mistral AINebius AI Studio––0.04000.1200.0600––131,072aggregator
Llama 3.2 1B InstructMetaTogether AI––0.06000.06000.0600––60,000aggregator
Llama 3.2 3B InstructMetaTogether AI––0.06000.06000.0600––131,072aggregator
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-10.04800.09600.0600––128,000aggregator
gpt-oss-120bOpenAIVeniceint4–0.03000.1500.06000.0300–131,072api
Gemma 3 12BGoogleDeepInfraflex–0.04000.1200.0600––131,072api
gpt-oss-120bOpenAINEAR AIfp4–0.03000.1500.06000.0150–131,072api
Schematron V2 TurboOpenRouterInference.net–us0.03000.1500.06000.0300–128,000api
gpt-oss-120bOpenAIio.netfp4–0.03000.1500.06000.0150–131,072api
Gemma 3 4BGoogleAWS Bedrock–ap-south-10.05000.09000.0600––131,072aggregator
Gemma 3 4BGoogleAWS Bedrock–ap-southeast-30.04800.09600.0600––131,072aggregator
Gemma 3 4BGoogleAWS Bedrock–eu-central-10.04800.09600.0600––131,072aggregator
Gemma 3 4BGoogleAWS Bedrock–eu-north-10.04800.09600.0600––131,072aggregator
Gemma 3 4BGoogleAWS Bedrock–eu-south-10.05000.09000.0600––131,072aggregator
Gemma 3 4BGoogleAWS Bedrock–eu-west-10.05000.09000.0600––131,072aggregator
Gemma 4 E2B ITGoogleAWS Bedrock–eu-central-10.04800.09600.0600––128,000aggregator
AutoGLM Phone 9B Multilingual 2 sourcesZhipu AI (Z.ai)Novita AI––0.03500.1380.0608––65,536aggregator
Qwen3 8B 2 sourcesAlibaba CloudNovita AI––0.03500.1380.0608––128,000aggregator
Nova Micro 1.0AmazonOpenRouter––0.03500.1400.0613––128,000api
Nova Micro 1.0AmazonAWS Bedrock–eu-west-10.03500.1400.0613––128,000api
Nova Micro 1.0AmazonAWS Bedrock––0.03500.1400.0613––128,000api
Amazon Nova Micro 2 sourcesAmazonAWS Bedrock––0.03500.1400.06130.0087500.0350128,000aggregator
Amazon Nova MicroAmazonAmazon––0.03500.1400.0613––128,000aggregator
Amazon Nova MicroAmazonAWS Bedrock–us0.03500.1400.06130.008750–128,000aggregator
Hy4 flashTencent CloudOpenRouter––0.03500.1410.06140.001500–1,048,576api
Gemma 3 4BGoogleOpenRouter––0.05000.1000.0625––131,072api
Gemma 3 4B 4 sourcesGoogleDeepInfra––0.05000.1000.0625––131,072official
Llama 4 MaverickMetaLambda discontinued––0.05000.1000.0625––1,000,000aggregator
Llama 4 ScoutMetaLambda discontinued––0.05000.1000.0625––10,000,000aggregator
Qwen3 32BAlibaba CloudLambda discontinued––0.05000.1000.0625––40,960aggregator
Gemma 3 12B 2 sourcesGoogleNovita AI––0.05000.1000.0625––131,072aggregator
Qwen3.5-9BAlibaba CloudPrime Intellect––0.05600.08200.06250.0500–262,144api
Gemma 3 4BGoogleAWS Bedrock–ap-northeast-10.05000.1000.0625––131,072aggregator
Gemma 3 4BGoogleAWS Bedrock–sa-east-10.05000.1000.0625––131,072aggregator
Qwen3.7 FlashAlibaba CloudAlibaba Cloud–us-east-10.03450.1500.06330.006900–1,000,000api
Amazon Nova MicroAmazonAWS Bedrock–apac0.03700.1480.06480.009250–128,000aggregator
gpt-oss-120bOpenAICoreWeavefp4–0.03000.1700.06500.0300–131,072api
Command R7B (12-2024)CohereOpenRouter––0.03750.1500.0656––128,000api
Command R7B (12-2024) 3 sourcesCohereCohere––0.03750.1500.0656––128,000api

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