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

ModelVendorHostVariantInputOutputBlended ↑?Cache readCache writeBatch inBatch outContextTokenizerLast changeConfidence?Source
gpt-oss-20b (GovCloud)openrouterdeepinfra–0.03000.00850.140.03940.05750.0162–n/a–n/a–n/a–n/a131072o200k2026-08-27 ↓aggregatorlitellm
Llama 3.1 8Bmetagroq–0.0500n/a0.0800n/a0.0575n/a–n/a–n/a–n/a–n/a131072–2024-10-08 ↓aggregatormodelsdev
Mistral-Small-24B-Instruct-2501deepinfradeepinfra–0.0500n/a0.0800n/a0.0575n/a–n/a–n/a–n/a–n/a–––officialofficial-deepinfra
Llama 3.1 8B Instructopenroutergroq–0.05000.01500.08000.02410.05750.01730.02500.0075–n/a–n/a–n/a16384llama3–apiopenrouter
Inference.net: Schematron V2 Turboopenrouteropenrouter–0.0300n/a0.15n/a0.0600n/a0.0300n/a–n/a–n/a–n/a128000––apiopenrouter
Inference.net: Schematron V2 Turboopenrouterinferencenetunknown0.0300n/a0.15n/a0.0600n/a0.0300n/a–n/a–n/a–n/a128000––apiopenrouter
gpt-oss-20b (GovCloud)openrouterparasailfp40.03000.00850.150.04230.06000.01690.02000.0056–n/a–n/a–n/a131072o200k–apiopenrouter
mistralai/Mistral-Nemo-Instruct-2407mistralnebius–0.0400n/a0.12n/a0.0600n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
us-gov-west-1/google.gemma-4-e2baws-bedrockaws-bedrock–0.0480n/a0.0960n/a0.0600n/a–n/a–n/a–n/a–n/a128000––aggregatorlitellm
Meta: Llama 3.2 1B Instructopenroutertogether–0.06000.01810.06000.01810.06000.0181–n/a–n/a–n/a–n/a60000llama3–aggregatorlitellm
Llama 3.2 3B Instructopenroutertogether–0.06000.01810.06000.01810.06000.0181–n/a–n/a–n/a–n/a32768llama3–aggregatorlitellm
ideogram-40togethertogether––n/a0.0600n/a0.0600n/a–n/a–n/a–n/a–n/a–––officialofficial-together
ideogram-3-0togethertogether–0.0600n/a–n/a0.0600n/a–n/a–n/a–n/a–n/a–––officialofficial-together
google-imagen-4-0-ultratogethertogether–0.0600n/a–n/a0.0600n/a–n/a–n/a–n/a–n/a–––officialofficial-together
Inference.net: Schematron V2 Turboopenrouterinferencenet–0.0300n/a0.15n/a0.0600n/a0.0300n/a–n/a–n/a–n/a128000––apiopenrouter
AutoGLM-Phone-9B-Multilingualnovitanovita–0.0350n/a0.14n/a0.0608n/a–n/a–n/a–n/a–n/a65536–2026-01-13 ↓aggregatorlitellm
Qwen3 8Balibabanovita–0.0350n/a0.14n/a0.0608n/a–n/a–n/a–n/a–n/a128000–2026-01-13 ↓aggregatorlitellm
Amazon: Nova Micro 1.0openrouteropenrouter–0.0350n/a0.14n/a0.0613n/a–n/a–n/a–n/a–n/a128000––apiopenrouter
Amazon: Nova Micro 1.0openrouteraws-bedrockunknown0.0350n/a0.14n/a0.0613n/a–n/a–n/a–n/a–n/a128000––apiopenrouter
Amazon: Nova Micro 1.0openrouteraws-bedrockunknown0.0350n/a0.14n/a0.0613n/a–n/a–n/a–n/a–n/a128000––apiopenrouter
Amazon Nova Microamazonaws-bedrock–0.0350n/a0.14n/a0.0613n/a0.0088n/a–n/a–n/a–n/a128000––aggregatorlitellm
Amazon Nova Microamazonamazon–0.0350n/a0.14n/a0.0613n/a–n/a–n/a–n/a–n/a128000––aggregatorlitellm
Amazon Nova Microamazonaws-bedrock–0.0350n/a0.14n/a0.0613n/a0.0088n/a–n/a–n/a–n/a128000––aggregatorlitellm
Amazon: Nova Micro 1.0openrouteraws-bedrock–0.0350n/a0.14n/a0.0613n/a–n/a–n/a–n/a–n/a128000––apiopenrouter
Amazon: Nova Micro 1.0openrouteraws-bedrock–0.0350n/a0.14n/a0.0613n/a–n/a–n/a–n/a–n/a128000––apiopenrouter
inclusionAI: Ling 3.0 Flash Finopenrouteropenrouter–0.0420n/a0.12n/a0.0623n/a0.0084n/a–n/a–n/a–n/a262144––apiopenrouter
inclusionAI: Ling 3.0 Flash Finopenrouternovitaunknown0.0420n/a0.12n/a0.0623n/a0.0084n/a–n/a–n/a–n/a262144––apiopenrouter
inclusionAI: Ling 3.0 Flash Finopenrouternovita–0.0420n/a0.12n/a0.0623n/a0.0084n/a–n/a–n/a–n/a262144––apiopenrouter
Gemma 3 4B ITopenrouteropenrouter–0.0500n/a0.10n/a0.0625n/a–n/a–n/a–n/a–n/a131072gemini–apiopenrouter
Gemma 3 4B ITopenrouterdeepinfra–0.0500n/a0.10n/a0.0625n/a–n/a–n/a–n/a–n/a131072gemini–apiopenrouter
Gemma 3 4B ITopenrouterdeepinfra–0.0500n/a0.10n/a0.0625n/a–n/a–n/a–n/a–n/a131072gemini2026-08-27 ↑aggregatorlitellm
Llama 4 Maverickmetalambda discontinued–0.05000.01500.100.03010.06250.0188–n/a–n/a–n/a–n/a1000000llama3–aggregatorlitellm
Llama 4 Scoutmetalambda discontinued–0.05000.01500.100.03010.06250.0188–n/a–n/a–n/a–n/a10000000llama3–aggregatorlitellm
qwen25-coder-32b-instructalibabalambda discontinued–0.0500n/a0.10n/a0.0625n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
qwen3-32b-fp8alibabalambda discontinued–0.0500n/a0.10n/a0.0625n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
Gemma 3 12Bopenrouternovita–0.0500n/a0.10n/a0.0625n/a–n/a–n/a–n/a–n/a131072gemini2026-01-13 ↓aggregatorlitellm
gemma-3-4b-itdeepinfradeepinfra–0.0500n/a0.10n/a0.0625n/a–n/a–n/a–n/a–n/a–––officialofficial-deepinfra
Amazon Nova Microamazonaws-bedrock–0.0370n/a0.15n/a0.0648n/a0.0093n/a–n/a–n/a–n/a128000––aggregatorlitellm
gpt-oss-120bopenroutercoreweavefp40.03000.00850.170.04790.06500.01830.03000.0085–n/a–n/a–n/a131072o200k–apiopenrouter
Command R7Bopenrouteropenrouter–0.0375n/a0.15n/a0.0656n/a–n/a–n/a–n/a–n/a128000––apiopenrouter
Command R7Bopenroutercohereunknown0.0375n/a0.15n/a0.0656n/a–n/a–n/a–n/a–n/a128000––apiopenrouter
Command R7Bopenroutercohere–0.0375n/a0.15n/a0.0656n/a–n/a–n/a–n/a–n/a128000–2026-06-18 ↓aggregatorlitellm
Command R7B Arabiccoherecohere–0.0375n/a0.15n/a0.0656n/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
Command R7Bcoherecohere–0.0375n/a0.15n/a0.0656n/a–n/a–n/a–n/a–n/a–––officialofficial-cohere
Command R7Bopenroutercohere–0.0375n/a0.15n/a0.0656n/a–n/a–n/a–n/a–n/a128000––apiopenrouter
DeepSeek V4 Flash 0731openrouterstreamlakefp80.04400.01440.130.04330.06600.02160.00140.0005–n/a–n/a–n/a1000000deepseek–apiopenrouter
Inception: Mercury 2.5openrouteropenrouter–0.0400n/a0.15n/a0.0675n/a0.0040n/a–n/a–n/a–n/a260000––apiopenrouter
Inception: Mercury 2.5openrouterinceptionunknown0.0400n/a0.15n/a0.0675n/a0.0040n/a–n/a–n/a–n/a260000––apiopenrouter
gpt-oss-120bopenrouterdekallm–0.03000.00850.180.05070.06750.01900.03000.0085–n/a–n/a–n/a131072o200k–apiopenrouter
gpt-oss-20b (GovCloud)openrouternovitafp40.04000.01130.150.04230.06750.0190–n/a–n/a–n/a–n/a131072o200k–apiopenrouter

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