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?Source
gpt-oss-safeguard-20bOpenAIAWS Bedrock–eu-south-10.08000.2300.118131,072o200k–aggregatorlitellm
gpt-oss-safeguard-20bOpenAIAWS Bedrock–eu-west-10.08000.2300.118131,072o200k–aggregatorlitellm
Nex-N2.5-ProOpenRouterOpenRouter––0.07500.2500.119262,144qwen2–apiopenrouter
Nex-N2.5-ProOpenRouterNex AGIfp8–0.07500.2500.119262,144qwen2–apiopenrouter
GLM 5.3 FlashZhipu AI (Z.ai)Tenstorrentfp8–0.07500.2500.1191,048,576––apiopenrouter
GLM 5.3 FlashZhipu AI (Z.ai)OpenInferencefp4–0.06000.3000.1201,048,576–2026-11-10 ↑apiopenrouter
Llama 3.2 3B InstructMetaParasail––0.05000.3300.120131,072llama3–apiopenrouter
Qwen3 14BAlibaba CloudNebius AI Studio––0.08000.2400.12040,960qwen2–aggregatorlitellm
Qwen/Qwen3-4BAlibaba CloudNebius AI Studio––0.08000.2400.12040,960––aggregatorlitellm
Qwen3 Coder 30B A3B Instruct 2 sourcesAlibaba CloudNovita AI––0.07000.2700.120262,144qwen22026-01-13 ↓aggregatorlitellm
Qwen-Omni TurboAlibaba CloudAlibaba Cloud––0.07000.2700.12032,768––aggregatormodelsdev
Embed 5 ProCohereCohere––0.120–0.120–––officialofficial-cohere
Llama 4 ScoutMetaDeepInfraflex+fp8–0.08000.2400.12010,000,000llama3–apiopenrouter
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–ap-south-10.07000.2700.120128,000––aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–eu-south-10.07000.2700.120128,000––aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–eu-west-10.07000.2700.120128,000––aggregatorlitellm
gpt-oss-safeguard-20bOpenAIAWS Bedrock–ap-northeast-10.08000.2400.120131,072o200k–aggregatorlitellm
gpt-oss-safeguard-20bOpenAIAWS Bedrock–ap-south-10.08000.2400.120131,072o200k–aggregatorlitellm
gpt-oss-safeguard-20bOpenAIAWS Bedrock–sa-east-10.08000.2400.120131,072o200k–aggregatorlitellm
Gemma 4 26B A4BGoogleOpenRouter––0.07650.2550.121262,144gemma–apiopenrouter
Llama 3.2 3B InstructMetaOpenRouter––0.05090.3350.122131,072llama3–apiopenrouter
Llama 3.2 3B InstructMetaCloudflare Workers AI––0.05090.3350.122131,072llama3–apiopenrouter
DeepSeek V4 FlashDeepSeekDigitalOcean––0.09800.1960.1231,048,576deepseek–apiopenrouter
Qwen3 Coder 30B A3B InstructAlibaba CloudSiliconFlowfp8–0.07000.2800.123262,144qwen2–apiopenrouter
mistral.mistral-7b-instruct-v0:2Mistral AIPerplexity––0.07000.2800.12332,000––aggregatorlitellm
Mixtral 8x7B InstructMistral AIPerplexity––0.07000.2800.12332,000––aggregatorlitellm
pplx-7b-chatPerplexityPerplexity––0.07000.2800.1238,192––aggregatorlitellm
sonar-small-chatPerplexityPerplexity––0.07000.2800.12316,384––aggregatorlitellm
ERNIE-4.5-21B-A3B-Thinking 2 sourcesNovita AINovita AI––0.07000.2800.123131,072–2026-01-13 ↓aggregatorlitellm
ERNIE 4.5 21B A3B 2 sourcesNovita AINovita AI––0.07000.2800.123120,000–2026-01-13 ↓aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–ap-south-10.07000.2800.123256,000––aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–eu-south-10.07000.2800.123256,000––aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–eu-west-10.07000.2800.123256,000––aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–ap-northeast-10.07000.2800.123128,000––aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–sa-east-10.07000.2800.123128,000––aggregatorlitellm
Gemma 4 26B A4BGoogleio.net––0.06700.2900.123262,144gemma2026-11-14 ↓apiopenrouter
Hy4 flashTencent CloudTencent Cloud promo −50%fp8–0.07000.2810.1231,048,576––apiopenrouter
Hy4 flashTencent CloudNovita AI––0.07000.2810.1231,048,576––aggregatormodelsdev
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–us-gov-east-10.07200.2760.123128,000––aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–us-gov-west-10.07200.2760.123128,000––aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–us-gov0.07200.2760.123128,000––aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–ap-southeast-30.07200.2760.123128,000––aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–eu-central-10.07200.2760.123128,000––aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–eu-north-10.07200.2760.123128,000––aggregatorlitellm
gpt-oss-safeguard-20bOpenAIAWS Bedrock–ap-southeast-30.08400.2400.123131,072o200k–aggregatorlitellm
gpt-oss-safeguard-20bOpenAIAWS Bedrock–eu-central-10.08400.2400.123131,072o200k–aggregatorlitellm
gpt-oss-safeguard-20bOpenAIAWS Bedrock–eu-north-10.08400.2400.123131,072o200k–aggregatorlitellm
Muse Spark 1.3 ContributorMetaOpenRouter––0.1000.2000.1251,048,576––apiopenrouter
Muse Spark 1.2 ContributorMetaOpenRouter––0.1000.2000.1251,048,576––apiopenrouter
UI-TARS 7BOpenRouterOpenRouter––0.1000.2000.125128,000––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