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

ModelHostVariantRegionInputOutputBlended ↑?Cache readCache writeBatch inBatch outContextLast changeConfidence?Source
gpt-oss-safeguard-20bAWS Bedrock–eu-south-10.08000.2300.118––––131,072–aggregatorlitellm
gpt-oss-safeguard-20bAWS Bedrock–eu-west-10.08000.2300.118––––131,072–aggregatorlitellm
Nex-N2.5-ProOpenRouter––0.07500.2500.1190.0150–––262,144–apiopenrouter
Nex-N2.5-ProNex AGIfp8–0.07500.2500.1190.0150–––262,144–apiopenrouter
GLM 5.3 FlashTenstorrentfp8–0.07500.2500.1190.0150–––1,048,576–apiopenrouter
GLM 5.3 FlashOpenInferencefp4–0.06000.3000.1200.0300–––1,048,5762026-11-10 ↑apiopenrouter
Llama 3.2 3B InstructParasail––0.05000.3300.120––––131,072–apiopenrouter
Qwen3 14BNebius AI Studio––0.08000.2400.120––––40,960–aggregatorlitellm
Qwen/Qwen3-4BNebius AI Studio––0.08000.2400.120––––40,960–aggregatorlitellm
Qwen3 Coder 30B A3B Instruct 2 sourcesNovita AI––0.07000.2700.120––––262,1442026-01-13 ↓aggregatorlitellm
Qwen-Omni TurboAlibaba Cloud––0.07000.2700.120––––32,768–aggregatormodelsdev
Embed 5 ProCohere––0.120–0.120––––––officialofficial-cohere
Llama 4 ScoutDeepInfraflex+fp8–0.08000.2400.120––––10,000,000–apiopenrouter
NVIDIA Nemotron Nano 9B v2AWS Bedrock–ap-south-10.07000.2700.120––––128,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2AWS Bedrock–eu-south-10.07000.2700.120––––128,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2AWS Bedrock–eu-west-10.07000.2700.120––––128,000–aggregatorlitellm
gpt-oss-safeguard-20bAWS Bedrock–ap-northeast-10.08000.2400.120––––131,072–aggregatorlitellm
gpt-oss-safeguard-20bAWS Bedrock–ap-south-10.08000.2400.120––––131,072–aggregatorlitellm
gpt-oss-safeguard-20bAWS Bedrock–sa-east-10.08000.2400.120––––131,072–aggregatorlitellm
Gemma 4 26B A4BOpenRouter––0.07650.2550.1210.0425–––262,144–apiopenrouter
Llama 3.2 3B InstructOpenRouter––0.05090.3350.122––––131,072–apiopenrouter
Llama 3.2 3B InstructCloudflare Workers AI––0.05090.3350.122––––131,072–apiopenrouter
DeepSeek V4 FlashDigitalOcean––0.09800.1960.1230.0196–––1,048,576–apiopenrouter
Qwen3 Coder 30B A3B InstructSiliconFlowfp8–0.07000.2800.123––––262,144–apiopenrouter
mistral.mistral-7b-instruct-v0:2Perplexity––0.07000.2800.123––––32,000–aggregatorlitellm
Mixtral 8x7B InstructPerplexity––0.07000.2800.123––––32,000–aggregatorlitellm
pplx-7b-chatPerplexity––0.07000.2800.123––––8,192–aggregatorlitellm
sonar-small-chatPerplexity––0.07000.2800.123––––16,384–aggregatorlitellm
ERNIE-4.5-21B-A3B-Thinking 2 sourcesNovita AI––0.07000.2800.123––––131,0722026-01-13 ↓aggregatorlitellm
ERNIE 4.5 21B A3B 2 sourcesNovita AI––0.07000.2800.123––––120,0002026-01-13 ↓aggregatorlitellm
nvidia.nemotron-nano-3-30bAWS Bedrock–ap-south-10.07000.2800.123––––256,000–aggregatorlitellm
nvidia.nemotron-nano-3-30bAWS Bedrock–eu-south-10.07000.2800.123––––256,000–aggregatorlitellm
nvidia.nemotron-nano-3-30bAWS Bedrock–eu-west-10.07000.2800.123––––256,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2AWS Bedrock–ap-northeast-10.07000.2800.123––––128,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2AWS Bedrock–sa-east-10.07000.2800.123––––128,000–aggregatorlitellm
Gemma 4 26B A4Bio.net––0.06700.2900.1230.0390–––262,1442026-11-14 ↓apiopenrouter
Hy4 flashTencent Cloud promo −50%fp8–0.07000.2810.1230.003000–––1,048,576–apiopenrouter
Hy4 flashNovita AI––0.07000.2810.1230.003000–––1,048,576–aggregatormodelsdev
NVIDIA Nemotron Nano 9B v2AWS Bedrock–us-gov-east-10.07200.2760.123––0.03600.144128,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2AWS Bedrock–us-gov-west-10.07200.2760.123––0.03600.144128,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2AWS Bedrock–us-gov0.07200.2760.123––––128,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2AWS Bedrock–ap-southeast-30.07200.2760.123––––128,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2AWS Bedrock–eu-central-10.07200.2760.123––––128,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2AWS Bedrock–eu-north-10.07200.2760.123––––128,000–aggregatorlitellm
gpt-oss-safeguard-20bAWS Bedrock–ap-southeast-30.08400.2400.123––––131,072–aggregatorlitellm
gpt-oss-safeguard-20bAWS Bedrock–eu-central-10.08400.2400.123––––131,072–aggregatorlitellm
gpt-oss-safeguard-20bAWS Bedrock–eu-north-10.08400.2400.123––––131,072–aggregatorlitellm
Muse Spark 1.3 ContributorOpenRouter––0.1000.2000.1250.002000–––1,048,576–apiopenrouter
Muse Spark 1.2 ContributorOpenRouter––0.1000.2000.1250.002000–––1,048,576–apiopenrouter
UI-TARS 7BOpenRouter––0.1000.2000.1250.100–––128,000–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