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 writeBatch inBatch outContextLast changeConfidence?Source
Nemotron 3.5 LightningNVIDIAModelRunfp4–0.07000.2000.1030.0400–––1,048,576–apiopenrouter
gpt-oss-120bOpenAIMancerfp8–0.05500.2500.1040.0550–––131,0722026-11-02 ↑apiopenrouter
Nemotron 3 Nano 30B A3BNVIDIAOpenRouter––0.06000.2400.1050.0120–––262,144–apiopenrouter
Nova Lite 1.0AmazonOpenRouter––0.06000.2400.105––––300,000–apiopenrouter
Nemotron 3 Nano 30B A3BNVIDIANebius AI Studiofp8–0.06000.2400.1050.0120–––262,144–apiopenrouter
Nova Lite 1.0AmazonAWS Bedrock–eu-west-10.06000.2400.105––––300,000–apiopenrouter
Nova Lite 1.0AmazonAWS Bedrock––0.06000.2400.105––––300,000–apiopenrouter
Amazon Nova Lite 2 sourcesAmazonAWS Bedrock––0.06000.2400.1050.01500.06000.03000.120300,000–aggregatorlitellm
Model Router 2 sourcesAzure AI FoundryAzure AI Foundry––0.140free0.105––––200,000–aggregatorlitellm
Amazon Nova LiteAmazonAmazon––0.06000.2400.105––––300,000–aggregatorlitellm
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3BNVIDIANebius AI Studio––0.06000.2400.1050.0120–––262,144–aggregatorlitellm
nvidia/Nemotron-3-Nano-OmniNVIDIANebius AI Studio––0.06000.2400.105––––262,144–aggregatorlitellm
Nemotron 3.5 Lightning 2 sourcesNVIDIANebius AI Studio––0.06000.2400.1050.0300–––1,048,576–aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock––0.06000.2400.105––0.03000.120256,000–aggregatorlitellm
DeepSeek V4 Flash 0731DeepSeekDeepInfra––0.08000.1800.1050.0160–––1,048,576–aggregatorbackfill-litellm
Nemotron 3 Nano 30B A3BNVIDIAAWS Bedrock––0.06000.2400.105––––262,144–aggregatormodelsdev
Amazon Nova LiteAmazonAWS Bedrock–us0.06000.2400.1050.0150–0.03000.120300,000–aggregatorlitellm
NVIDIA Nemotron Nano 9B v2NVIDIAAWS Bedrock–ap-southeast-20.06180.2370.106––––128,000–aggregatorlitellm
gpt-oss-safeguard-20bOpenAIAWS Bedrock–ap-southeast-20.07210.2060.106––––131,072–aggregatorlitellm
Mistral Small 3.2 24BMistral AIOpenRouter––0.07500.2000.106––––256,000–apiopenrouter
Mistral Small 3.2 24BMistral AIDeepInfrafp8–0.07500.2000.106––––256,000–apiopenrouter
Mistral-Small-3.2-24B-Instruct-2506 2 sourcesMistral AIDeepInfra––0.07500.2000.106––––128,0002025-10-04 ↑officialofficial-deepinfra
Granite 4.2 8BOpenRouterDeepInfra––0.06000.2500.1080.0150–––131,072–apiopenrouter
nvidia/NVIDIA-Nemotron-Nano-9B-v2NVIDIATogether AI––0.06000.2500.108––––131,072–aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–ap-southeast-20.06180.2470.108––––256,000–aggregatorlitellm
GLM 5.3 FlashZhipu AI (Z.ai)Wafernvfp4–0.06500.2400.1090.0640–––1,048,5762026-11-11 ↑apiopenrouter
Ministral 3 3B 2512Mistral AIMistral AI–eu0.1100.1100.1100.0110–––131,072–apiopenrouter
LFM3-1.7BLiquid AILiquid AIfp8–0.08000.2000.1100.0200–––262,144–apiopenrouter
LFM3-1.7BLiquid AIOpenRouter––0.08000.2000.1100.0200–––262,144–apiopenrouter
eu.meta.llama3-2-1b-instruct-v1:0MetaAWS Bedrock–eu-west-10.1100.1100.110––––128,000–aggregatorlitellm
Amazon Nova LiteAmazonAWS Bedrock–apac0.06300.2520.1100.0158–––300,000–aggregatorlitellm
Ling 3.0 Flash VL 2 sourcesOpenRouterNovita AI promo −72%––0.07500.2200.1110.0150–––131,072–apiopenrouter
Ling 3.0 Flash Fin 2 sourcesOpenRouterNovita AI promo −44%––0.07500.2200.1110.0150–––262,144–apiopenrouter
Ling 3.0 Flash Sante 2 sourcesOpenRouterNovita AI promo −44%––0.07500.2200.1110.0150–––262,144–apiopenrouter
GLM 5.3 FlashZhipu AI (Z.ai)particle-aiflex+nvfp4–0.06500.2500.1110.0200–––1,048,576–apiopenrouter
DeepSeek V4 FlashDeepSeekOpenRouter––0.09000.1800.1130.0180–––1,048,576–apiopenrouter
DeepSeek V4 FlashDeepSeekDeepInfrafp8–0.09000.1800.1130.0180–––1,048,576–apiopenrouter
Qwen3.5-9BAlibaba CloudSiliconFlowfp8–0.1000.1500.113––––262,144–apiopenrouter
Qwen3.5-9B 4 sourcesAlibaba CloudDeepInfra––0.1000.1500.113––––262,144–officialofficial-deepinfra
DeepSeek V4 Flash 2 sourcesDeepSeekDeepInfra––0.09000.1800.1130.01800.113––1,048,576–aggregatorlitellm
Gemini Embedding 001GoogleGoogle––0.150free0.113––––2,048–aggregatormodelsdev
Gemini Embedding 001GoogleGoogle Vertex AI––0.150free0.113––––2,048–aggregatormodelsdev
DeepSeek-V4-FlashDeepInfraDeepInfra––0.09000.1800.1130.0180–––1,000,000–officialofficial-deepinfra
Gemma 3 12BGoogleDeepInfrapriority–0.07500.2250.113––––131,072–apiopenrouter
Gemma 4 26B A4BGoogleAkashMLfp4–0.07000.2400.1130.0460–––262,144–apiopenrouter
DeepSeek V4 Flash 0731DeepSeekWafernvfp4us0.05000.3000.1130.0350–––1,048,5762026-11-19 ↑apiopenrouter
Qwen3.5-FlashAlibaba CloudOpenRouter––0.06500.2600.114––––1,000,000–apiopenrouter
Qwen3.5-FlashAlibaba CloudAlibaba Cloud––0.06500.2600.114––––1,000,000–apiopenrouter
GPT OSS 20B 2 sourcesOpenAIGoogle Vertex AI––0.07000.2500.1150.007000–0.03500.125131,0722026-09-11 ↓aggregatorlitellm
DeepSeek V4.1 Flash 1017DeepSeekIonStreamflex–0.07750.2330.1160.002325–––1,048,5762026-11-12 ↓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