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
Reka Flash 3OpenRouterOpenRouter––0.1000.2000.125––––65,536–apiopenrouter
Muse Spark 1.3 Contributor 3 sourcesMetaMeta––0.1000.2000.1250.002000–––1,048,576–apiopenrouter
Muse Spark 1.2 Contributor 3 sourcesMetaMeta––0.1000.2000.1250.002000–––1,048,576–apiopenrouter
Laguna S 2.1OpenRouterPoolside promo −10%fp4–0.1000.2000.1250.0100–––1,048,576–apiopenrouter
Laguna XS 2.1OpenRouterPoolside promo −40%fp8–0.1000.2000.1250.0500–––262,144–apiopenrouter
UI-TARS 7BOpenRouterParasail––0.1000.2000.1250.100–––128,000–apiopenrouter
Reka Flash 3OpenRouterReka AI––0.1000.2000.125––––65,536–apiopenrouter
Qwen2.5 7B InstructAlibaba CloudPhala––0.1000.2000.125––––32,768–apiopenrouter
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–ap-northeast-10.07000.2900.125––––256,000–aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–sa-east-10.07000.2900.125––––256,000–aggregatorlitellm
Amazon Nova LiteAmazonAWS Bedrock–us-gov-west-10.07200.2880.1260.0180–0.03600.144300,000–aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–us-gov-east-10.07200.2880.126––0.03600.144256,000–aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–us-gov-west-10.07200.2880.126––0.03600.144256,000–aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–us-gov0.07200.2880.126––––256,000–aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–ap-southeast-30.07200.2880.126––––256,000–aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–eu-central-10.07200.2880.126––––256,000–aggregatorlitellm
nvidia.nemotron-nano-3-30bNVIDIAAWS Bedrock–eu-north-10.07200.2880.126––––256,000–aggregatorlitellm
gpt-oss-20bOpenAIFireworks AI––0.07000.3000.1280.0350–––131,0722026-06-18 ↑aggregatorlitellm
openai.gpt-oss-20b-1:0OpenAIAWS Bedrock––0.07000.3000.128––0.03500.150128,000–aggregatorlitellm
Hy-MT2-30B-A3BOpenRouterOpenRouter––0.07400.2950.129––––8,192–apiopenrouter
Hy-MT2-7BOpenRouterOpenRouter––0.07400.2950.129––––8,192–apiopenrouter
Hy-MT2-30B-A3BOpenRouterTencent Cloudfp8–0.07400.2950.129––––8,192–apiopenrouter
Hy-MT2-7BOpenRouterTencent Cloudfp8–0.07400.2950.129––––8,192–apiopenrouter
Qwen3 32BAlibaba CloudOpenRouter––0.08000.2800.130––––131,072–apiopenrouter
Qwen3 14BAlibaba CloudNextBitint4–0.1000.2200.130––––40,960–apiopenrouter
Qwen3 32BAlibaba CloudDeepInfrafp8–0.08000.2800.130––––131,072–apiopenrouter
Qwen3 32B 3 sourcesAlibaba CloudDeepInfra––0.08000.2800.130––––131,0722026-08-27 ↓officialofficial-deepinfra
GLM-4.6V-FlashXZhipu AI (Z.ai)Zhipu AI (Z.ai)––0.04000.4000.1300.004000–––––officialofficial-zhipu
eu.meta.llama3-2-1b-instruct-v1:0MetaAWS Bedrock–eu0.1300.1300.130––––128,000–aggregatorlitellm
eu.meta.llama3-2-1b-instruct-v1:0MetaAWS Bedrock–eu-central-10.1300.1300.130––––128,000–aggregatorlitellm
eu.meta.llama3-2-1b-instruct-v1:0MetaAWS Bedrock–eu-west-30.1300.1300.130––––128,000–aggregatorlitellm
gpt-oss-20bOpenAIAWS Bedrock–ap-southeast-30.07000.3100.130––––131,072–aggregatorlitellm
gpt-oss-safeguard-20bOpenAIOpenRouter––0.07500.3000.1310.0375–––131,072–apiopenrouter
Seed 1.6 FlashOpenRouterByteDance Seedfp8–0.07500.3000.131––––262,144–apiopenrouter
gpt-oss-safeguard-20b 3 sourcesOpenAIGroq––0.07500.3000.1310.0375–––131,072–apiopenrouter
gpt-oss-20b 3 sourcesOpenAIGroq––0.07500.3000.1310.0375–––131,0722026-01-21 ↓apiopenrouter
Phi-4-MiniMicrosoftAzure AI Foundry––0.07500.3000.131––––131,072–aggregatorlitellm
Phi-4-mini-reasoning 2 sourcesMicrosoftAzure AI Foundry––0.07500.3000.131––––131,0722026-09-17 ↓aggregatorlitellm
DeepSeek V4 Flash 2 sourcesDeepSeekFireworks AI––0.1050.2100.1310.0210–––1,048,576–apiopenrouter
gemini-2.0-flash-liteGoogleGoogle Vertex AI––0.07500.3000.131––0.03750.150––aggregatorlitellm
Phi-4-miniMicrosoftAzure AI Foundry––0.07500.3000.131––––128,000–aggregatormodelsdev
accounts/fireworks/routers/spot-deepseek-v4-flashFireworks AIFireworks AI––0.1050.2100.1310.0210–––1,048,576–aggregatorlitellm
MiniMax M3.1 FlashMiniMaxMiniMaxoff-peak–0.07500.3000.1310.007500–––1,048,576–apiopenrouter
MiniMax M3.1 FlashMiniMaxOpenRouteroff-peak–0.07500.3000.1310.007500–––1,048,576–apiopenrouter
gpt-oss-20bOpenAIAWS Bedrock–ap-southeast-20.07210.3090.131––––131,072–aggregatorlitellm
Nemotron 3.5 Super VLNVIDIADarkbloomnvfp4–0.06000.3500.1330.0100–––1,048,576–apiopenrouter
Mistral Small 3.2 24BMistral AIVenicefp8–0.09380.2500.133––––256,000–apiopenrouter
nano-banana-proTogether AITogether AI–––0.1340.134––––––officialofficial-together
DeepSeek-V4-Flash-0731DeepInfraDeepInfrafp8+priority–0.09000.2700.1350.0225–––1,048,576–apiopenrouter
Amazon Nova LiteAmazonAWS Bedrock–eu0.07800.3120.1370.0195–––300,000–aggregatorlitellm

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