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 ↑?ContextTokenizerConfidence?Source
accounts/fireworks/models/llama-v3p1-8b-instructFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/llama-v3p2-1b-instructFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/llama-v3p2-3b-instructFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
Ministral 3 3B 2 sourcesAWS Bedrock––0.1000.1000.100128,000–aggregatorlitellm
ministral-3-3b-2512Mistral AI––0.1000.1000.100131,072–aggregatorlitellm
together-ai-up-to-4bTogether AI––0.1000.1000.100––aggregatorlitellm
arize-ai/qwen-2-1.5b-instructTogether AI––0.1000.1000.10032,768–aggregatorlitellm
glm-4-32b-0414-128k 2 sourcesZhipu AI (Z.ai)––0.1000.1000.100128,000–officialofficial-zhipu
accounts/fireworks/models/codegemma-2bFireworks AI––0.1000.1000.1008,192–aggregatorlitellm
accounts/fireworks/models/cogito-v1-preview-llama-3bFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/deepseek-coder-1b-baseFireworks AI––0.1000.1000.10016,384–aggregatorlitellm
accounts/fireworks/models/deepseek-r1-distill-qwen-1p5bFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/ernie-4p5-21b-a3b-ptFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/ernie-4p5-300b-a47b-ptFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/flux-1-devFireworks AI––0.1000.1000.1004,096–aggregatorlitellm
accounts/fireworks/models/flux-1-schnellFireworks AI––0.1000.1000.1004,096–aggregatorlitellm
accounts/fireworks/models/gemma-2b-itFireworks AI––0.1000.1000.1008,192–aggregatorlitellm
accounts/fireworks/models/llama-guard-3-1bFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/llama-v2-70bFireworks AI––0.1000.1000.1004,096–aggregatorlitellm
accounts/fireworks/models/llama-v3p1-405b-instruct-longFireworks AI––0.1000.1000.1004,096–aggregatorlitellm
accounts/fireworks/models/llama-v3p1-70b-instruct-1bFireworks AI––0.1000.1000.1004,096–aggregatorlitellm
accounts/fireworks/models/llama-v3p2-1bFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/llama-v3p2-3bFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
MiniMax-M1Fireworks AI––0.1000.1000.1001,000,000–aggregatorlitellm
accounts/fireworks/models/ministral-3-3b-instruct-2512Fireworks AI––0.1000.1000.100256,000–aggregatorlitellm
accounts/fireworks/models/nemotron-nano-v2-12b-vlFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/phi-2-3bFireworks AI––0.1000.1000.1002,048–aggregatorlitellm
Phi-3-mini-128k-instructFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/qwen2-vl-2b-instructFireworks AI––0.1000.1000.10032,768–aggregatorlitellm
accounts/fireworks/models/qwen2p5-0p5b-instructFireworks AI––0.1000.1000.10032,768–aggregatorlitellm
accounts/fireworks/models/qwen2p5-1p5b-instructFireworks AI––0.1000.1000.10032,768–aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-0p5bFireworks AI––0.1000.1000.10032,768–aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-0p5b-instructFireworks AI––0.1000.1000.10032,768–aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-1p5bFireworks AI––0.1000.1000.10032,768–aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-1p5b-instructFireworks AI––0.1000.1000.10032,768–aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-3bFireworks AI––0.1000.1000.10032,768–aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-3b-instructFireworks AI––0.1000.1000.10032,768–aggregatorlitellm
accounts/fireworks/models/qwen3-0p6bFireworks AI––0.1000.1000.10040,960–aggregatorlitellm
accounts/fireworks/models/qwen3-1p7bFireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/qwen3-1p7b-fp8-draftFireworks AI––0.1000.1000.100262,144–aggregatorlitellm
accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072Fireworks AI––0.1000.1000.100131,072–aggregatorlitellm
accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960Fireworks AI––0.1000.1000.10040,960–aggregatorlitellm
accounts/fireworks/models/stablecode-3bFireworks AI––0.1000.1000.1004,096–aggregatorlitellm
accounts/fireworks/models/starcoder2-3bFireworks AI––0.1000.1000.10016,384–aggregatorlitellm
gpt-oss-120b 2 sourcesNovita AI––0.05000.2500.100131,072o200kaggregatorlitellm
GPT-6 LunaOpenAIbatch–0.05000.2500.1001,050,000o200kofficialofficial-openai
eu.meta.llama3-2-1b-instruct-v1:0AWS Bedrock–us0.1000.1000.100128,000–aggregatorlitellm
Nemotron 3.5 LightningOpenRouter––0.07000.2000.1031,048,576–apiopenrouter
NVIDIA Nemotron Nano 9B v2 2 sourcesAWS Bedrock––0.06000.2300.103128,000–aggregatorlitellm
gpt-oss-safeguard-20b 2 sourcesAWS Bedrock––0.07000.2000.103131,072o200kaggregatorlitellm

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