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

ModelVendorHostVariantInputOutputBlended ↑?Cache readCache writeBatch inBatch outContextTokenizerLast changeConfidence?Source
text-embedding-3-largeazureazure–0.13n/afreen/a0.0975n/a–n/a–n/a–n/a–n/a8191––aggregatormodelsdev
text-embedding-3-largeazureopenai–0.13n/afreen/a0.0975n/a–n/a–n/a–n/a–n/a8191––aggregatormodelsdev
Reka Edgeopenrouteropenrouter–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a16384––apiopenrouter
Mistral: Ministral 3 3B 2512openrouteropenrouter–0.100.03560.100.03560.100.03560.01000.0036–n/a–n/a–n/a131072mistral–apiopenrouter
OpenAI: GPT-6 Luna Proopenrouteropenaiunknown0.05000.01410.250.07040.100.02820.00500.00140.06250.0176–n/a–n/a1050000o200k–apiopenrouter
GPT-6 Lunaopenaiopenaiunknown0.05000.01410.250.07040.100.02820.00500.00140.06250.0176–n/a–n/a–o200k–apiopenrouter
Reka Edgeopenrouterrekaunknown0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a16384––apiopenrouter
Mistral: Ministral 3 3B 2512openroutermistralunknown0.100.03560.100.03560.100.03560.01000.0036–n/a–n/a–n/a131072mistral–apiopenrouter
Mistral: Ministral 3 3B 2512openroutermistralunknown0.100.03560.100.03560.100.03560.01000.0036–n/a–n/a–n/a131072mistral–apiopenrouter
gpt-oss-120bopenroutercrusoe–0.05000.01410.250.07040.100.02820.05000.0141–n/a–n/a–n/a131072o200k–apiopenrouter
gpt-oss-120bopenrouternovitafp40.05000.01410.250.07040.100.0282–n/a–n/a–n/a–n/a131072o200k–apiopenrouter
Gemma-3-27b-itopenrouterdeepinfrafp80.0800n/a0.16n/a0.10n/a–n/a–n/a–n/a–n/a131072gemini–apiopenrouter
FW-Nemotron-Lightning-3.5-30B-A3Bazureazure–0.0600n/a0.22n/a0.10n/a0.0100n/a–n/a–n/a–n/a262144––aggregatorlitellm
llama3.1-8bmetacerebras–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a128000––aggregatorlitellm
Gemma-3-27b-itopenrouterdeepinfra–0.0800n/a0.16n/a0.10n/a–n/a–n/a–n/a–n/a131072gemini2026-08-27 ↓aggregatorlitellm
accounts/fireworks/models/llama-v3p1-8b-instructmetafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a16384––aggregatorlitellm
accounts/fireworks/models/llama-v3p2-1b-instructmetafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a16384––aggregatorlitellm
accounts/fireworks/models/llama-v3p2-3b-instructmetafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a16384––aggregatorlitellm
eu.meta.llama3-2-1b-instruct-v1:0metaaws-bedrock–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a128000––aggregatorlitellm
Ministral 3 3Bmistralaws-bedrock–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a256000––aggregatorlitellm
ministral-3b-2512mistralmistral–0.10n/a0.10n/a0.10n/a0.0100n/a–n/a–n/a–n/a131072––aggregatorlitellm
ministral-3b-latestmistralmistral–0.10n/a0.10n/a0.10n/a0.0100n/a–n/a–n/a–n/a131072––aggregatorlitellm
ministral-3-3b-2512mistralmistral–0.10n/a0.10n/a0.10n/a0.0100n/a–n/a–n/a–n/a131072––aggregatorlitellm
together-ai-up-to-4btogethertogether–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a–––aggregatorlitellm
arize-ai/qwen-2-1.5b-instructalibabatogether–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
eu.meta.llama3-2-1b-instruct-v1:0metaaws-bedrock–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a128000––aggregatorlitellm
glm-4-32b-0414-128kzhipuzhipu–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a128000––aggregatorlitellm
accounts/fireworks/models/codegemma-2bfireworksfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a8192––aggregatorlitellm
accounts/fireworks/models/cogito-v1-preview-llama-3bfireworksfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
accounts/fireworks/models/deepseek-coder-1b-basedeepseekfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a16384––aggregatorlitellm
accounts/fireworks/models/deepseek-r1-distill-qwen-1p5bdeepseekfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
accounts/fireworks/models/ernie-4p5-21b-a3b-ptfireworksfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
accounts/fireworks/models/ernie-4p5-300b-a47b-ptfireworksfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
accounts/fireworks/models/flux-1-devfireworksfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
accounts/fireworks/models/flux-1-schnellfireworksfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
accounts/fireworks/models/gemma-2b-itgooglefireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a8192––aggregatorlitellm
accounts/fireworks/models/llama-guard-3-1bmetafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
accounts/fireworks/models/llama-v2-70bmetafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
accounts/fireworks/models/llama-v3p1-405b-instruct-longmetafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
accounts/fireworks/models/llama-v3p1-70b-instruct-1bmetafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
accounts/fireworks/models/llama-v3p2-1bmetafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
accounts/fireworks/models/llama-v3p2-3bmetafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
MiniMax-M1minimaxfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a1000000––aggregatorlitellm
accounts/fireworks/models/ministral-3-3b-instruct-2512fireworksfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a256000––aggregatorlitellm
accounts/fireworks/models/nemotron-nano-v2-12b-vlnvidiafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
accounts/fireworks/models/phi-2-3bmicrosoftfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a2048––aggregatorlitellm
accounts/fireworks/models/phi-3-mini-128k-instructmicrosoftfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
accounts/fireworks/models/qwen2-vl-2b-instructalibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
accounts/fireworks/models/qwen2p5-0p5b-instructalibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
accounts/fireworks/models/qwen2p5-1p5b-instructalibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––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