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
accounts/fireworks/models/qwen2p5-coder-0p5balibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-0p5b-instructalibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-1p5balibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-1p5b-instructalibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-3balibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
accounts/fireworks/models/qwen2p5-coder-3b-instructalibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
accounts/fireworks/models/qwen3-0p6balibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a40960––aggregatorlitellm
accounts/fireworks/models/qwen3-1p7balibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
accounts/fireworks/models/qwen3-1p7b-fp8-draftalibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a262144––aggregatorlitellm
accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072alibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960alibabafireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a40960––aggregatorlitellm
accounts/fireworks/models/stablecode-3bfireworksfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
accounts/fireworks/models/starcoder2-3bfireworksfireworks–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a16384––aggregatorlitellm
gpt-oss-120bopenrouternovita–0.05000.01410.250.07040.100.0282–n/a–n/a–n/a–n/a131072o200k2026-01-13 ↓aggregatorlitellm
Ministral 8B (latest)mistralmistral–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
GPT-6 Lunaopenaiopenaibatch0.05000.01410.250.07040.100.02820.00500.00140.06250.0176–n/a–n/a–o200k–officialofficial-openai
GPT-6 Lunaopenaiopenaiflex0.05000.01410.250.07040.100.02820.00500.00140.06250.0176–n/a–n/a–o200k–officialofficial-openai
gemma-3-27b-itdeepinfradeepinfra–0.0800n/a0.16n/a0.10n/a–n/a–n/a–n/a–n/a–––officialofficial-deepinfra
glm-4-32b-0414-128kzhipuzhipu–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a128000––officialofficial-zhipu
OpenAI: GPT-6 Luna Proopenrouteropenai–0.05000.01410.250.07040.100.02820.00500.00140.06250.0176–n/a–n/a1050000o200k–apiopenrouter
GPT-6 Lunaopenaiopenai–0.05000.01410.250.07040.100.02820.00500.00140.06250.0176–n/a–n/a–o200k–apiopenrouter
Reka Edgeopenrouterreka–0.10n/a0.10n/a0.10n/a–n/a–n/a–n/a–n/a16384––apiopenrouter
Mistral: Ministral 3 3B 2512openroutermistral–0.100.03560.100.03560.100.03560.01000.0036–n/a–n/a–n/a131072mistral–apiopenrouter
Mistral: Ministral 3 3B 2512openroutermistral–0.100.03560.100.03560.100.03560.01000.0036–n/a–n/a–n/a131072mistral–apiopenrouter
Qwen-Omni Turboalibabaalibaba–0.0580n/a0.23n/a0.10n/a–n/a–n/a–n/a–n/a32768–2026-10-04 ↓aggregatormodelsdev
Qwen Doc Turboalibabaalibaba–0.0870n/a0.14n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatormodelsdev
Nemotron 3.5 Lightning 30B A3Bopenrouterphalaunknown0.0700n/a0.20n/a0.10n/a0.0400n/a–n/a–n/a–n/a262144––apiopenrouter
Nemotron 3.5 Lightning 30B A3Bopenroutercoreweave–0.0700n/a0.20n/a0.10n/a0.0400n/a–n/a–n/a–n/a262144––apiopenrouter
gpt-oss-120bopenroutermancer-2fp80.04500.01270.280.07750.100.0289–n/a–n/a–n/a–n/a131072o200k–apiopenrouter
NVIDIA Nemotron Nano 9B v2nvidiaaws-bedrock–0.0600n/a0.23n/a0.10n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
openai.gpt-oss-safeguard-20bopenaiaws-bedrock–0.0700n/a0.20n/a0.10n/a–n/a–n/a–n/a–n/a128000––aggregatorlitellm
openai.gpt-oss-safeguard-20baws-bedrockaws-bedrock–0.0700n/a0.20n/a0.10n/a–n/a–n/a–n/a–n/a131072–2026-03-11 ↓aggregatorlitellm
Safety GPT OSS 20Bopenrouteraws-bedrock–0.07000.01970.200.05630.100.0289–n/a–n/a–n/a–n/a131072o200k–aggregatormodelsdev
Nemotron 3.5 Lightning 30B A3Bopenrouterphala–0.0700n/a0.20n/a0.10n/a0.0400n/a–n/a–n/a–n/a262144––apiopenrouter
Amazon: Nova Lite 1.0openrouteropenrouter–0.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a300000––apiopenrouter
nemotron-3-nano-30b-a3bopenrouternebiusfp80.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a262144––apiopenrouter
Amazon: Nova Lite 1.0openrouteraws-bedrockunknown0.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a300000––apiopenrouter
Amazon: Nova Lite 1.0openrouteraws-bedrockunknown0.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a300000––apiopenrouter
Amazon Nova Liteamazonaws-bedrock–0.0600n/a0.24n/a0.11n/a0.0150n/a–n/a–n/a–n/a300000––aggregatorlitellm
model_routerazureazure–0.14n/afreen/a0.11n/a–n/a–n/a–n/a–n/a200000––aggregatorlitellm
Model Routerazureazure–0.14n/afreen/a0.11n/a–n/a–n/a–n/a–n/a200000––aggregatorlitellm
Amazon Nova Liteamazonamazon–0.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a300000––aggregatorlitellm
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3Bnebiusnebius–0.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a262144––aggregatorlitellm
nvidia/Nemotron-3-Nano-Omninvidianebius–0.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a262144––aggregatorlitellm
nvidia/Nemotron-3_5-Lightningnvidianebius–0.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a1048576––aggregatorlitellm
nvidia.nemotron-nano-3-30bnvidiaaws-bedrock–0.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a256000––aggregatorlitellm
Amazon Nova Liteamazonaws-bedrock–0.0600n/a0.24n/a0.11n/a0.0150n/a–n/a–n/a–n/a300000––aggregatorlitellm
deepseek-ai/DeepSeek-V4-Flash-0731deepseekdeepinfra–0.0800n/a0.18n/a0.11n/a0.0160n/a–n/a–n/a–n/a1024000––aggregatorlitellm
Nemotron 3.5 Lightning 30B A3Bopenrouternebius–0.0600n/a0.24n/a0.11n/a0.0600n/a–n/a–n/a–n/a262144––aggregatormodelsdev
nemotron-3-nano-30b-a3bopenrouteraws-bedrock–0.0600n/a0.24n/a0.11n/a–n/a–n/a–n/a–n/a262144––aggregatormodelsdev

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