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
cosmos-predict1-5bnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a0––aggregatormodelsdev
Llama 3.1 Nemotron Nano VL 8B v1metanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a32768––aggregatormodelsdev
studiovoicenvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
nemotron-content-safety-reasoning-4bnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
llama-3.1-nemotron-safety-guard-8b-v3metanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
nv-embed-v1nvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a32768––aggregatormodelsdev
synthetic-video-detectornvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a0––aggregatormodelsdev
cosmos-transfer2.5-2bnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a0––aggregatormodelsdev
Nemotron 3 Nano Omni 30B A3B Reasoningopenrouternvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a256000––aggregatormodelsdev
Llama 3.1 Nemotron Nano 8B v1metanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a131072––aggregatormodelsdev
Active Speaker Detectionnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a0––aggregatormodelsdev
streampetrnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
llama-nemotron-rerank-vl-1b-v2metanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
nemotron-mini-4b-instructnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
Cosmos Reason2 8Bnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a131072––aggregatormodelsdev
nemotron-3-content-safetynvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
Llama 3.3 Nemotron Super 49B v1.5nvidianvidia–freefreefreefreefreefree–n/a–n/a–n/a–n/a131072llama3–aggregatormodelsdev
magpie-tts-zeroshotnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a0––aggregatormodelsdev
riva-translate-4b-instruct-v1_1nvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
Nemotron Nano 12B v2 VLnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
Nemotron 3.5 Content Safetyopenrouternvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
Llama 3.3 Nemotron Super 49B v1.5metanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a131072––aggregatormodelsdev
llama-3_2-nemoretriever-300m-embed-v1metanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a32768––aggregatormodelsdev
gliner-piinvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
usdcodenvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
usdvalidatenvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a0––aggregatormodelsdev
Llama 3.1 Nemotron 70B Instructmetanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
rerank-qa-mistral-4bnvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
Qwen Image Editalibabanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a0––aggregatormodelsdev
Qwen3 Coder 480B A35B Instructalibabanvidia–freefreefreefreefreefree–n/a–n/a–n/a–n/a262144qwen2–aggregatormodelsdev
Qwen3.5-122B-A10Bopenrouternvidia–freefreefreefreefreefree–n/a–n/a–n/a–n/a262144qwen2–aggregatormodelsdev
Qwen3 Next 80B A3B Instructopenrouternvidia–freefreefreefreefreefree–n/a–n/a–n/a–n/a262144qwen2–aggregatormodelsdev
Qwen3.5-397B-A17Bopenrouternvidia–freefreefreefreefreefree–n/a–n/a–n/a–n/a262144qwen2–aggregatormodelsdev
Qwen2.5 Coder 32b Instructalibabanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
Qwen Imagealibabanvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a0––aggregatormodelsdev
Whisper Large v3nvidianvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a0––aggregatormodelsdev
gpt-oss-20b (GovCloud)openrouternvidia–freefreefreefreefreefree–n/a–n/a–n/a–n/a131072o200k–aggregatormodelsdev
Phi-4-Minimicrosoftnvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a131072––aggregatormodelsdev
Phi 4 Multimodalmicrosoftnvidia–freen/afreen/afreen/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
Devstral Small 2mistralmistral–freen/afreen/afreen/a–n/a–n/a–n/a–n/a256000––aggregatormodelsdev
DeepSeek R1 Distill Llama 8Bdeepseekalibaba–freen/afreen/afreen/a–n/a–n/a–n/a–n/a32768––aggregatormodelsdev
DeepSeek R1 Distill Qwen 1.5Bdeepseekalibaba–freen/afreen/afreen/a–n/a–n/a–n/a–n/a32768––aggregatormodelsdev
prism-ml-ternary-bonsai-27btogethertogether–freen/afreen/afreen/a–n/a–n/a–n/a–n/a–––officialofficial-together
accounts/fireworks/models/flux-1-dev-controlnet-unionfireworksfireworks–0.0010n/a0.0010n/a0.0010n/a–n/a–n/a–n/a–n/a4096––aggregatorlitellm
juggernaut-lightning-fluxtogethertogether–0.0017n/a–n/a0.0017n/a–n/a–n/a–n/a–n/a–––officialofficial-together
sd-xltogethertogether–0.0019n/a–n/a0.0019n/a–n/a–n/a–n/a–n/a–––officialofficial-together
juggernaut-pro-fluxtogethertogether–0.0049n/a–n/a0.0049n/a–n/a–n/a–n/a–n/a–––officialofficial-together
qwen-imagetogethertogether–0.0058n/a–n/a0.0058n/a–n/a–n/a–n/a–n/a–––officialofficial-together
Qwen3-Embedding-8Balibabanebius–0.0100n/afreen/a0.0075n/a–n/a–n/a–n/a–n/a40960––aggregatormodelsdev
Qwen/Qwen2.5-Coder-7Balibabanebius–0.0100n/a0.0300n/a0.0150n/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