NVIDIA

Models

ModelTierCheapest input $/MtokCheapest output $/Mtok
dracarys-llama-3.1-70b-instruct–$0.000000$0.000000
BGE M3–$0.000000$0.000000
FLUX.1-dev–$0.000000$0.000000
FLUX.1-Kontext-dev–$0.000000$0.000000
FLUX.1-schnell–$0.000000$0.000000
FLUX.2 Klein 4B–$0.000000$0.000000
ByteDance-Seed/Seed-OSS-36B-Instruct–$0.000000$0.000000
DiffusionGemma 26B A4B IT–$0.000000$0.000000
paligemma–$0.000000$0.000000
esm2-650m–$0.000000$0.000000
esmfold–$0.000000$0.000000
Ministral 3 14B Instruct 2512–$0.000000$0.000000
accounts/fireworks/models/nemotron-3-ultra-nvfp4–$0.600000$2.400000
accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b–$0.050000$0.200000
accounts/fireworks/models/nemotron-nano-v2-12b-vl–$0.100000$0.100000
Active Speaker Detection–$0.000000$0.000000
bevformer–$0.000000$0.000000
cosmos-predict1-5b–$0.000000$0.000000
Cosmos Reason2 8B–$0.000000$0.000000
cosmos-transfer1-7b–$0.000000$0.000000
cosmos-transfer2.5-2b–$0.000000$0.000000
gliner-pii–$0.000000$0.000000
magpie-tts-zeroshot–$0.000000$0.000000
nemotron-3-ultra-nvfp4–$0.600000$2.400000
nemotron-lightning-3p5-30b-a3b–$0.050000$0.200000
NVIDIA Nemotron Nano 12B v2 VL BF16–$0.200000$0.600000
nvidia.nemotron-nano-3-30b–$0.060000$0.240000
NVIDIA Nemotron Nano 9B v2–$0.000000$0.000000
nvidia.nemotron-super-3-120b–$0.150000$0.650000
Llama 3.3 Nemotron Super 49B v1.5small$0.000000$0.000000
nv-embed-v1–$0.000000$0.000000
nv-embedcode-7b-v1–$0.000000$0.000000
nemotron-3-content-safety–$0.000000$0.000000
nvidia/Nemotron-3-Nano-Omni–$0.060000$0.240000
nvidia/Nemotron-3_5-Lightning–$0.060000$0.240000
nvidia/Nemotron-Content-Safety-3.5–$0.200000$0.200000
nemotron-content-safety-reasoning-4b–$0.000000$0.000000
nemotron-mini-4b-instruct–$0.000000$0.000000
Nemotron Nano 12B v2 VL–$0.000000$0.000000
nemotron-voicechat–$0.000000$0.000000
perplexity/nemotron-3-ultra-550b-a55b–$0.250000$2.500000
perplexity/nemotron-3.5-lightning-30b-a3b–$0.011500$0.170000
rerank-qa-mistral-4b–$0.000000$0.000000
riva-translate-4b-instruct-v1_1–$0.000000$0.000000
sparsedrive–$0.000000$0.000000
streampetr–$0.000000$0.000000
studiovoice–$0.000000$0.000000
synthetic-video-detector–$0.000000$0.000000
usdcode–$0.000000$0.000000
usdvalidate–$0.000000$0.000000
Whisper Large v3–$0.000000$0.000000
sarvam-m–$0.000000$0.000000
Step 3.5 Flash–$0.000000$0.000000
solar-10.7b-instruct–$0.000000$0.000000

Price history

Blended ($/Mtok, 75% input / 25% output) price over time for every model this host serves. Click a legend entry to hide or show its line.

Hosted offerings

ModelVariantInput $/MtokOutput $/MtokConfidence
NVIDIA: Nemotron 3.5 Lightning (free)free$0.000000$0.000000high
NVIDIA: Nemotron 3.5 Content Safety (free)free$0.000000$0.000000high
NVIDIA: Nemotron 3 Ultra (free)free$0.000000$0.000000high
NVIDIA: Nemotron 3 Nano Omni (free)free$0.000000$0.000000high
NVIDIA: Nemotron 3 Super (free)free$0.000000$0.000000high
BGE M3–$0.000000$0.000000medium
Poolside: Laguna XS 2.1 (free)–$0.000000$0.000000medium
dracarys-llama-3.1-70b-instruct–$0.000000$0.000000medium
GLM-5.3-Flash–$0.000000$0.000000medium
GLM-5.2–$0.000000$0.000000medium
GLM-5.3–$0.000000$0.000000medium
Thinking Machines: Inkling (free)–$0.000000$0.000000medium
FLUX.1-schnell–$0.000000$0.000000medium
FLUX.1-dev–$0.000000$0.000000medium
FLUX.1-Kontext-dev–$0.000000$0.000000medium
FLUX.2 Klein 4B–$0.000000$0.000000medium
Llama Guard 4 12B–$0.000000$0.000000medium
Meta: Muse Glimmer 30B–$0.000000$0.000000medium
esmfold–$0.000000$0.000000medium
Meta: Llama 3.3 70B Instruct–$0.000000$0.000000medium
Llama-3.2-90B-Vision-Instruct–$0.000000$0.000000medium
Llama 4 Maverick 17b 128e Instruct–$0.000000$0.000000medium
Llama 3.1 8B Instruct–$0.000000$0.000000medium
Llama 3.2 11b Vision Instruct–$0.000000$0.000000medium
Llama 3.2 1b Instruct–$0.000000$0.000000medium
Llama 3.2 3B Instruct–$0.000000$0.000000medium
Llama 3.1 70B Instruct (US)–$0.000000$0.000000medium
esm2-650m–$0.000000$0.000000medium
solar-10.7b-instruct–$0.000000$0.000000medium
ByteDance-Seed/Seed-OSS-36B-Instruct–$0.000000$0.000000medium
DiffusionGemma 26B A4B IT–$0.000000$0.000000medium
Google: Gemma 4 31B (free)–$0.000000$0.000000medium
Gemma 2 2b It–$0.000000$0.000000medium
Google: Gemma 3 12B–$0.000000$0.000000medium
Gemma 3n E2b It–$0.000000$0.000000medium
paligemma–$0.000000$0.000000medium
Gemma 3n E4b It–$0.000000$0.000000medium
Google: Gemma 3 4B–$0.000000$0.000000medium
MiniMax-M2.7–$0.000000$0.000000medium
MiniMax-M3–$0.000000$0.000000medium
DeepSeek: DeepSeek V4 Flash 0731–$0.000000$0.000000medium
DeepSeek: DeepSeek V4.1 Flash–$0.000000$0.000000medium
DeepSeek: DeepSeek V4 Pro 0813–$0.000000$0.000000medium
Step 3.5 Flash–$0.000000$0.000000medium
Step 3.7 Flash–$0.000000$0.000000medium
mistral-nemotron–$0.000000$0.000000medium
Mistral-7B-Instruct-v0.3–$0.000000$0.000000medium
Mistral Large 3 675B Instruct 2512–$0.000000$0.000000medium
Magistral Small 2506–$0.000000$0.000000medium
mistral-small-4-119b-2603–$0.000000$0.000000medium
Mistral: Mixtral 8x7B Instruct–$0.000000$0.000000medium
Mistral Medium 3.5–$0.000000$0.000000medium
Ministral 3 14B Instruct 2512–$0.000000$0.000000medium
Mistral: Mixtral 8x22B Instruct–$0.000000$0.000000medium
Mistral Medium 3–$0.000000$0.000000medium
Kimi K3–$0.000000$0.000000medium
MoonshotAI: Kimi K2.6–$0.000000$0.000000medium
sarvam-m–$0.000000$0.000000medium
NVIDIA Nemotron Nano 9B v2–$0.000000$0.000000medium
Llama 3.1 Nemotron Ultra 253B–$0.000000$0.000000medium
sparsedrive–$0.000000$0.000000medium
NVIDIA: Nemotron 3 Nano 30B A3B–$0.000000$0.000000medium
NVIDIA: Nemotron 3.5 Lightning (free)–$0.000000$0.000000medium
llama-nemotron-embed-vl-1b-v2–$0.000000$0.000000medium
nv-embedcode-7b-v1–$0.000000$0.000000medium
nemotron-voicechat–$0.000000$0.000000medium
bevformer–$0.000000$0.000000medium
cosmos-transfer1-7b–$0.000000$0.000000medium
cosmos-predict1-5b–$0.000000$0.000000medium
Llama 3.1 Nemotron Nano VL 8B v1–$0.000000$0.000000medium
studiovoice–$0.000000$0.000000medium
nemotron-content-safety-reasoning-4b–$0.000000$0.000000medium
llama-3.1-nemotron-safety-guard-8b-v3–$0.000000$0.000000medium
nv-embed-v1–$0.000000$0.000000medium
synthetic-video-detector–$0.000000$0.000000medium
cosmos-transfer2.5-2b–$0.000000$0.000000medium
NVIDIA: Nemotron 3 Nano Omni (free)–$0.000000$0.000000medium
Llama 3.1 Nemotron Nano 8B v1–$0.000000$0.000000medium
Active Speaker Detection–$0.000000$0.000000medium
streampetr–$0.000000$0.000000medium
llama-nemotron-rerank-vl-1b-v2–$0.000000$0.000000medium
nemotron-mini-4b-instruct–$0.000000$0.000000medium
Cosmos Reason2 8B–$0.000000$0.000000medium
nemotron-3-content-safety–$0.000000$0.000000medium
Llama 3.3 Nemotron Super 49B v1.5–$0.000000$0.000000medium
magpie-tts-zeroshot–$0.000000$0.000000medium
riva-translate-4b-instruct-v1_1–$0.000000$0.000000medium
Nemotron Nano 12B v2 VL–$0.000000$0.000000medium
NVIDIA: Nemotron 3.5 Content Safety (free)–$0.000000$0.000000medium
Llama 3.3 Nemotron Super 49B v1.5–$0.000000$0.000000medium
llama-3_2-nemoretriever-300m-embed-v1–$0.000000$0.000000medium
gliner-pii–$0.000000$0.000000medium
usdcode–$0.000000$0.000000medium
usdvalidate–$0.000000$0.000000medium
Llama 3.1 Nemotron 70B Instruct–$0.000000$0.000000medium
rerank-qa-mistral-4b–$0.000000$0.000000medium
Qwen Image Edit–$0.000000$0.000000medium
Qwen3 Coder 480B A35B Instruct–$0.000000$0.000000medium
Qwen: Qwen3.5-122B-A10B–$0.000000$0.000000medium
Qwen: Qwen3 Next 80B A3B Instruct–$0.000000$0.000000medium
Qwen: Qwen3.5 397B A17B–$0.000000$0.000000medium
Qwen2.5 Coder 32b Instruct–$0.000000$0.000000medium
Qwen Image–$0.000000$0.000000medium
Whisper Large v3–$0.000000$0.000000medium
OpenAI: gpt-oss-20b–$0.000000$0.000000medium
Phi-4-Mini–$0.000000$0.000000medium
Phi 4 Multimodal–$0.000000$0.000000medium
DeepSeek: DeepSeek V4 Flash 0423–$0.140000$0.280000medium
NVIDIA: Nemotron 3 Super (free)–$0.200000$0.800000medium
DeepSeek: DeepSeek V4 Pro 0423–$0.435000$0.870000medium
NVIDIA: Nemotron 3 Ultra (free)–$0.500000$2.500000medium