Monday, October 5, 2026 · No. 435Prices synced 19 hours ago
All·AI·Model

The AI Model Price Index

Nvidia

Cloud platforms · 106 listings · documentation ↗ · @ai-sdk/openai-compatible

Nvidia model prices, USD per one million tokens
CompareModelInput $/1MOutput $/1MCached $/1MContextCapsAcceptsCutoffListed
DeepSeek V4.1 FlashNvidiafreefree—1MRTVWMay 2025Sep 2026
GLM-5.3-FlashNvidiafreefree—1MRTVW—Aug 2026
GLM-5.3Nvidiafreefree—1MRTW—Aug 2026
DeepSeek V4 Pro 0813Nvidiafreefree—1MRTW—Aug 2026
Nemotron 3.5 Lightning 30B A3BNvidiafreefree—262KRTW—Aug 2026
Muse Glimmer 30BNvidiafreefree—131KRTVWJan 2026Aug 2026
DeepSeek V4 Flash 0731Nvidiafreefree—1MRTWMay 2025Jul 2026
Kimi K3Nvidiafreefree—1.0MRTVW—Jul 2026
InklingNvidiafreefree—1.0MRTVW—Jul 2026
Laguna XS 2.1Nvidiafreefree—262KRTW—Jul 2026
GLM-5.2Nvidiafreefree—1MRTW—Jun 2026
DiffusionGemma 26B A4B ITNvidiafreefree—250KRTVWJan 2025Jun 2026
Nemotron 3 Ultra 550B A55BNvidia$0.50$2.50$0.151MRTW—Jun 2026
Nemotron 3.5 Content SafetyNvidiafreefree—128KRVW—Jun 2026
MiniMax-M3Nvidiafreefree—1MRTVW—Jun 2026
Step 3.7 FlashNvidiafreefree—256KRTVW—May 2026
Mistral Medium 3.5Nvidiafreefree—262KRTVW—Apr 2026
Nemotron 3 Nano OmniNvidiafreefree—256KRTVW—Apr 2026
DeepSeek V4 FlashNvidia$0.14$0.28$0.00281.0MRTWMay 2025Apr 2026
DeepSeek V4 ProNvidia$0.435$0.87$0.00361.0MRTWMay 2025Apr 2026
Kimi K2.6Nvidiafreefree—262KRTVWJan 2025Apr 2026
Active Speaker DetectionNvidiafreefree——W—Apr 2026
nemotron-3-content-safetyNvidiafreefree—128KW—Apr 2026
synthetic-video-detectorNvidiafreefree——W—Apr 2026
Gemma-4-31B-ITNvidiafreefree—256KRTVWJan 2025Apr 2026
llama-nemotron-rerank-vl-1b-v2Nvidiafreefree—128KVW—Mar 2026
MiniMax-M2.7Nvidiafreefree—205KRTW—Mar 2026
mistral-small-4-119b-2603Nvidiafreefree—128KRTVW—Mar 2026
nemotron-voicechatNvidiafreefree—128KTW—Mar 2026
Nemotron 3 SuperNvidia$0.20$0.80—262KRTWApr 2024Mar 2026
gliner-piiNvidiafreefree—128KW—Mar 2026
cosmos-transfer2.5-2bNvidiafreefree——VW—Feb 2026
Qwen3.5 122B-A10BNvidiafreefree—262KRTVW—Feb 2026
Qwen3.5-397B-A17BNvidiafreefree—262KRTVWJan 2026Feb 2026
llama-nemotron-embed-vl-1b-v2Nvidiafreefree—33KVW—Feb 2026
Step 3.5 FlashNvidiafreefree—256KRTW—Feb 2026
nemotron-content-safety-reasoning-4bNvidiafreefree—128KRW—Jan 2026
FLUX.2 Klein 4BNvidiafreefree—41KVWJun 2025Jan 2026
usdcodeNvidiafreefree—128K—Jan 2026
riva-translate-4b-instruct-v1_1Nvidiafreefree—128KW—Dec 2025
Ministral 3 14B Instruct 2512Nvidiafreefree—262KTVW—Dec 2025
Mistral Large 3 675B Instruct 2512Nvidiafreefree—262KTVWJan 2025Dec 2025
Cosmos Reason2 8BNvidiafreefree—131KRTVW—Dec 2025
streampetrNvidiafreefree—128KW—Nov 2025
llama-3.1-nemotron-safety-guard-8b-v3Nvidiafreefree—128KW—Oct 2025
Nemotron Nano 12B v2 VLNvidiafreefree—128KRTVW—Oct 2025
Magistral Small 2506Nvidiafreefree—33K—Sep 2025
Mistral Medium 3Nvidiafreefree—131KV—Sep 2025
ByteDance-Seed/Seed-OSS-36B-InstructNvidiafreefree—262KT—Sep 2025
Qwen Image EditNvidiafreefree——V—Aug 2025
nvidia-nemotron-nano-9b-v2Nvidiafreefree—131KRTWSep 2024Aug 2025
FLUX.1-Kontext-devNvidiafreefree—41KVW—Aug 2025
Qwen ImageNvidiafreefree——V—Aug 2025
GPT OSS 20BNvidiafreefree—131KRTW—Aug 2025
Phi 4 MultimodalNvidiafreefree—128K—Jul 2025
Llama 3.3 Nemotron Super 49B v1.5Nvidiafreefree—131KRTW—Jul 2025
sarvam-mNvidiafreefree—128KTW—Jul 2025
llama-3_2-nemoretriever-300m-embed-v1Nvidiafreefree—33KW—Jul 2025
Qwen3 Coder 480B A35B InstructNvidiafreefree—262KTApr 2025Jul 2025
cosmos-transfer1-7bNvidiafreefree——VW—Jun 2025
Gemma 3n E2b ItNvidiafreefree—128KTVWJun 2024Jun 2025
mistral-nemotronNvidiafreefree—128KTW—Jun 2025
Gemma 3n E4b ItNvidiafreefree—128KTVWJun 2024Jun 2025
magpie-tts-zeroshotNvidiafreefree——W—May 2025
Llama 3.1 Nemotron 70B InstructNvidiafreefree—128KTW—Apr 2025
Llama 3.1 Nemotron Nano VL 8B v1Nvidiafreefree—33KRTVW—Apr 2025
Llama 3.1 Nemotron Ultra 253BNvidiafreefree—128KRTW—Apr 2025
Llama 3.3 Nemotron Super 49B v1Nvidiafreefree—131KRTW—Apr 2025
Llama Guard 4 12BNvidiafreefree—128KVW—Apr 2025
Llama 4 Maverick 17b 128e InstructNvidiafreefree—128KTVWFeb 2024Apr 2025
Mistral-7B-Instruct-v0.3Nvidiafreefree—66KTW—Apr 2025
bevformerNvidiafreefree—128KW—Mar 2025
cosmos-predict1-5bNvidiafreefree——VW—Mar 2025
Llama 3.1 Nemotron Nano 8B v1Nvidiafreefree—131KRTW—Mar 2025
sparsedriveNvidiafreefree—128KW—Mar 2025
nv-embedcode-7b-v1Nvidiafreefree—33KW—Mar 2025
Gemma 3 12B ITNvidiafreefree—131KTVW—Mar 2025
Gemma 3 4B ITNvidiafreefree—131KTVW—Mar 2025
Llama 3.1 8B InstructNvidiafreefree—16KTWDec 2023Jan 2025
Phi-4-MiniNvidiafreefree—131KTWDec 2024Dec 2024
Qwen3-Next-80B-A3B-InstructNvidiafreefree—262KTDec 2024Dec 2024
nemotron-3-nano-30b-a3bNvidiafreefree—131KRTWSep 2024Dec 2024
Llama 3.3 70b InstructNvidiafreefree—128KTW—Nov 2024
Qwen2.5 Coder 32b InstructNvidiafreefree—128KTW—Nov 2024
studiovoiceNvidiafreefree—128KW—Oct 2024
Llama-3.2-90B-Vision-InstructNvidiafreefree—128KTVWDec 2023Sep 2024
Llama 3.2 11b Vision InstructNvidiafreefree—128KTVWDec 2023Sep 2024
Llama 3.2 1b InstructNvidiafreefree—128KTWDec 2023Sep 2024
Llama 3.2 3B InstructNvidiafreefree—33KW—Sep 2024
dracarys-llama-3.1-70b-instructNvidiafreefree—128KTW—Sep 2024
esm2-650mNvidiafreefree—128KW—Aug 2024
nemotron-mini-4b-instructNvidiafreefree—128KTW—Aug 2024
FLUX.1-devNvidiafreefree—4KAug 2024Aug 2024
FLUX.1-schnellNvidiafreefree—77WJul 2024Aug 2024
usdvalidateNvidiafreefree——W—Jul 2024
Gemma 2 2b ItNvidiafreefree—128KTW—Jul 2024
Llama 3.1 70b InstructNvidiafreefree—128KTW—Jul 2024
nv-embed-v1Nvidiafreefree—33KW—Jun 2024
solar-10.7b-instructNvidiafreefree—128KTW—Jun 2024
paligemmaNvidiafreefree—128KVW—May 2024
Mistral: Mixtral 8x22B InstructNvidiafreefree—66KTW—Apr 2024
rerank-qa-mistral-4bNvidiafreefree—128KW—Mar 2024
esmfoldNvidiafreefree—128KW—Mar 2024
BGE M3Nvidiafreefree—8KW—Jan 2024
Mistral: Mixtral 8x7B InstructNvidiafreefree—33KTW—Dec 2023
Whisper Large v3Nvidiafreefree——WSep 2023Sep 2023