LiteLLMModels

Nebius AI Studio model pricing

As of October 10, 2026, 55 Nebius AI Studio models are available through LiteLLM. The most recently added are DeepSeek V4.1 Flash, Cosmos3 Super Reasoner, Hermes 4 405B. Prices below are Nebius AI Studio's list prices.

How to call Nebius AI Studio with LiteLLM

Nebius AI Studio models

ModelLabPriceContextProvidersAdded
DeepSeek V4.1 FlashDeepSeek$0.30 / $1.20 per 1M tokens1M8Sep 2026
Cosmos3 Super ReasonerNVIDIA$0.10 / $0.30 per 1M tokens256K1Sep 2026
Hermes 4 405B–$1 / $3 per 1M tokens128K1Sep 2026
Hermes 4 70B–$0.13 / $0.40 per 1M tokens128K1Sep 2026
Minicpm V 4.5–$0.658 / $1.11 per 1M tokens32K1Sep 2026
Nemotron 3 Nano OmniNVIDIA$0.06 / $0.24 per 1M tokens256K1Sep 2026
Nemotron 3 Super 120B A12BNVIDIA$0.30 / $0.90 per 1M tokens256K1Sep 2026
Nvidia Nemotron 3 Nano 30B A3BNVIDIA$0.06 / $0.24 per 1M tokens256K1Sep 2026
GLM 5.3Z.ai$1.40 / $4.40 per 1M tokens1M12Aug 2026
GLM 5.3 FlashZ.ai$0.15 / $0.50 per 1M tokens1M11Aug 2026
Qwen3.8 27BAlibaba$0.45 / $3 per 1M tokens256K5Aug 2026
Nemotron 3 Ultra 550B A55BNVIDIA$1 / $3 per 1M tokens1M3Aug 2026
Kimi K3Moonshot AI$3 / $15 per 1M tokens1M13Aug 2026
Nemotron 3.5 LightningNVIDIA$0.06 / $0.24 per 1M tokens1M1Aug 2026
DeepSeek V4 FlashDeepSeek$0.14 / $0.28 per 1M tokens1M22Jun 2026
DeepSeek V4 ProDeepSeek$1.32 / $3.96 per 1M tokens979K17Jun 2026
GLM 5.2Z.ai$1.40 / $4.40 per 1M tokens1M19Jun 2026
Kimi K2.7 CodeMoonshot AI$0.95 / $4 per 1M tokens256K14Jun 2026
MiniMax M3MiniMax$0.30 / $1.20 per 1M tokens1M9Jun 2026
GLM 5.1Z.ai$1.40 / $4.40 per 1M tokens198K10May 2026
Kimi K2.6Moonshot AI$0.95 / $4 per 1M tokens256K13Apr 2026
BGE En Icl–$0.01 per 1M tokens32K1Mar 2026
BGE Multilingual Gemma2–$0.01 per 1M tokens8K2Mar 2026
E5 Mistral 7B Instruct–$0.01 per 1M tokens32K1Mar 2026
Qwen3.5 397B A17BAlibaba$0.60 / $3.60 per 1M tokens256K7Mar 2026
MiniMax M2.5MiniMax$0.30 / $1.20 per 1M tokens192K7Feb 2026
Qwen2 VL 72B InstructAlibaba$0.13 / $0.40 per 1M tokens128K3Dec 2025
Qwen2 VL 7B InstructAlibaba$0.02 / $0.06 per 1M tokens128K2Dec 2025
Qwen2.5 32B InstructAlibaba$0.06 / $0.20 per 1M tokens128K2Dec 2025
Qwen3 30B A3B Instruct 2507Alibaba$0.10 / $0.30 per 1M tokens256K3Dec 2025
Qwen3 Embedding 8BAlibaba$0.01 per 1M tokens40K5Dec 2025
Qwen3 Next 80B A3B ThinkingAlibaba$0.15 / $1.20 per 1M tokens128K9Sep 2025
GPT OSS 120BOpenAI$0.15 / $0.60 per 1M tokens128K22Aug 2025
Mistral Nemo InstructMistral AI$0.04 / $0.12 per 1M tokens128K5Aug 2025
Qwen2.5 Coder 7BAlibaba$0.01 / $0.03 per 1M tokens32K3Aug 2025
Qwen3 235B A22B Instruct 2507Alibaba$0.20 / $0.60 per 1M tokens256K8Aug 2025
Hermes 3 Llama 3.1 405B–$1 / $3 per 1M tokens128K2Jul 2025
Llama 3.1 Nemotron Ultra 253B V1Meta$0.60 / $1.80 per 1M tokens128K1Jul 2025
Llama 3.3 Nemotron Super 49B V1Meta$0.10 / $0.40 per 1M tokens128K1Jul 2025
Qwen2.5 VL 72B InstructAlibaba$0.25 / $0.75 per 1M tokens32K5Jul 2025
Qwen3 14BAlibaba$0.08 / $0.24 per 1M tokens32K4Jul 2025
Qwen3 235B A22BAlibaba$0.20 / $0.60 per 1M tokens256K5Jul 2025
Qwen3 30B A3BAlibaba$0.10 / $0.30 per 1M tokens32K9Jul 2025
Qwen3 4BAlibaba$0.08 / $0.24 per 1M tokens32K3Jul 2025
Qwen3 32BAlibaba$0.10 / $0.30 per 1M tokens40K11May 2025
QwQ 32BAlibaba$0.15 / $0.45 per 1M tokens32K7May 2025
Gemma 3 27B ITGoogle$0.10 / $0.30 per 1M tokens110K6Mar 2025
DeepSeek R1 Distill Llama 70BDeepSeek$0.25 / $0.75 per 1M tokens128K9Feb 2025
DeepSeek R1DeepSeek$0.80 / $2.40 per 1M tokens128K16Jan 2025
DeepSeek V3DeepSeek$0.50 / $1.50 per 1M tokens128K15Jan 2025
Llama 3.3 70B InstructMeta$0.13 / $0.40 per 1M tokens128K18Dec 2024
Qwen2.5 72B InstructAlibaba$0.13 / $0.40 per 1M tokens128K6Dec 2024
Llama 3.1 405B InstructMeta$1 / $3 per 1M tokens128K7Jul 2024
Llama 3.1 70B InstructMeta$0.13 / $0.40 per 1M tokens128K11Jul 2024
Llama 3.1 8B InstructMeta$0.02 / $0.06 per 1M tokens128K13Jul 2024