← Providers

Nebius Token Factory

nebius·Cloud·34 models·Official docs ↗
At a glance
Models hosted34With public price 34
Cheapest anywhere1
Model typesText / Chat 33Embedding 1
Cheapest model hereQwen3-Embedding-8B
SDK package@ai-sdk/openai-compatible
APIhttps://api.tokenfactory.nebius.com/v1

Hosted models by blended price asc

34 of 34
Cheapest here?
Qwen3-Embedding-8BEmbeddingQwen/Qwen3-Embedding-8B$0.01$032,7681.0× pricier
Nemotron 3 Nano 30B A3Bnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B$0.06$0.24$0.00632,0001.2× pricier
Nemotron 3 Nano Omninvidia/Nemotron-3-Nano-Omni$0.06$0.24$0.00665,5361.1× pricier
Qwen3 32BQwen/Qwen3-32B$0.10$0.30$0.01128,0001.2× pricier
Qwen3 30B A3B Instruct 2507Qwen/Qwen3-30B-A3B-Instruct-2507$0.10$0.30$0.01128,0001.8× pricier
gemma-3-27b-itgoogle/gemma-3-27b-it$0.10$0.30$0.01110,0001.0× pricier
DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash$0.14$0.28$0.14131,0722.2× pricier
Llama-3.3-70B-Instructmeta-llama/Llama-3.3-70B-Instruct$0.13$0.40$0.013128,0002.1× pricier
Hermes 4 70BNousResearch/Hermes-4-70B$0.13$0.40$0.013128,0001.0× pricier
gpt-oss-120b-fastopenai/gpt-oss-120b-fast$0.10$0.50$0.018,000Only channel
GPT OSS 120Bopenai/gpt-oss-120b$0.15$0.60$0.015128,0004.8× pricier
Qwen3 235B-A22B Instruct 2507Qwen/Qwen3-235B-A22B-Instruct-2507$0.20$0.60262,1441.8× pricier
DeepSeek V3.2deepseek-ai/DeepSeek-V3.2$0.30$0.45$0.03163,0001.5× pricier
Qwen2.5-VL 72B InstructQwen/Qwen2.5-VL-72B-Instruct$0.25$0.75$0.025128,0001.0× pricier
Qwen3-Next 80B-A3B (Thinking)Qwen/Qwen3-Next-80B-A3B-Thinking$0.15$1.20$0.015128,0001.5× pricier
Qwen3-Next-80B-A3B-Thinking-fastQwen/Qwen3-Next-80B-A3B-Thinking-fast$0.15$1.20$0.0158,000Only channel
INTELLECT-3PrimeIntellect/INTELLECT-3$0.20$1.10$0.02128,000Only channel
Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b$0.30$0.90256,0002.7× pricier
MiniMax-M2.5MiniMaxAI/MiniMax-M2.5$0.30$1.20$0.03196,6081.6× pricier
MiniMax-M3MiniMaxAI/MiniMax-M3$0.30$1.201,048,5761.3× pricier
MiniMax-M2.5-fastMiniMaxAI/MiniMax-M2.5-fast$0.30$1.20$0.038,000Only channel
DeepSeek-V3.2-fastdeepseek-ai/DeepSeek-V3.2-fast$0.40$2.00$0.048,000Only channel
Qwen3-235B-A22B-Thinking-2507-fastQwen/Qwen3-235B-A22B-Thinking-2507-fast$0.50$2.00$0.058,000Only channel
llama-3.1-nemotron-ultra-253b-v1nvidia/Llama-3_1-Nemotron-Ultra-253B-v1$0.60$1.80$0.06128,0001.0× pricier
Kimi K2.5moonshotai/Kimi-K2.5$0.50$2.50$0.05256,0001.5× pricier
Kimi K2.5 Fastmoonshotai/Kimi-K2.5-fast$0.50$2.50$0.05256,000Lowest anywhere
Qwen3.5 397B-A17BQwen/Qwen3.5-397B-A17B$0.60$3.60$0.06262,1443.5× pricier
Qwen3.5-397B-A17B-fastQwen/Qwen3.5-397B-A17B-fast$0.60$3.60$0.068,000Only channel
Hermes 4 405BNousResearch/Hermes-4-405B$1.00$3.00$0.10128,0001.0× pricier
GLM-5zai-org/GLM-5$1.00$3.20$0.10200,0001.9× pricier
Kimi K2.7 Codemoonshotai/Kimi-K2.7-Code$0.95$4.00262,1443.6× pricier
GLM-5.2zai-org/GLM-5.2$1.40$4.40432,0004.4× pricier
DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro$1.75$3.50$0.151,000,0005.0× pricier
Kimi K3moonshotai/Kimi-K3$3.00$15.00$3.001,048,5761.7× pricier