Nebius Token Factory
Provider ID: nebius
Details
SDK package@ai-sdk/openai-compatible
Models32
APIhttps://api.tokenfactory.nebius.com/v1
Links
Documentation
Auth: NEBIUS_API_KEY
Models (32)
MiniMax-M2.5
MiniMax model for chat, coding, office work, and agentic tasks
196,608 ctxreasoning
MiniMax-M2.5-fast
Legacy model retained for compatibility with older integrations
8,000 ctxreasoning
MiniMax-M3
MiniMax multimodal model for long-context coding, perception, and agent planning
1,048,576 ctxreasoning
Hermes-4-405B
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
128,000 ctxreasoning
Hermes-4-70B
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
128,000 ctxreasoning
INTELLECT-3
Legacy model retained for compatibility with older integrations
128,000 ctx
Qwen2.5-VL-72B-Instruct
Qwen vision-language model for visual reasoning, documents, and agent tasks
128,000 ctx
Qwen3 235B A22B Instruct 2507
Qwen instruction model for multilingual chat, reasoning, and tool use
262,144 ctx
Qwen3-235B-A22B-Thinking-2507-fast
Legacy model retained for compatibility with older integrations
8,000 ctxreasoning
Qwen3-30B-A3B-Instruct-2507
Qwen instruction model for multilingual chat, reasoning, and tool use
128,000 ctx
Qwen3-32B
Qwen instruction model for multilingual chat, reasoning, and tool use
128,000 ctx
Qwen3-Embedding-8B
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
32,768 ctx
Qwen3-Next-80B-A3B-Thinking
Qwen reasoning model for deliberate problem solving, math, and coding
128,000 ctxreasoning
Qwen3-Next-80B-A3B-Thinking-fast
Legacy model retained for compatibility with older integrations
8,000 ctxreasoning
Qwen3.5-397B-A17B
Qwen instruction model for multilingual chat, reasoning, and tool use
262,144 ctxreasoning
Qwen3.5-397B-A17B-fast
Legacy model retained for compatibility with older integrations
8,000 ctxreasoning
DeepSeek-V3.2
Legacy model retained for compatibility with older integrations
163,000 ctxreasoning
DeepSeek-V3.2-fast
Legacy model retained for compatibility with older integrations
8,000 ctxreasoning
DeepSeek V4 Pro
Open MoE flagship with million-token context for coding and long agent runs
1,000,000 ctxreasoning
Gemma-3-27b-it
Open Gemma instruction model for efficient chat and self-hosted deployments
110,000 ctx
Llama-3.3-70B-Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
128,000 ctx
Kimi-K2.5
Legacy model retained for compatibility with older integrations
256,000 ctxreasoning
Kimi-K2.5-fast
Legacy model retained for compatibility with older integrations
256,000 ctxreasoning
Kimi K2.7 Code
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking
262,144 ctxreasoning
Llama-3.1-Nemotron-Ultra-253B-v1
Flagship Nemotron model for high-throughput reasoning and complex agents
128,000 ctx
Nemotron-3-Nano-30B-A3B
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
32,000 ctx
Nemotron-3-Nano-Omni
Open Nemotron omni model combining reasoning with text, vision, and audio
65,536 ctxreasoning
Nemotron-3-Super-120B-A12B
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
256,000 ctxreasoning
gpt-oss-120b
Open-weight GPT model for self-hosted reasoning and instruction-following workloads
128,000 ctxreasoning
gpt-oss-120b-fast
Legacy model retained for compatibility with older integrations
8,000 ctxreasoning
GLM-5
Legacy model retained for compatibility with older integrations
200,000 ctxreasoning
GLM-5.2
Open flagship GLM for long-horizon coding agents and million-token context work
432,000 ctxreasoning
Community Rating
—
No ratings yet
Sign in to rate