# ![Nebius Token Factory logo](https://models.dev/logos/nebius.svg)Nebius Token Factory Access 46 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable. Learn more in the [Nebius Token Factory documentation](https://docs.tokenfactory.nebius.com/). ```bash NEBIUS_API_KEY=your-api-key ``` ```typescript import { Agent } from "@mastra/core/agent"; const agent = new Agent({ id: "my-agent", name: "My Agent", instructions: "You are a helpful assistant", model: "nebius/BAAI/bge-en-icl" }); // Generate a response const response = await agent.generate("Hello!"); // Stream a response const stream = await agent.stream("Tell me a story"); for await (const chunk of stream) { console.log(chunk); } ``` > **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Nebius Token Factory documentation](https://docs.tokenfactory.nebius.com/) for details. ## Models | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M | | --------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- | | `nebius/BAAI/bge-en-icl` | 33K | | | | | | $0.01 | — | | `nebius/BAAI/bge-multilingual-gemma2` | 8K | | | | | | $0.01 | — | | `nebius/black-forest-labs/flux-dev` | 77 | | | | | | — | — | | `nebius/black-forest-labs/flux-schnell` | 77 | | | | | | — | — | | `nebius/deepseek-ai/deepseek-r1-0528` | 128K | | | | | | $0.80 | $2 | | `nebius/deepseek-ai/deepseek-r1-0528-fast` | 131K | | | | | | $2 | $6 | | `nebius/deepseek-ai/deepseek-v3-0324` | 128K | | | | | | $0.50 | $2 | | `nebius/deepseek-ai/deepseek-v3-0324-fast` | 128K | | | | | | $0.75 | $2 | | `nebius/deepseek-ai/deepseek-v3.2` | 128K | | | | | | $0.30 | $0.45 | | `nebius/google/gemma-2-2b-it` | 8K | | | | | | $0.02 | $0.06 | | `nebius/google/gemma-2-9b-it-fast` | 8K | | | | | | $0.03 | $0.09 | | `nebius/google/gemma-3-27b-it` | 128K | | | | | | $0.10 | $0.30 | | `nebius/google/gemma-3-27b-it-fast` | 128K | | | | | | $0.20 | $0.60 | | `nebius/intfloat/e5-mistral-7b-instruct` | 33K | | | | | | $0.01 | — | | `nebius/meta-llama/Llama-3.3-70B-Instruct` | 128K | | | | | | $0.13 | $0.40 | | `nebius/meta-llama/llama-3.3-70b-instruct-fast` | 128K | | | | | | $0.25 | $0.75 | | `nebius/meta-llama/llama-guard-3-8b` | 8K | | | | | | $0.02 | $0.06 | | `nebius/meta-llama/meta-llama-3.1-8b-instruct` | 128K | | | | | | $0.02 | $0.06 | | `nebius/meta-llama/meta-llama-3.1-8b-instruct-fast` | 128K | | | | | | $0.03 | $0.09 | | `nebius/MiniMaxAI/minimax-m2.1` | 128K | | | | | | $0.30 | $1 | | `nebius/moonshotai/kimi-k2-instruct` | 200K | | | | | | $0.50 | $2 | | `nebius/moonshotai/kimi-k2-thinking` | 128K | | | | | | $0.60 | $3 | | `nebius/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.50 | $3 | | `nebius/NousResearch/hermes-4-405b` | 128K | | | | | | $1 | $3 | | `nebius/NousResearch/hermes-4-70b` | 128K | | | | | | $0.13 | $0.40 | | `nebius/nvidia/llama-3_1-nemotron-ultra-253b-v1` | 128K | | | | | | $0.60 | $2 | | `nebius/nvidia/nemotron-nano-v2-12b` | 32K | | | | | | $0.07 | $0.20 | | `nebius/nvidia/nvidia-nemotron-3-nano-30b-a3b` | 32K | | | | | | $0.06 | $0.24 | | `nebius/openai/gpt-oss-120b` | 128K | | | | | | $0.15 | $0.60 | | `nebius/openai/gpt-oss-20b` | 128K | | | | | | $0.05 | $0.20 | | `nebius/PrimeIntellect/intellect-3` | 128K | | | | | | $0.20 | $1 | | `nebius/qwen/qwen2.5-coder-7b-fast` | 128K | | | | | | $0.03 | $0.09 | | `nebius/qwen/qwen2.5-vl-72b-instruct` | 128K | | | | | | $0.25 | $0.75 | | `nebius/qwen/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.20 | $0.60 | | `nebius/qwen/qwen3-235b-a22b-thinking-2507` | 262K | | | | | | $0.20 | $0.80 | | `nebius/qwen/qwen3-30b-a3b-instruct-2507` | 128K | | | | | | $0.10 | $0.30 | | `nebius/qwen/qwen3-30b-a3b-thinking-2507` | 128K | | | | | | $0.10 | $0.30 | | `nebius/qwen/qwen3-32b` | 128K | | | | | | $0.10 | $0.30 | | `nebius/qwen/qwen3-32b-fast` | 128K | | | | | | $0.20 | $0.60 | | `nebius/qwen/qwen3-coder-30b-a3b-instruct` | 128K | | | | | | $0.10 | $0.30 | | `nebius/qwen/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.40 | $2 | | `nebius/qwen/qwen3-embedding-8b` | 33K | | | | | | $0.01 | — | | `nebius/qwen/qwen3-next-80b-a3b-thinking` | 128K | | | | | | $0.15 | $1 | | `nebius/zai-org/glm-4.5` | 128K | | | | | | $0.60 | $2 | | `nebius/zai-org/glm-4.5-air` | 128K | | | | | | $0.20 | $1 | | `nebius/zai-org/glm-4.7-fp8` | 128K | | | | | | $0.40 | $2 | ## Advanced Configuration ### Custom Headers ```typescript const agent = new Agent({ id: "custom-agent", name: "custom-agent", model: { url: "https://api.tokenfactory.nebius.com/v1", id: "nebius/BAAI/bge-en-icl", apiKey: process.env.NEBIUS_API_KEY, headers: { "X-Custom-Header": "value" } } }); ``` ### Dynamic Model Selection ```typescript const agent = new Agent({ id: "dynamic-agent", name: "Dynamic Agent", model: ({ requestContext }) => { const useAdvanced = requestContext.task === "complex"; return useAdvanced ? "nebius/zai-org/glm-4.7-fp8" : "nebius/BAAI/bge-en-icl"; } }); ```