Skip to main content

Nebius Token Factory logoNebius 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.

.env
NEBIUS_API_KEY=your-api-key
src/mastra/agents/my-agent.ts
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 for details.

Models
Direct link to Models

ModelContextToolsReasoningImageAudioVideoInput $/1MOutput $/1M
nebius/BAAI/bge-en-icl33K$0.01
nebius/BAAI/bge-multilingual-gemma28K$0.01
nebius/black-forest-labs/flux-dev77
nebius/black-forest-labs/flux-schnell77
nebius/deepseek-ai/DeepSeek-R1-0528128K$0.80$2
nebius/deepseek-ai/DeepSeek-R1-0528-fast131K$2$6
nebius/deepseek-ai/DeepSeek-V3-0324128K$0.50$2
nebius/deepseek-ai/DeepSeek-V3-0324-fast128K$0.75$2
nebius/deepseek-ai/DeepSeek-V3.2128K$0.30$0.45
nebius/google/gemma-2-2b-it8K$0.02$0.06
nebius/google/gemma-2-9b-it-fast8K$0.03$0.09
nebius/google/gemma-3-27b-it128K$0.10$0.30
nebius/google/gemma-3-27b-it-fast128K$0.20$0.60
nebius/intfloat/e5-mistral-7b-instruct33K$0.01
nebius/meta-llama/Llama-3.3-70B-Instruct128K$0.13$0.40
nebius/meta-llama/Llama-3.3-70B-Instruct-fast128K$0.25$0.75
nebius/meta-llama/Llama-Guard-3-8B8K$0.02$0.06
nebius/meta-llama/Meta-Llama-3.1-8B-Instruct128K$0.02$0.06
nebius/meta-llama/Meta-Llama-3.1-8B-Instruct-fast128K$0.03$0.09
nebius/MiniMaxAI/MiniMax-M2.1128K$0.30$1
nebius/moonshotai/Kimi-K2-Instruct200K$0.50$2
nebius/moonshotai/Kimi-K2-Thinking128K$0.60$3
nebius/moonshotai/Kimi-K2.5262K$0.50$3
nebius/NousResearch/Hermes-4-405B128K$1$3
nebius/NousResearch/Hermes-4-70B128K$0.13$0.40
nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1128K$0.60$2
nebius/nvidia/Nemotron-Nano-V2-12b32K$0.07$0.20
nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B32K$0.06$0.24
nebius/openai/gpt-oss-120b128K$0.15$0.60
nebius/openai/gpt-oss-20b128K$0.05$0.20
nebius/PrimeIntellect/INTELLECT-3128K$0.20$1
nebius/Qwen/Qwen2.5-Coder-7B-fast128K$0.03$0.09
nebius/Qwen/Qwen2.5-VL-72B-Instruct128K$0.25$0.75
nebius/Qwen/Qwen3-235B-A22B-Instruct-2507262K$0.20$0.60
nebius/Qwen/Qwen3-235B-A22B-Thinking-2507262K$0.20$0.80
nebius/Qwen/Qwen3-30B-A3B-Instruct-2507128K$0.10$0.30
nebius/Qwen/Qwen3-30B-A3B-Thinking-2507128K$0.10$0.30
nebius/Qwen/Qwen3-32B128K$0.10$0.30
nebius/Qwen/Qwen3-32B-fast128K$0.20$0.60
nebius/Qwen/Qwen3-Coder-30B-A3B-Instruct128K$0.10$0.30
nebius/Qwen/Qwen3-Coder-480B-A35B-Instruct262K$0.40$2
nebius/Qwen/Qwen3-Embedding-8B33K$0.01
nebius/Qwen/Qwen3-Next-80B-A3B-Thinking128K$0.15$1
nebius/zai-org/GLM-4.5128K$0.60$2
nebius/zai-org/GLM-4.5-Air128K$0.20$1
nebius/zai-org/GLM-4.7-FP8128K$0.40$2
46 available models

Advanced Configuration
Direct link to Advanced Configuration

Custom Headers
Direct link to Custom Headers

src/mastra/agents/my-agent.ts
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
Direct link to Dynamic Model Selection

src/mastra/agents/my-agent.ts
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";
}
});
On this page