跳到主要内容
非官方简体中文翻译，内容版权归 Mastra 所有，遵循 Apache-2.0 许可。

Cortecs logoCortecs

Access 106 Cortecs models through Mastra's model router. Authentication is handled automatically using the CORTECS_API_KEY environment variable.

Learn more in the Cortecs documentation.

.env
CORTECS_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: "cortecs/apertus-70b"
});

// 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);
}
备注

Mastra uses the OpenAI-compatible /chat/completions endpoint. Some provider-specific features may not be available. Check the Cortecs documentation for details.

Models
Models的直接链接

ModelContextToolsReasoningImageAudioVideoInput $/1MOutput $/1M
cortecs/apertus-70b66K$1$2
cortecs/claude-4-5-sonnet200K$3$15
cortecs/claude-4-6-sonnet1.0M$3$16
cortecs/claude-haiku-4-5200K$1.00$5
cortecs/claude-haiku-5.51.0M$0.11$0.56
cortecs/claude-opus-51.0M$6$27
cortecs/claude-opus-5.51.0M$4$22
cortecs/claude-opus4-5200K$5$27
cortecs/claude-opus4-61.0M$5$27
cortecs/claude-opus4-71.0M$5$27
cortecs/claude-opus4-81.0M$5$27
cortecs/claude-sonnet-51.0M$2$11
cortecs/claude-sonnet-5.51.0M$2$11
cortecs/codestral-2508256K$0.37$1
cortecs/deepseek-v3.2164K$0.50$1
cortecs/deepseek-v4-flash-07311.0M$0.08$0.41
cortecs/deepseek-v4-pro1.0M$2$3
cortecs/deepseek-v4-pro-08131.0M$2$4
cortecs/deepseek-v4.1-flash1.0M$0.20$0.60
cortecs/deepseek-v4.1-flash-10171.0M$0.51$2
cortecs/devstral-2512256K$0.48$2
cortecs/gemini-2.5-flash1.0M$0.30$2
cortecs/gemini-2.5-pro1.0M$1$10
cortecs/gemini-3.1-flash-lite1.0M$0.27$2
cortecs/gemini-3.5-flash1.0M$2$10
cortecs/gemini-3.5-flash-lite1.0M$0.33$3
cortecs/gemini-3.6-flash1.0M$0.75$4
cortecs/gemini-3.7-flash1.0M$0.75$4
cortecs/gemini-3.8-flash1.0M$0.82$4
cortecs/gemini-4-argon1.0M$2$11
cortecs/gemma-3-27b-it131K$0.10$0.30
cortecs/gemma-4-26b-a4b-it262K$0.11$0.56
cortecs/gemma-4-31b-it262K$0.22$0.39
cortecs/glm-4.7-flash203K$0.08$0.48
cortecs/glm-5.1203K$1$4
cortecs/glm-5.21.0M$0.90$3
cortecs/glm-5.31.0M$0.51$2
cortecs/glm-5.3-flash1.0M$0.10$0.35
cortecs/gpt-4.11.0M$2$9
cortecs/gpt-4.1-mini1.0M$0.43$2
cortecs/gpt-4.1-nano1.0M$0.11$0.43
cortecs/gpt-4o128K$3$11
cortecs/gpt-4o-mini128K$0.16$0.64
cortecs/gpt-5400K$1$11
cortecs/gpt-5-mini400K$0.28$2
cortecs/gpt-5-nano400K$0.06$0.44
cortecs/gpt-5.1400K$1$11
cortecs/gpt-5.41.1M$3$15
cortecs/gpt-5.6-luna1.1M$0.22$1
cortecs/gpt-5.6-sol1.1M$4$22
cortecs/gpt-5.6-terra1.1M$2$13
cortecs/gpt-6-astra1.1M$12$61
cortecs/gpt-6-luna1.1M$0.12$0.60
cortecs/gpt-6-sol1.1M$2$12
cortecs/gpt-6.1-sol1.1M$2$12
cortecs/gpt-oss-120b131K$0.09$0.45
cortecs/gpt-oss-20b131K$0.04$0.17
cortecs/gpt-oss-safeguard-120b128K$0.18$0.70
cortecs/hermes-4-405b128K$1.00$3
cortecs/kimi-k2.6256K$0.47$3
cortecs/kimi-k2.7-code262K$0.66$3
cortecs/kimi-k31.0M$3$15
cortecs/llama-3.3-70b-instruct131K$0.72$0.72
cortecs/minicpm-v-4.532K$0.65$1
cortecs/minimax-m2400K$0.35$1
cortecs/minimax-m2.1196K$0.36$1
cortecs/minimax-m2.5196K$0.35$1
cortecs/minimax-m31.0M$0.30$1
cortecs/ministral-14b-2512256K$0.24$0.24
cortecs/ministral-3b-2512256K$0.12$0.12
cortecs/ministral-8b-2512256K$0.18$0.18
cortecs/mistral-7b-instruct-v0.232K$0.16$0.22
cortecs/mistral-large-240232K$4$13
cortecs/mistral-large-2512256K$0.61$2
cortecs/mistral-large-4-01.0M$0.77$2
cortecs/mistral-medium-3.5256K$2$8
cortecs/mistral-nemo-instruct-2407128K$0.14$0.14
cortecs/mistral-small-2503128K$0.11$0.33
cortecs/mistral-small-2603262K$0.16$0.63
cortecs/mistral-small-3.2-24b-instruct-2506131K$0.10$0.31
cortecs/mixtral-8x7B-instruct-v0.132K$0.49$0.76
cortecs/nemotron-nano-v2-12b128K$0.24$0.71
cortecs/nova-2-lite1.0M$0.37$3
cortecs/nova-lite-v1300K$0.07$0.28
cortecs/nova-micro-v1128K$0.04$0.16
cortecs/nova-pro-v1300K$0.92$4
cortecs/nvidia-nemotron-3-nano-30b-a3b256K$0.06$0.24
cortecs/pixtral-12b-2409128K$0.22$0.22
cortecs/pixtral-large-2502128K$2$6
cortecs/qwen2.5-vl-72b-instruct32K$1$1
cortecs/qwen3-235b-a22b-instruct-2507262K$0.20$0.60
cortecs/qwen3-30b-a3b-instruct-2507262K$0.10$0.30
cortecs/qwen3-32b16K$0.18$0.70
cortecs/qwen3-coder-30b-a3b-instruct262K$0.18$0.70
cortecs/qwen3-coder-next256K$0.17$0.89
cortecs/qwen3-vl-235b-a22b256K$0.62$3
cortecs/qwen3.5-397b-a17b262K$0.67$4
cortecs/qwen3.5-9b262K$0.11$0.17
cortecs/qwen3.6-27b262K$0.45$3
cortecs/qwen3.6-35b-a3b262K$0.17$0.56
cortecs/qwen3.8-2.4t-a95b262K$3$6
cortecs/qwen3.8-27b1.0M$0.10$0.40
cortecs/qwen3.8-flash-next262K$0.20$0.50
cortecs/qwen3guard-gen-0.6b32K——
cortecs/qwen3guard-gen-8b32K——
cortecs/voxtral-small-250732K$0.12$0.37
106 available models

Model availability, capabilities, context windows, and pricing are sourced from models.dev and may change.

Advanced configuration
Advanced configuration的直接链接

Custom headers
Custom headers的直接链接

src/mastra/agents/my-agent.ts
const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.cortecs.ai/v1",
    id: "cortecs/apertus-70b",
    apiKey: process.env.CORTECS_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic model selection
Dynamic model selection的直接链接

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
      ? "cortecs/voxtral-small-2507"
      : "cortecs/apertus-70b";
  }
});
On this page