> Discover all available pages from the documentation index: https://mastra.zisheng.pro/ja/llms.txt # ![Snowflake Cortex ロゴ](https://models.dev/logos/snowflake-cortex.svg)Snowflake Cortex Mastra のモデルルーターを通じて 21 個の Snowflake Cortex モデルを利用できます。認証には `SNOWFLAKE_CORTEX_PAT` 環境変数が自動的に使用されます。 Configure `SNOWFLAKE_ACCOUNT` as well. 詳しくは、[Snowflake Cortex のドキュメント](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api)を参照してください。 ```bash SNOWFLAKE_ACCOUNT=your-value SNOWFLAKE_CORTEX_PAT=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: "snowflake-cortex/claude-fable-5" }); // 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); } ``` > **情報:** Mastra は OpenAI 互換の `/chat/completions` endpoint を使用します。一部の Provider 固有機能は利用できない場合があります。詳しくは、[Snowflake Cortex のドキュメント](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api)を確認してください。 ## モデル | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M | | ----------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- | | `snowflake-cortex/claude-fable-5` | 1.0M | | | | | | — | — | | `snowflake-cortex/claude-haiku-4-5` | 200K | | | | | | — | — | | `snowflake-cortex/claude-opus-4-7` | 1.0M | | | | | | — | — | | `snowflake-cortex/claude-opus-4-8` | 1.0M | | | | | | — | — | | `snowflake-cortex/claude-sonnet-4-5` | 200K | | | | | | — | — | | `snowflake-cortex/claude-sonnet-4-6` | 1.0M | | | | | | — | — | | `snowflake-cortex/deepseek-r1` | 128K | | | | | | — | — | | `snowflake-cortex/gemini-3.1-pro` | 1.0M | | | | | | — | — | | `snowflake-cortex/mistral-large2` | 262K | | | | | | — | — | | `snowflake-cortex/openai-gpt-4.1` | 1.0M | | | | | | — | — | | `snowflake-cortex/openai-gpt-5` | 400K | | | | | | — | — | | `snowflake-cortex/openai-gpt-5-mini` | 272K | | | | | | — | — | | `snowflake-cortex/openai-gpt-5-nano` | 400K | | | | | | — | — | | `snowflake-cortex/openai-gpt-5.1` | 400K | | | | | | — | — | | `snowflake-cortex/openai-gpt-5.2` | 400K | | | | | | — | — | | `snowflake-cortex/openai-gpt-5.4` | 1.1M | | | | | | — | — | | `snowflake-cortex/openai-gpt-5.5` | 1.1M | | | | | | — | — | | `snowflake-cortex/openai-gpt-5.6-luna` | 1.1M | | | | | | — | — | | `snowflake-cortex/openai-gpt-5.6-sol` | 1.1M | | | | | | — | — | | `snowflake-cortex/openai-gpt-5.6-terra` | 1.1M | | | | | | — | — | | `snowflake-cortex/snowflake-llama3.3-70b` | 128K | | | | | | — | — | ## 高度な設定 ### カスタムヘッダー ```typescript const agent = new Agent({ id: "custom-agent", name: "custom-agent", model: { url: "https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1", id: "snowflake-cortex/claude-fable-5", apiKey: process.env.SNOWFLAKE_CORTEX_PAT, headers: { "X-Custom-Header": "value" } } }); ``` ### 動的なモデル選択 ```typescript const agent = new Agent({ id: "dynamic-agent", name: "Dynamic Agent", model: ({ requestContext }) => { const useAdvanced = requestContext.task === "complex"; return useAdvanced ? "snowflake-cortex/snowflake-llama3.3-70b" : "snowflake-cortex/claude-fable-5"; } }); ```