Codestral
Code-Generierung mit dem Codestral-Modell von Mistral.
api.langdock.com durch die Base URL deines Deployments: <deployment-url>/api/publicRate Limits
Die Standard-Limits sind 500 RPM (Anfragen pro Minute) und 60.000 TPM (Tokens pro Minute).- RPM wird je Workspace, Modell und API-Key begrenzt.
- TPM teilen sich alle API-Keys, die dasselbe Modell in einem Workspace verwenden.
- In Dedicated Deployments können Admins unter Einstellungen > Workspace > Produkte > API eigene Limits je Modell festlegen.
429 Too Many Requests Antwort.
Verwendung des Continue AI Code Agents
Die Verwendung des Codestral-Modells in Kombination mit Chat-Completion-Modellen der Langdock API ermöglicht es, den Open-Source-KI-Code-Agenten Continue (continue.dev) vollständig über die Langdock API zu nutzen. Continue ist als VS Code-Erweiterung und als JetBrains-Erweiterung verfügbar. Um die von Continue verwendeten Modelle anzupassen, bearbeite die Konfigurationsdatei unter~/.continue/config.yaml (MacOS / Linux) oder %USERPROFILE%\.continue\config.yaml (Windows). Das ältere config.json Format ist veraltet.
Nachfolgend findest du ein Beispiel-Setup für die Verwendung von Continue mit dem Codestral-Modell für Autovervollständigung und Claude Sonnet 4.6 und GPT-5.2-Modellen für Chats und Bearbeitungen, die alle über die Langdock API bereitgestellt werden.
Autorisierungen
API key as Bearer token. Format "Bearer YOUR_API_KEY"
Pfadparameter
The region of the API to use.
eu Body
ID of the model to use. Only compatible for now with:
codestral-2501
The text/code to complete.
What sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both. The default value varies depending on the model you are targeting. Call the /models endpoint to retrieve the appropriate value.
0 <= x <= 1.5Nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
0 <= x <= 1The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length.
x >= 0Whether to stream back partial progress. If set, tokens will be sent as data-only server-side events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON.
Stop generation if this token is detected. Or if one of these tokens is detected when providing an array
The seed to use for random sampling. If set, different calls will generate deterministic results.
x >= 0Optional text/code that adds more context for the model. When given a prompt and a suffix the model will fill what is between them. When suffix is not provided, the model will simply execute completion starting with prompt.
The minimum number of tokens to generate in the completion.
x >= 0Antwort
Successful Response