Mistral AI
Call Mistral chat and embedding models through your Verdictan gateway. Your Mistral key stays on the gateway, and your application calls the gateway with its API token.
Configure the provider
Each target serves one model. For chat and embeddings, configure one target for each, and the gateway picks the target whose model matches the request.
pack:
name: mistral-integration
version: 1.0.0
enabled: true
policies:
chain:
- prompt-injection
providers:
targets:
- id: mistral-chat
provider: mistral
model: "replace-with-mistral-chat-model-id"
base_url: https://api.mistral.ai
secret_key_ref:
env: VERDICTAN_MISTRAL_API_KEY
- id: mistral-embed
provider: mistral
model: "mistral-embed"
base_url: https://api.mistral.ai
secret_key_ref:
env: VERDICTAN_MISTRAL_API_KEYThe gateway appends the path for each request family, such as /v1/chat/completions or /v1/embeddings, and sends the key from VERDICTAN_MISTRAL_API_KEY as a Bearer token. Leave out the mistral-embed target if you only need chat.
Start and verify
To deploy from your terminal, use CLI 0.1.14 or later instead of the Console step. Check In sync. Then use the chat request below to verify the Mistral model.
With the quickstart in Docker, follow the container steps instead of steps 1 to 3.
-
In the gateway terminal, set the key and lint the file:
export VERDICTAN_MISTRAL_API_KEY="<provider-api-key>" verdictan policy lint --file policy-config.yaml -
Restart the test gateway with the key in its environment.
-
Deploy the file to the test agent in Configurations. If that agent already runs
pack.version1.0.0, increase the version first. Then wait for the gateway log lineconnected read model refresh applied updated configwith your version asconfig_version. Try the change on a test gateway has the steps. -
In a second terminal, send a chat request:
export VERDICTAN_CLIENT_TOKEN="<api-token>" curl --fail-with-body http://127.0.0.1:41002/v1/chat/completions \ -H "Authorization: Bearer ${VERDICTAN_CLIENT_TOKEN}" \ -H "Content-Type: application/json" \ -d '{"model":"replace-with-mistral-chat-model-id","messages":[{"role":"user","content":"Reply with Hello."}]}' -
If you kept the embedding target, send an embeddings request:
curl --fail-with-body http://127.0.0.1:41002/v1/embeddings \ -H "Authorization: Bearer ${VERDICTAN_CLIENT_TOKEN}" \ -H "Content-Type: application/json" \ -d '{"model":"mistral-embed","input":["Hello"]}'
The chat reply is in choices[0].message.content, and the vectors are in data[].embedding. The chat request appears in History when capture is on, or in the delivered events.
Supported requests
| Request | Support |
|---|---|
| Chat Completions | Yes. Streaming and tools work if the model supports them. |
| Messages | Translated to Chat Completions |
| Embeddings | Yes, with an embedding model |
Responses, audio, image input, response_format, parallel tool calls | No |
The gateway authenticates embeddings requests and applies provider access rules and budgets. Supported input-stage controls run on embeddings text. Output controls do not apply. See Runtime request families.
Failure behavior
| Problem | What to check |
|---|---|
401 from the gateway | The API token is active, and the key is set on the gateway host. |
| Provider authentication error | VERDICTAN_MISTRAL_API_KEY is set in the gateway process. Restart the gateway. |
| Model not found | The request model matches one target model. |
Error from /v1/embeddings | The request names the embedding model, not the chat model. |
Provider 429 or another upstream error | The response body and your Mistral limits. See Handle policy blocks and gateway errors. |
Limits
- Model names, prices, rate limits, and data terms are in the Mistral AI documentation.
- Streaming and tools vary by model. Test each one with your model.
- A listener on a non-loopback address needs TLS and network controls.
Next steps
- Provider configuration: target fields, routing, and fallback.
- Runtime request families: request families and their policy stages.