Skip to main content

Model Providers

DeepSeek

Call DeepSeek chat and reasoning models through your Verdictan gateway. Your DeepSeek key stays on the gateway, and your application calls the gateway with its application token.

Start with a plain text reply. Reasoning models return extra fields, so look at a real response before your application displays or stores them.

Before you start​

  • A working gateway from the quickstart.
  • A DeepSeek API key, and one model ID that your account can use.
  • The gateway startup command, and a separate application token for test requests.

Configure the provider​

policy-config.yaml
pack:
  name: deepseek-integration
  version: 1.0.0
  enabled: true
policies:
  chain:
    - prompt-injection
providers:
  targets:
    - id: deepseek-primary
      provider: deepseek
      model: "replace-with-deepseek-model-id"
      base_url: https://api.deepseek.com
      secret_key_ref:
        env: VERDICTAN_DEEPSEEK_API_KEY

base_url must start with https://. The gateway appends /v1/chat/completions and sends the key from VERDICTAN_DEEPSEEK_API_KEY as a Bearer token.

Start and verify​

The CLI deployment procedure is an alternative to the Console step. It requires CLI 0.1.14 or later. Check In sync, then send the DeepSeek request below to verify model access.

With the quickstart in Docker, follow the container steps instead of steps 1 to 3.

  1. In the gateway terminal, set the key and lint the file:

    export VERDICTAN_DEEPSEEK_API_KEY="<provider-api-key>"
verdictan policy lint --file policy-config.yaml

  2. Restart the test gateway with the key in its environment.

  3. Deploy the file to the test agent in Configurations. If that agent already runs pack.version 1.0.0, increase the version first. Then wait for the gateway log line connected read model refresh applied updated config with your version as config_version. Try the change on a test gateway has the steps.

  4. In a second terminal, send a request for the configured model:

    export VERDICTAN_CLIENT_TOKEN="<application-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-deepseek-model-id","messages":[{"role":"user","content":"Reply with Hello."}]}'

choices[0].message.content contains the reply, and the request appears in History when capture is on, or in the delivered events.

Supported requests​

RequestSupport
Chat CompletionsYes. Streaming and tools work if the model supports them.
MessagesTranslated to Chat Completions
Responses, embeddings, image input, response_format, parallel tool callsNo

Failure behavior​

ProblemWhat to check
401 from the gatewayThe application token is active, and the key is set on the gateway host.
Provider authentication errorVERDICTAN_DEEPSEEK_API_KEY is set in the gateway process. Restart the gateway.
Model not foundThe request model matches the target, and your account can use it.
capability.unsupported_familyThe request is Chat Completions or Messages.
Provider 429 or another upstream errorThe response body and your DeepSeek balance and rate limits. See Error Handling.

Limits​

  • Model names, prices, rate limits, and data terms are in the DeepSeek API documentation.
  • The gateway passes the model ID unchanged. A reasoning model returns fields that a chat model does not. Check which fields your application uses before production.
  • A listener on a non-loopback address needs TLS and network controls.

Next steps​