SambaNova

Call SambaNova Cloud models through your Verdictan gateway. Your SambaNova key stays on the gateway, and your application calls the gateway with its application token.

Verdictan has no SambaNova-specific adapter. The target uses the generic OpenAI-compatible path, so test your model and each feature you need before production.

Before you start

• A working gateway from the quickstart.
• A SambaNova 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

The gateway has no default address for SambaNova, so always set base_url. Check the current service address in the SambaNova documentation.

policy-config.yaml

pack:
  name: sambanova-integration
  version: 1.0.0
  enabled: true
policies:
  chain:
    - prompt-injection
providers:
  targets:
    - id: sambanova-primary
      provider: sambanova
      model: "replace-with-sambanova-model-id"
      base_url: https://api.sambanova.ai
      secret_key_ref:
        env: VERDICTAN_SAMBANOVA_API_KEY

The gateway appends /v1/chat/completions and sends the key from VERDICTAN_SAMBANOVA_API_KEY as a Bearer token.

Start and verify

For a file-based deployment, follow Deploy from the CLI with CLI 0.1.14 or later. Wait for In sync. Then send the SambaNova request below with the application token.

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_SAMBANOVA_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-sambanova-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

Request	Support
Chat Completions	Yes
Messages	Translated to Chat Completions
Streaming, tools	Not tested. Check them with your model.
Responses, embeddings, audio, image input, response_format, parallel tool calls	No

Failure behavior

Problem	What to check
401 from the gateway	The application token is active, and the key is set on the gateway host.
Provider authentication error	VERDICTAN_SAMBANOVA_API_KEY is set in the gateway process. Restart the gateway.
Connection error or 404	base_url is set to the current SambaNova service address.
Model not found	The request model matches the target, and your account can use it.
Provider 429 or another upstream error	The response body and your SambaNova limits. See Error Handling.

Limits

• Model names, prices, rate limits, and data terms are in the SambaNova Cloud documentation.
• 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.