FeaturesBring Your Own LLM

DeepSeek

Configure jambonz to use DeepSeek's V4 family models.

DeepSeek’s V4 models offer strong reasoning at substantially lower cost than equivalent OpenAI or Anthropic tiers. The wire is OpenAI-compatible (chat completions, streaming, tools), so the integration is straightforward.

Get credentials

  1. Sign in at https://platform.deepseek.com.
  2. Open API keys in the dashboard (direct link: https://platform.deepseek.com/api_keys).
  3. Click Create new API key, copy the value.

Configure in jambonz

In the portal: Account → LLM Services → + Add LLM Service → DeepSeek.

API Key
stringRequired

The key from DeepSeek’s dashboard.

Base URL
string

Defaults to https://api.deepseek.com/v1. Override for self-hosted DeepSeek deployments or proxy endpoints.

Click Test to verify.

Use in an agent verb

1session.agent({
2  llm: {
3    vendor: 'deepseek',
4    model: 'deepseek-v4-flash',
5    llmOptions: {
6      systemPrompt: 'You are a helpful voice assistant.',
7    },
8  },
9  stt: { vendor: 'deepgram', language: 'en-US' },
10  tts: { vendor: 'cartesia', voice: 'sonic-english' },
11  turnDetection: 'krisp',
12  bargeIn: { enable: true },
13  actionHook: '/agent-complete',
14}).send();

Available Models

See DeepSeek’s models & pricing page for the full list and current pricing. Common picks:

ModelNotes
deepseek-v4-flashDefault — fast, cheap, tool-capable
deepseek-v4-proHigher quality at higher cost

Quirks & errors

deepseek-chat and deepseek-reasoner are deprecated — older V3-era ids that the manifest flags as deprecated: true. They still work in some accounts but are scheduled for removal. Switch to deepseek-v4-flash or deepseek-v4-pro.

Tool-calling reliability is weaker than OpenAI/Anthropic on shorter prompts. If your agent depends on consistent tool invocation, test thoroughly with realistic prompts. For complex tool flows, consider Claude or GPT-4o.

401 — key revoked or copied with whitespace. Regenerate at platform.deepseek.com/api_keys.