DeepSeek

Guild supports DeepSeek models. This page lists the models Guild recognizes, the inference providers that serve them, and how to call them from an agent.


Name under Models in the credential form	DeepSeek
`provider` in `llmPreferences`	`"deepseek"`
Default model	`deepseek-v3.2`
Managed access	No. Add your own credential (BYOK).

Inference providers

DeepSeek models are served only through third-party inference providers, not a DeepSeek API.

Provider	Notes
AWS Bedrock	Serves `deepseek-v3.2` and `deepseek-r1`.
OpenRouter	Served under OpenRouter’s `deepseek/` namespace.
Fireworks AI	Serves DeepSeek models, such as `deepseek-v4.1-flash`.

Write the canonical model name, such as deepseek-v3.2, everywhere in Guild. Guild maps it to each provider’s own model ID.

Models

Guild prices and recognizes these DeepSeek model IDs. A policy or preference can also name any other model your credential can reach.

Model	Notes
`deepseek-v3.2`	The default.
`deepseek-r1`	A reasoning model.
`deepseek-v4.1-flash`	Served by Fireworks AI.

Set up DeepSeek

Guild has no managed key for DeepSeek. To use DeepSeek models, add a credential for a provider that serves them. Adding your first credential switches the whole account to bring your own key (BYOK).

Open Models & providers

Click Access & setup in the left nav, then Models & providers. In an organization, only admins can open it.

Add a credential

Click Add API key and choose an inference provider from the table above.

Enter the provider's secret

Give the credential a Name and paste your provider’s API key. AWS Bedrock asks for an IAM role and region instead.

Choose DeepSeek

Under Models, check DeepSeek. Keep deepseek-v3.2 as its default model or enter another from the list above. Then click Add Key.

To control which workspaces and agents can use DeepSeek models, add a model policy for the credential. For example, --models "deepseek-*" limits a policy to matching models:

guild llm policy create --credential <credential-id> --publisher DEEPSEEK --target-id <workspace-or-agent-id> --models "deepseek-*"

Use it from an agent

Agent code never names a credential. Guild resolves the call against the workspace owner’s settings. To ask for DeepSeek explicitly, put it in llmPreferences:

const result = await task.llm.generateText({
  prompt: "Summarize this text...",
  llmPreferences: [
    { provider: "deepseek", model: "deepseek-r1" },
    { provider: "deepseek" },
  ],
})

The first entry asks for deepseek-r1. The second falls back to the default model of the matching policy. Preferences are strict: if no credential or policy allows any of them, the call fails rather than using another publisher. See LLM preferences.

Models & providers for credentials, model policies, and the daily token limit
LLMs for task.llm and the unified LLM proxy
Usage for spend by model

Overview

The Smith

The Factory

Platform

Agent SDK

Inference providers

Models

Set up DeepSeek

Use it from an agent

​Inference providers

​Models

​Set up DeepSeek

​Use it from an agent

​Related pages

Inference providers

Models

Set up DeepSeek

Use it from an agent

Related pages