HERMES + DEEPSEEK

Use DeepSeek in Hermes Agent.

DeepSeek V4 supports both OpenAI chat completions and Anthropic messages protocols through RunAPI. Hermes Agent connects via the custom:runapi provider — same base URL and key you use for other models. Activate reasoning mode with a request parameter. RunAPI prices DeepSeek at 50% of official rates.

one API key · OpenAI + Anthropic protocols · streaming support
Use RunAPI to call DeepSeek V4 Pro through Hermes Agent's custom:runapi provider.

Requirements:
- Use the custom:runapi provider already configured in Hermes Agent
- Call the RunAPI chat completions endpoint at https://runapi.ai/v1/chat/completions
- Set model to "deepseek-v4-pro"
- The RUNAPI_API_KEY environment variable provides authorization
- The response streams back as SSE events in OpenAI chat completions format
- To enable reasoning, set thinking.type to "enabled" in the request body
curl -X POST https://runapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [
      {"role": "system", "content": "You are a helpful coding assistant."},
      {"role": "user", "content": "Write a Python function that finds the longest palindromic substring in O(n) time using Manacher algorithm."}
    ],
    "stream": true,
    "max_tokens": 4096
  }'
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "deepseek-v4-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here is Manacher's algorithm implementation..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 356,
    "total_tokens": 398
  }
}
Copy the curl command to test deepseek
HOW IT WORKS

Use DeepSeek in Hermes Agent in three steps

1

Configure RunAPI provider

Set the RUNAPI_API_KEY environment variable. If you already added RunAPI as custom:runapi in Hermes Agent, the same provider and key work for DeepSeek — no extra configuration. If not, add RunAPI with base_url https://runapi.ai/v1 and api_mode chat_completions.

export RUNAPI_API_KEY=runapi_xxx
2

Select a DeepSeek model

Switch the model to deepseek-v4-pro for quality or deepseek-v4-flash for speed. Both use the /v1/chat/completions endpoint through the custom:runapi provider. Enable reasoning by passing thinking.type set to enabled — no separate model entry needed.

model: deepseek-v4-pro
3

Stream the response

Hermes Agent receives the response as an SSE stream in OpenAI chat completions format. Token usage appears in the final event. Switch between DeepSeek, GPT, and Claude models without changing the provider config — only the model field changes.

stream: true
PARAMETERS

DeepSeek chat completions parameters

Parameter Type Description
model string Required. deepseek-v4-pro or deepseek-v4-flash.
messages array Required. Array of message objects with role (system, user, assistant) and content fields.
stream boolean Optional. Set to true for SSE streaming. Default false.
max_tokens integer Optional. Maximum number of tokens to generate.
temperature number Optional. Sampling temperature between 0 and 2. Lower values are more deterministic.
thinking object Optional. Set type to "enabled" to activate DeepSeek's built-in reasoning mode.

What is DeepSeek on Hermes Agent?

DeepSeek V4 is a budget-friendly LLM that works through both OpenAI and Anthropic protocol surfaces on RunAPI. Hermes Agent calls it through the same custom:runapi provider used for GPT and Claude -- just change the model parameter. Built-in reasoning mode activates with a request parameter, and RunAPI prices DeepSeek at 50% of the already-low official rates, making it the cheapest reasoning-capable model available through a single API key.

DeepSeek use cases

Self-hosting alternative evaluation

Test DeepSeek through RunAPI's API before deciding whether to self-host the open-source weights. If API costs stay below your infrastructure break-even, keep using the hosted version. If volume justifies it, deploy locally with the same model.

Building reasoning UIs that show chain-of-thought

Enable thinking mode and display the thinking tokens in your UI so users can see how the model worked through a problem. Useful for tutoring apps, code debugging tools, or decision support systems.

High-volume batch processing at minimum cost

Run DeepSeek Flash for fast, cheap processing of large document sets, classification tasks, or data extraction jobs where per-token cost matters more than peak quality.

FAQ

DeepSeek + Hermes Agent questions

Hermes Agent general setup

Not configured yet? Start with the RunAPI setup guide for Hermes Agent.

Hermes Agent setup guide →

DeepSeek model catalog

See DeepSeek V4 variants, pricing, and API docs.

DeepSeek models →

Try DeepSeek in Hermes Agent today.

Get a free RunAPI key, set the model to deepseek-v4-pro in Hermes Agent, and start reasoning at half the cost of direct DeepSeek access.