Hermes Agent + DeepSeek
Power Hermes Agent with a flat-rate DeepSeek API.
Hermes Agent can connect to a custom OpenAI-compatible endpoint. Point it at Camel Stream to run file operations, terminal tools, retries, and long sessions without a per-token bill.
Why this setup
Keep the agent. Change the inference bill.
Built for long loops
Hermes can inspect files, use the terminal, retry work, and carry context across an agent session. Flat-rate inference makes those loops easier to budget.
No client rewrite
Hermes documents custom OpenAI-compatible endpoints, so the provider changes while the rest of the agent workflow stays familiar.
Transparent throughput
The founding plan runs one active generation at a time and queues extra requests instead of creating token overages.
Configuration
Connect Hermes Agent to Stream.
1. Create your Stream API key
Sign up for Stream, subscribe to the founding plan, and copy the API key from your Stream account.
2. Choose a custom endpoint
Run hermes model, choose Custom endpoint, set API mode to Chat Completions, and enter the Stream base URL, model ID, context length, and API key shown below.
3. Start a tool-using session
Open Hermes in a test repository and ask it to inspect files before making a small change. Confirm that text generation and tool calls both complete.
hermes model
# Choose: Custom endpoint
# Base URL: https://stream.camelai.com/v1
# API mode: Chat Completions
# Model: deepseek-v4-flash
# Context length: 262144
# API key: <your Stream API key>Troubleshooting
Check these details first.
Most connection issues come down to the endpoint, API mode, model ID, or key. Start with these checks.
Use https://stream.camelai.com/v1 exactly as shown, including /v1 but not /chat/completions.
Set API mode to Chat Completions. Other Hermes API modes will 404 against this endpoint.
Use deepseek-v4-flash as the model ID; display names from another provider will not resolve.
If Hermes was already running, restart it after changing the saved provider or API key.
Test the main model first, then verify any separately configured Hermes auxiliary models.
Frequently asked questions
Before you connect.
More coding-agent guides
Use Stream with another agent.
Give your coding agent room to work.
DeepSeek V4 Flash through an OpenAI-compatible API with unlimited token usage for one fixed monthly price.
Get your API key