Anthropic · Text

Hermes Agent x Claude

Claude is Anthropic's LLM family, spanning Opus (frontier), Sonnet (balanced), and Haiku (fast). Through RunAPI, all Claude variants share the same API shape and per-token billing.

13 variants from $0.60 / 1M tokens Commercial OK
Get API Key View Hermes Agent Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use claude-fable-5 when it matches the task: Mythos-class 1M context; state-of-the-art coding, reasoning, and vision.

You have access to RunAPI chat models for Claude.

Available Claude models:
- claude-fable-5: Mythos-class 1M context; state-of-the-art coding, reasoning, and vision
  chat endpoints: /v1/messages
- claude-fable-5-1: 1M context; successor to Fable 5
  chat endpoints: /v1/messages
- claude-haiku-4-5-20251001: Haiku 4.5 for reproducible outputs
  chat endpoints: /v1/messages
- claude-opus-4-1-20250805: claude-opus-4-1-20250805
  chat endpoints: /v1/messages
- claude-opus-4-5-20251101: claude-opus-4-5-20251101
  chat endpoints: /v1/messages
- claude-opus-4-6: 1M token context; frontier reasoning
  chat endpoints: /v1/messages
- claude-opus-4-7: 1M context; enhanced coding and tool use over 4.6
  chat endpoints: /v1/messages
- claude-opus-4-8: 1M context; strongest judgment and long-workflow reliability
  chat endpoints: /v1/messages
- claude-opus-5: 1M context; frontier reasoning and long-workflow reliability
  chat endpoints: /v1/messages
- claude-opus-5-5: 1M context; long-running agentic coding and knowledge work
  chat endpoints: /v1/messages
- claude-sonnet-4-5-20250929: claude-sonnet-4-5-20250929
  chat endpoints: /v1/messages
- claude-sonnet-4-6: 1M context; matches Opus coding
  chat endpoints: /v1/messages
- claude-sonnet-5: 1M context; near-Opus coding and agentic skill at Sonnet cost
  chat endpoints: /v1/messages

Use the model ID and chat endpoint that match the user's request.
Example request: Review this pull request for security vulnerabilities, performance issues, and suggest concrete improvements.
Verify the active model with: hermes model;hermes doctor

Public Versions and Endpoints

Model ID Endpoints Price Catalog
claude-fable-5
/v1/messages
$10.00 / 1M tokens Model detail
claude-fable-5-1
/v1/messages
$10.00 / 1M tokens Model detail
claude-haiku-4-5-20251001
/v1/messages
$0.60 / 1M tokens Model detail
claude-opus-4-1-20250805
/v1/messages
$9.00 / 1M tokens Model detail
claude-opus-4-5-20251101
/v1/messages
$3.00 / 1M tokens Model detail
claude-opus-4-6
/v1/messages
$3.00 / 1M tokens Model detail
claude-opus-4-7
/v1/messages
$3.00 / 1M tokens Model detail
claude-opus-4-8
/v1/messages
$3.00 / 1M tokens Model detail
claude-opus-5
/v1/messages
$3.00 / 1M tokens Model detail
claude-opus-5-5
/v1/messages
$4.00 / 1M tokens Model detail
claude-sonnet-4-5-20250929
/v1/messages
$1.80 / 1M tokens Model detail
claude-sonnet-4-6
/v1/messages
$1.80 / 1M tokens Model detail
claude-sonnet-5
/v1/messages
$1.36 / 1M tokens Model detail

Verify

Poll until the task reaches a terminal status

Select <model-id> to generate verification commands.

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.
How it works

Get Started in 3 Steps

  1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. Configure RunAPI

    Add the provider configuration for this agent.

  3. Verify the result

    Run the agent status and model-selection commands shown below.

What to Build with Hermes Agent + Claude

  • AI agents with tool use

    Use Claude's function calling in Hermes Agent to build multi-step workflows that read files, query data, and take actions.

  • Code generation and review

    Route coding tasks through Claude in Hermes Agent, using a larger version for architecture decisions and a faster one for everyday reviews and tests.

  • Content generation with prompt caching

    Generate documentation, reports, or marketing copy at scale, using prompt caching when the system prompt and context repeat across requests.

Why Use Claude Through RunAPI + Hermes Agent

  • 13 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Direct responses

    Synchronous calls return the result in the same response, so your agent can use it immediately without task polling.

Hermes Agent + Claude Questions

Can I call Claude from Hermes Agent through RunAPI?

Yes. Configure RunAPI as a provider in Hermes Agent with the settings shown on this page and pick a Claude version from the versions list. The same RunAPI API key works for every model.

Does switching Claude versions require reconfiguring Hermes Agent?

No. Change only the model in your Hermes config or with the model command during a session. The provider and API key stay the same.

How does prompt caching reduce Claude costs in Hermes Agent?

Mark the system prompt or large context blocks for caching. Later requests that share the cached prefix pay a lower input rate, which helps agent loops where tools and instructions repeat every turn.

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

Yes. This Model Line supports a client-facing LLM protocol.

Start using Claude with Hermes Agent

Get API Key Read Quickstart

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us