Does Hermes Agent support Mistral?

Yes. Hermes reaches La Plateforme through its custom OpenAI-compatible provider (base URL https://api.mistral.ai/v1), and also supports Mistral models via OpenRouter and self-hosted Ollama / vLLM endpoints. MISTRAL_API_KEY on its own is used only for Voxtral speech-to-text and text-to-speech. On a paid OpenClaw Launch plan, pick a Mistral model under All OpenRouter models to use your included credits, or add your Mistral key as a Custom API Provider on the API Keys page.

Which Mistral model should I use with Hermes?

Mistral Medium 3 is the recommended default. Use Mistral Large 2 for complex reasoning, Codestral for coding workflows, and open-weight Mixtral for self-host with EU data residency.

Can I self-host Mistral with Hermes?

Yes. Mistral 7B, Mixtral 8x7B, Mixtral 8x22B, and Codestral are Apache-2.0 licensed. Run them via Ollama or vLLM and point Hermes at the local endpoint.

← Home

Guide

Hermes Agent + Mistral: Use Mistral AI's Open and Hosted Models

Mistral — the Paris-based AI lab's model family — pairs frontier quality with a strong open-source story. Mistral Large 2 handles deep reasoning, Mistral Medium 3 is the balanced workhorse, and Codestral leads on coding benchmarks for its size class.

Running your bot on OpenClaw Launch? The steps below use localhost, which is correct when the agent and the model server run on the same machine. A hosted bot runs in the cloud, so it cannot reach localhost or a home LAN address — those are refused when you save them. Give the model server a publicly reachable address instead (your own domain, a port forward, or a tunnel), save it under API keys ending in /v1. The endpoint then appears in the model picker as a custom entry — pick the model your server reports, or type its exact id if the list comes back empty, and set it as the default.

What Is Mistral?

Mistral AI is a European AI lab known for shipping strong open-weight models alongside hosted commercial offerings. Mistral pioneered mixture-of-experts architectures with Mixtral and has consistently delivered top-tier multilingual performance — particularly strong on French, German, Spanish, and Italian.

Hermes Agent reaches Mistral through three paths: La Plateforme (Mistral's hosted API), OpenRouter for unified access, or self-hosted for the open-weight variants (Mistral 7B, Mixtral 8x7B/8x22B, Codestral Mamba).

Mistral Model Lineup for Hermes

Model	Best For	Context	Cost (Input)
Mistral Large 2	Frontier reasoning, complex tool use	128K tokens	~$2/M tokens
Mistral Medium 3	Everyday agent default — balanced	128K tokens	~$0.40/M tokens
Mistral Small 3	Fast chat, high-volume bots	128K tokens	~$0.20/M tokens
Codestral	Code generation, refactoring, FIM	32K tokens	~$0.30/M tokens
Mixtral 8x22B (open)	Self-hosted MoE, strong multilingual	64K tokens	Self-host cost only

Option 1: Hermes Agent on OpenClaw Launch (Easiest)

Mistral is not in the curated model list, but a paid plan reaches it two ways. Use your included AI credits by picking a Mistral model under All OpenRouter models in the model dropdown, or bring your own La Plateforme key as below. Either way there is no server, Docker, or config file to manage. The 30-minute free trial runs on the free trial models only.

Go to openclawlaunch.com/hermes-hosting and deploy a Hermes agent.
To use your own key instead of credits, create one at console.mistral.ai/api-keys.
On the API Keys page, add a Custom API Provider with base URL https://api.mistral.ai/v1 and your key. OpenClaw Launch reads the model list from your Mistral account.
Pick Mistral Medium 3 (or Large 2 / Codestral) as your bot's model, then connect Telegram, Discord, WhatsApp, or another channel.

Option 2: Mistral La Plateforme API Direct (Self-Hosted)

# Hermes has no dedicated Mistral provider, but La Plateforme is
# OpenAI-compatible, so the custom provider talks to it directly.
# A custom endpoint authenticates with OPENAI_API_KEY.
export OPENAI_API_KEY=$MISTRAL_API_KEY

# Pick the provider and default model (interactive wizard)
hermes model

# config.yaml equivalent:
# model:
#   provider: custom
#   default: mistral-medium-3
#   base_url: https://api.mistral.ai/v1
#   api_mode: chat_completions

Generate an API key at console.mistral.ai/api-keys. Billing is usage-based with EU data residency available.

Option 3: Mistral via OpenRouter (Self-Hosted)

export OPENROUTER_API_KEY=sk-or-...
# Pick the provider and default model (interactive wizard)
hermes model

Option 4: Self-Hosted Mistral via Ollama or vLLM

Mistral 7B, Mixtral 8x7B, Mixtral 8x22B, and Codestral are open-weight under Apache 2.0. Run them locally for full data privacy.

# Ollama path (easiest)
ollama pull mixtral:8x22b
export OLLAMA_HOST=http://127.0.0.1:11434
# Pick the provider and default model (interactive wizard)
hermes model

# vLLM path (production)
vllm serve mistralai/Mixtral-8x22B-Instruct-v0.1 --port 8000
export OPENAI_API_BASE=http://127.0.0.1:8000/v1
# Pick the provider and default model (interactive wizard)
hermes model

When to Choose Each Mistral Model

Choose Mistral Medium 3 as your default. It hits roughly Claude Sonnet quality on tool use and reasoning at a fifth of the cost — the sweet spot for everyday Hermes deployments.

Choose Mistral Large 2 for complex multi-step agent tasks where you'd otherwise use Claude Opus or GPT-5.6 Sol. Strongest on European languages.

Choose Codestral for coding agents: strong fill-in-the-middle, 80+ programming languages, and dedicated FIM tokens that pair well with skill-based workflows.

Choose open-weight Mixtral when you need EU data residency or fully air-gapped deployment — the Apache-2.0 license permits any use.

Switching Models at Runtime

/model mistralai/mistral-medium-3
/model mistralai/mistral-large-2
/model mistralai/codestral

What's Next?

Hermes Agent + Llama — Another open-weight option
Hermes Agent + Claude — Anthropic Claude with Hermes
Hermes Agent + vLLM — Production self-host for Mistral
Hermes Agent + OpenRouter — One key for 200+ models