Skip to content
➜NextOS

Mistral
in NextOS.

Tool calling, reasoning effort, prompt caching, and Mistral-hosted web search / code interpreter via the Conversations API.

Use MistralGet an API key

01Supported models

Every model
this plugin lists.

  • mistral-large-2512

    Mistral Large 3 (most capable)

    256K contexttools

    Apache 2.0, 675B total / 41B active, multimodal. Alias mistral-large-latest.

  • mistral-medium-3-5

    Mistral Medium 3.5 (frontier, agentic)

    256K contexttools

    Supports reasoning effort - "high" is recommended for agentic and code use. Alias mistral-medium-latest.

  • mistral-small-2603

    Mistral Small 4 (fast, hybrid reasoning)

    256K contexttools

    Apache 2.0, 119B total / 6.5B active; unifies instruct, reasoning and coding. Alias mistral-small-latest.

  • ministral-14b-2512

    Ministral 3 14B

    256K contexttools

    No built-in tools - stays on Chat Completions.

  • ministral-8b-2512

    Ministral 3 8B

    256K contexttools

    No built-in tools - stays on Chat Completions.

  • ministral-3b-2512

    Ministral 3 3B (cheapest)

    256K contexttools

    No built-in tools - stays on Chat Completions.

  • zai-glm-5-2

    Z.ai GLM 5.2 (1M context)

    1M contexttools

    Third-party, hosted by Mistral (Public Preview). Max output 128k. No built-in tools.

  • codestral-2508

    Codestral (code, FIM)

    128K contexttools

    Also serves /v1/fim/completions, outside this plugin.

02Bring your own key, or hosted

How you
pay for it.

Mistral runs bring-your-own-key only: add your key in Settings > API keys, or send it per-request over the gateway.

  • Full tool calling - agents can use every app and MCP tool through this provider
  • No provider-hosted web search
  • No provider-hosted URL fetch

03Governance

The same controls
as every provider.

  • Restrict which providers and models a team may use at all - an allowed list on the org policy, enforced on every gateway call
  • Set a default model the whole workspace inherits, with per-agent pins for the job that needs a different one
  • Per-org and per-key budgets and rate limits, checked before a call reaches the provider
  • Guardrails (PII redaction, prompt-injection screening) applied to every request and response, regardless of provider
  • A full audit trail of governance and budget events, in the team's activity log

04Over the gateway

One endpoint,
OpenAI-compatible.

gateway — next.os
curl https://jonkum.in/api/v1/chat/completions \
  -H "Authorization: Bearer ngk_..." \
  -H "X-Provider-Key: your-mistral-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistral/mistral-large-2512","messages":[{"role":"user","content":"..."}]}'

Omit X-Provider-Key to run on the account's hosted allowance instead, where the plan supports it. See the gateway page for the full API.

05Every other provider

one plane · every provider · your key or ours

Run agents on Mistral.
Governed exactly like every other provider.

Set your defaultSee pricing