Mistral Large 3 API via TokenMix

Use Mistral Large 3 from Mistral as a chat model through the TokenMix AI API relay and multi-model gateway.

Open-weight general-purpose multimodal model with granular MoE architecture (41B active / 675B total). Released under Apache 2.0 with 262K context.

API access

  • Base URL: https://api.tokenmix.ai/v1
  • Model ID: mistral-large
  • OpenAI SDK compatible. Change the base URL and use your TokenMix API key.

Pricing

Input $0.47/M tokens, output $1.41/M tokens

Capabilities

Vision, Function calling, JSON mode, Streaming

Model specs

  • Context: 262K tokens
  • Max output: 8K tokens

Availability

2/2 available API endpoints are healthy right now.

Recent performance

TTFT 136ms, latency 906ms, throughput 1.1 tok/s.

Start using this model

Create an API key, top up from $1 when needed, and call this model through the TokenMix OpenAI-compatible endpoint.

Create API key · View pricing · Quickstart