MiniMax / minimax/minimax-m3.1-flash-preview
MiniMax M3.1 Flash Preview - access through LLMTR
MiniMax M3.1 Flash Preview is MiniMax's closed-beta model for coding and agent workflows; it is not hosted in Turkey, and its behaviour may change during the beta. It provides a 1,000,000-token context, returns at most 524,288 tokens per response and accepts text and images. Tool calling and JSON object mode work; reasoning depth is set with reasoning_effort from low to max. It reasons before every answer and the reasoning counts toward the output limit, so do not set max_tokens low. The model is free and is not charged to your balance, but using it requires an account that has been topped up at least once (minimum $5). The free period ends on 6 October 2026 at 23:59 (TRT); after that the metered minimax/minimax-m3 is available.
Technical specifications
| Canonical ID | minimax/minimax-m3.1-flash-preview |
|---|---|
| Provider | MiniMax |
| Context window | 1,000,000 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | Not available |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | Not available |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | Not available |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"minimax/minimax-m3.1-flash-preview","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- Using MiniMax M3.1 Flash Preview with Claude Code and coding agents - For Claude Code, ANTHROPIC_BASE_URL=https://llmtr.com and ANTHROPIC_MODEL=minimax/minimax-m3.1-flash-preview:low are enough. In OpenAI-compatible agents the base URL is https://llmtr.com/v1.
- Tool calling with MiniMax M3.1 Flash Preview: an agent loop with the OpenAI SDK - Define tools in the tools field; when finish_reason is tool_calls, run the tool and send the result back with role tool, and repeat until stop. The loop runs on /v1/chat/completions.
- MiniMax M3.1 Flash Preview on the LLMTR API: free access, limits and first request - Send an OpenAI-compatible Chat Completions request with minimax/minimax-m3.1-flash-preview. The model is free and is not charged to your balance; using it requires an account that has been topped up at least once.
Related models
- MiniMax M3 minimax/minimax-m3
- MiniMax M2.7 minimax/minimax-m2.7
- MiniMax M2.7 Highspeed minimax/minimax-m2.7-highspeed
- MiniMax M2.5 minimax/minimax-m2.5
- MiniMax M2.5 Highspeed minimax/minimax-m2.5-highspeed
- MiniMax H3 minimax/minimax-h3
- MiniMax H3 Max minimax/minimax-h3-max
- Gemma 4 llmtr/gemma-4