MiniMax M3.1 Flash
MiniMaxReleased Oct 19, 2026minimax-m3.1-flash
- Reasoning
- yes, with effort levels
- Context
- 1M tokens
- Max output
- 524K tokens
- Input
- text, image, video
- API features
- tools, structured outputs, JSON mode, seed, logprobs
- MiniMax's API
- yes, as MiniMax-M3.1-Flash
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from MiniMax
Speed by provider
Output speed of MiniMax M3.1 Flash at each host, fastest first
- Together AI228 tok/s0.57 s to first token
- Parasail207 tok/s0.98 s to first token
- InferenceNet29 tok/s1.55 s to first token
Speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · a snapshot of real traffic before the daily read, not a daily average · bars from zero.
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| InferenceNet | $0.10 | $0.50 | $0.005 | 29 | 1.55 s | 100% | Oct 23 |
| Minimax | $0.15 | $0.60 | $0.015 | — | — | — | Oct 20 |
| Parasail | $0.15 | $0.60 | $0.015 | 207 | 0.98 s | 100% | Oct 23 |
| Together AI | $0.15 | $0.60 | $0.015 | 228 | 0.57 s | 100% | Oct 23 |
4 of 4 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| InferenceNet | fp4 | 1M | 512K | yes | yes | yes |
| Minimax | — | 1M | 512K | — | — | — |
| Parasail | fp8 | 1M | 512K | yes | yes | yes |
| Together AI | — | 1M | — | yes | yes | yes |
As served by each host and declared to OpenRouter; not verified by us · weights: the precision the host declares
MiniMax M3.1 Flash spec sheet, field by field, with sources
MiniMax M3.1 Flash spec sheetmaker-declared
What MiniMax declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 1,000,000 tokensmaker's docs · read 2026-10-20
- Parameters
- to verify
- Active experts
- to verify
- Weight precision
- to verify
- License
- to verifyScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker
- Modalities
- text · image · videomaker's docs · read 2026-10-20
- Max output (official)
- 524,288 tokensmaker's docs · read 2026-10-20
- Release date
- October 19, 2026
- Maker lifecycle status
- General availability
www.minimax.io · maker's documentation · read 2026-10-20 · 5 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| InferenceNet | $0.35 | $1.05 | $0.90 |
| Minimax | $0.45 | $1.50 | $1.20 |
| Parasail | $0.45 | $1.50 | $1.20 |
| Together AI | $0.45 | $1.50 | $1.20 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other MiniMax models · all its models, hosts and history ›
- MiniMax-M312 providers · from $1.19
- MiniMax M2.59 providers · from $1.22
- MiniMax M2.77 providers · from $1.05
- MiniMax M23 providers · from $1.27
- MiniMax M12 providers · from $2.60
- MiniMax M2.12 providers · from $1.50