MiniMax M3.1 Flash
The 3rd most-used model on the router over the last 7 days, with 7.7% of tokens.
- Launch
- Oct 19, 2026
- Context
- 1M tokens
- Modality
- text, image and video → text
- Reasoning
- yes
- License
- Open weights
- Input
- $0.15 / 1M
- Output
- $0.60 / 1M
Weekly token share
Share of the router's weekly volume, since the first week with volume
No full week with volume yet. The last-7-days share above comes from the daily window.
What this model is used for new
Tasks where the model ranks among the leaders, and its share of each
Plus 3 more tasks with a smaller share.
Ranks among the leaders in 15 of the 29 classified tasks. Its largest share is in research and reports, 19.2% of the task's tokens; in the heaviest task where it appears, workflow execution (23.4% of classified volume), it holds 9.2%.
Snapshot of the rolling 7-day window through Oct 23, 2026. Share: the model's tokens in the task over the task's total tokens. Weight: the task's share of classified volume.
Where to run it
Endpoints in the source's catalog, from cheapest to most expensive on input
| Provider | Input | Output | Context | Quantization | Zero retention |
|---|---|---|---|---|---|
| Relace | $0.09 | $0.50 | 1M | fp4 | yes |
| InferenceNet | $0.10 | $0.55 | 1M | fp4 | yes |
| InferenceNet | $0.10 | $0.55 | 1M | fp4 | yes |
| GMICloud | $0.143 | $0.57 | 1M | fp8 | no |
| DigitalOcean | $0.15 | $0.60 | 1M | not reported | yes |
| Novita | $0.15 | $0.60 | 1M | fp16 | yes |
| Nebius | $0.15 | $0.60 | 1M | fp4 | yes |
| Wafer | $0.15 | $0.60 | 1M | not reported | yes |
| ModelRun | $0.15 | $0.60 | 1M | fp4 | yes |
| Parasail | $0.15 | $0.60 | 1M | fp8 | yes |
| Together | $0.15 | $0.60 | 1M | not reported | yes |
| Minimax | $0.15 | $0.60 | 1M | not reported | no |
| SambaNova | $0.30 | $1.20 | 1M | not reported | yes |
13 endpoints across 12 providers, with input from $0.09 to $0.30 per 1M tokens. 11 offer zero data retention.
Prices in US dollars per million tokens, from the latest archived endpoint catalog.
Benchmarks
Artificial Analysis indexes and benchmarks run by the source, with cost per task
GPQA Diamond 86.7%
$0.035 per task, 198 tasks. 62nd of 169 evaluated. Median of evaluated models: 83.4%, $0.025 per task.
τ-bench verified, airline 70.7%
$0.017 per task, 50 tasks. 81st of 150 evaluated. Median of evaluated models: 71.3%, $0.065 per task.
Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Oct 24, 2026. The gray mark is the median of evaluated models.
Against the week's largest models
The five largest proprietary and five largest open-weights models over the last 7 days
| Model | Lab | 7-day share | Blended price | Context | Intelligence | Weeks in top 10 |
|---|---|---|---|---|---|---|
| Proprietary | ||||||
| Claude Opus 5.5Anthropic | Anthropic | 4.5% | $8.00 | 1M | 57.6 | 2 |
| GPT-6 LunaOpenAI | OpenAI | 3.8% | $0.20 | 1M | 38.1 | 4 |
| Muse Spark 1.3 ContributorMeta | Meta | 1.7% | $0.125 | 1M | — | 0 |
| jev-1.13Typesafe | Typesafe | 1.6% | — | — | — | 0 |
| Claude Haiku 5.5Anthropic | Anthropic | 1.5% | $0.20 | 1M | 43.4 | 0 |
| Open weights | ||||||
| DeepSeek V4.1 Flash 1017DeepSeek | DeepSeek | 14.9% | $0.263 | 1M | 39.5 | 0 |
| DeepSeek V4.1 FlashDeepSeek | DeepSeek | 11.5% | $0.265 | 1M | 24.7 | 6 |
| MiniMax M3.1 Flashthis pageMiniMax | MiniMax | 7.7% | $0.263 | 1M | 42.7 | 0 |
| GLM 5.3 FlashZ.ai (GLM) | Z.ai (GLM) | 6.6% | $0.237 | 1M | 41.8 | 8 |
| Hy4 previewTencent | Tencent | 4.9% | $1.25 | 1M | — | 7 |
Share over the last 7 days (Oct 17, 2026 to Oct 23, 2026). Blended price in US dollars per million tokens, weighted 75% input and 25% output. A dash means the number is not published, not zero.