MiniMax: MiniMax M3.1 Flash
by MiniMaxMiniMax: MiniMax M3.1 Flash is a large language model from MiniMax. It costs $0.150 per million input tokens and $0.600 per million output tokens. Its context window is 1.0M tokens.
- Input / 1M tokens
- $0.150
- Output / 1M tokens
- $0.600
- Cached input / 1M
- $0.015
- Context window
- 1.0M
On repeated prefixes
tokens
Who serves it cheapest
11 hosts serve MiniMax M3.1 Flash. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| StreamLakeCheapestfp8 | $0.135 | $0.540 | 1M | - | 99.5% |
| SambaNova | $0.135 | $0.540 | 1.0M | - | 98.8% |
| GMICloudfp8 | $0.143 | $0.570 | 1.0M | - | 99.9% |
| Fireworks | $0.150 | $0.600 | 1.0M | - | 100.0% |
| InferenceNetfp4 | $0.150 | $0.600 | 1M | - | 98.0% |
| DigitalOcean | $0.150 | $0.600 | 1.0M | - | 100.0% |
| Novitafp16 | $0.150 | $0.600 | 1M | - | 99.3% |
| ModelRunfp4 | $0.150 | $0.600 | 1.0M | - | 99.8% |
| Parasailfp8 | $0.150 | $0.600 | 1.0M | - | 100.0% |
| Together | $0.150 | $0.600 | 1.0M | - | 99.6% |
| Minimax | $0.150 | $0.600 | 1.0M | - | 99.9% |
The spread between StreamLake and Minimax is 1.1× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 28.9
About MiniMax M3.1 Flash
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
Specifications
| Model ID | minimax/minimax-m3.1-flash |
|---|---|
| Provider | MiniMax |
| Context window | 1.0M tokens |
| Max output | 524K tokens |
| Input modalities | text, image, video |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - MiniMaxAI/MiniMax-M3.1-Flash |
| Released | October 19, 2026 |
Cheaper alternatives
Models that cost less than MiniMax M3.1 Flash while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does MiniMax: MiniMax M3.1 Flash cost?
$0.150 per million input tokens and $0.600 per million output tokens. Cached input reads cost $0.015 per million tokens.
What is the context window of MiniMax: MiniMax M3.1 Flash?
1.0M tokens, with up to 524K tokens of output per request.
Which provider serves MiniMax: MiniMax M3.1 Flash cheapest?
StreamLake at $0.135 per million input tokens - 1.1× cheaper than Minimax, the most expensive of the 11 hosts serving it.
Confirm against the source: MiniMax official pricing.