MiniMax M3.1 Flash is MiniMax's multimodal model in the M3 family. The vendor reports improvements across multiple benchmarks compared with M3 (vendor claim, not independently measured). It is available via OpenRouter. The price listed here is the OpenRouter listed price, checked Nov 18, 2026: $0.15 per million input tokens and $0.60 per million output tokens. Data Source: OpenRouter listing. Data Confidence: Partial.
MiniMax M3.1 Flash supports a 1,048,576-token context window and a maximum output of 524,288 tokens — one of the largest output limits available. It supports vision input, function calling, and streaming. It is not classified as a reasoning model on this page.
Within the MiniMax M3 family, M3.1 Flash is the cost-efficient multimodal variant. MiniMax M3 ($0.80/$2.40 via MiniMax direct) is the flagship reasoning model in the family. M3.1 Flash's $0.15/$0.60 pricing makes it one of the most affordable multimodal options across all providers.
Data source: OpenRouter listing, checked Nov 18, 2026. Data Confidence: Partial — throughput, latency, and benchmark scores are not available for this model at this time. The benchmark improvement claim is from the vendor and has not been independently verified.
MiniMax M3.1 Flash is suited to high-volume multimodal workloads where cost efficiency is the primary constraint. Its 1M+ context window and 524K output limit make it well-suited for long-context applications, and its low price makes it accessible for large-scale deployments.
Input price vs 219 efficient models tracked. Avg: $0.321/1M.
| Model ID | minimax-m3-1-flash |
| Provider | MiniMax |
| Model Family | MiniMax M3 |
| Tier | Efficient |
| Context Window | 1,048,576 tokens (1.0M) |
| Max Output Tokens | 524,288 tokens |
| Input Price | $0.15 / 1M tokens |
| Output Price | $0.6 / 1M tokens |
| Cached Input Price | Not available |
| Throughput | — |
| Latency (P50) | — |
| Intelligence Score | — |
| LiveBench Score | — |
| Cost per Task (LiveBench) | — |
| Data Confidence | Partial |
| HLE Score | — |
| GPQA Diamond | — |
| SWE-bench Score | — |
| OSWorld Score | — |
| BrowseComp Score | — |
| Terminal-Bench Score | — |
| AutoBench Score | — |
| Parameters | — |
| Vision Support | Yes |
| Function Calling | Yes |
| Streaming | Yes |
| Reasoning Model | No |
| Open Weights | No |
| Data Source | Static (verified) |
| Last Updated | 2026-11-18 |
Self-hosting minimax-m3-1-flash? These GPUs are well-matched for this model's compute and memory requirements.