MiniMax
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,...
Cost / 1M tokens
Low usage$0.15
input
$0.015
cached input
$0.60
output
Context Window
1M
Up to 524K max output
Architecture
428B total · 23B active MoE
text + image + video → text
Quickstart & API
minimax/minimax-m3.1-flashBest for & Strengths
Key Strengths
Recommended Workloads in ChatOSS
- Computer-use & SaaS automation
- Deep research & synthesis
- Multimodal agent workflows
Verified Evaluations
Benchmarks & Frontier Comparison
How MiniMax M3.1 Flash compares against leading open-weight and proprietary frontier models across independent agentic coding and reasoning suites.
| Benchmark (Metric) | MiniMax M3.1 Flash | DeepSeek V4.1 Flash | GLM 5.3 | Kimi K3.1 Pro | Claude Opus 5.5 |
|---|---|---|---|---|---|
| Agentic & Software Engineering | |||||
| ChatOSS Agentic Coding Index (%) | 52.6% | 63.2% | 58.3% | 65% | 74.1% |
| SWE-Bench Verified (%) | — | 91.5% | 95.4% | 94.8% | 97% |
| DeepSWE v1.1 (Pass@1 %) | 66.5% | 77% | 69% | 73.5% | 74.2% |
| Vibe Code Bench v1.1 (%) | 73.94% | 87.7% | 78.1% | 88.4% | 90.3% |
| Terminal-Bench 4.0 (%) | 26% | 42.3% | 42% | 46.2% | 65.2% |
| Code Migration (%) | 44% | 45.6% | 44.2% | 52% | 66.7% |
| Intelligence & Token Economics | |||||
| Artificial Analysis Intelligence Index (0–100) | 29.1 | 39.5 | 44.8 | 55.1 | 57.6 |
| Input Price (/ 1M tokens) | $0.15 | $0.15 | $1.40 | $2.00 | $4.00 |
| Output Price (/ 1M tokens) | $0.60 | $0.60 | $4.40 | $10.00 | $20.00 |
ChatOSS Agentic Coding Index
ChatOSS Benchmark Audit · 4-benchmark composite mean
DeepSWE v1.1
DeepSWE / Official Audit · Mini-SWE-Agent
Vibe Code Bench v1.1
Vals.ai · OpenHands
Terminal-Bench 4.0
Vals.ai / Artificial Analysis · Terminus 2
Code Migration
Vals.ai · Vals evaluation harness
AutomationBench
Artificial Analysis v4.3
Artificial Analysis Intelligence Index
Artificial Analysis
Humanity's Last Exam (Pass@1)
Artificial Analysis / Audit
Active Provider Endpoints (11)
Upstream inference providers serving MiniMax M3.1 Flash, with per-provider pricing, context limits, quantization, and 24-hour uptime.
| Provider | Input / 1M | Output / 1M | Cache Read / 1M | Context | Max Output | Quantization | Uptime (24h) |
|---|---|---|---|---|---|---|---|
GMICloudcache gmicloud/fp8 | $0.113 | $0.45 | $0.011 | 1M | 944K | fp8 | 99.8% |
StreamLakecache streamlake/fp8 | $0.135 | $0.54 | $0.013 | 1M | 512K | fp8 | 99.9% |
Fireworkscache fireworks | $0.15 | $0.60 | $0.015 | 1M | 944K | — | 93.5% |
InferenceNetcache inference-net/fp4 | $0.15 | $0.60 | $0.015 | 1M | 524K | fp4 | 100.0% |
DigitalOceancache digitalocean | $0.15 | $0.60 | $0.015 | 1M | 944K | — | 100.0% |
Nebiuscache nebius/fp4 | $0.15 | $0.60 | $0.015 | 1M | 944K | fp4 | 100.0% |
SambaNovacache sambanova | $0.15 | $0.60 | $0.015 | 1M | 944K | — | 100.0% |
Parasailcache parasail/fp8 | $0.15 | $0.60 | $0.015 | 1M | 524K | fp8 | 100.0% |
InferenceNetcache inference-net/fp4/us | $0.15 | $0.60 | $0.015 | 1M | 524K | fp4 | 99.6% |
Togethercache together | $0.15 | $0.60 | $0.015 | 1M | 944K | — | 99.9% |
Minimaxcache minimax | $0.15 | $0.60 | $0.015 | 1M | 524K | — | 100.0% |
Supported API Parameters
Parameters accepted by this model when called through ChatOSS or OpenRouter.
Deep-Dive Benchmarks & Teardowns
Independent benchmark analysis and real-world agent billing teardowns featuring MiniMax M3.1 Flash.
2026-10-27 · 10 min read
MiniMax M3.1 Flash vs. DeepSeek V4.1 Flash 1017: cheaper tokens, higher bill
Both list at $0.15/$0.60 per million tokens, and MiniMax wins the business-workflow benchmarks. But on vals.ai's Vibe Code Bench v1.1, DeepSeek's October 17 checkpoint scores 87.73% at $0.58 per test while M3.1 Flash scores 73.94% at $1.15 — because the cheaper token burns 66.86M of them per task. Here is the independent evidence and the cache-aware math.
2026-10-29 · 11 min read
MiniMax M3.1 Flash may be the best open-source orchestrator agent right now
AutomationBench is the closest public test of orchestration, and MiniMax M3.1 Flash wins it on both the independent run (73% vs 67%) and the vendors' table (62.8 vs 60.5). It also leads HLE in Artificial Analysis's run, 48% to 43% — but DeepSeek V4.1 Flash 1017 still owns coding, cache-heavy bills and the MIT licence. The honest case, including the numbers that cut against it.
Compare Similar Models
Browse all models →MiniMax
MiniMax M3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
MiniMax
MiniMax M2.7
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
MiniMax
MiniMax M2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
Anthropic
Claude Opus 5.5
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
Moonshot AI
Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...
Anthropic
Claude Fable 5.1
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...