MiniMax-M3.1-Flash / Chat
Next-gen efficiency-focused multimodal model (428B MoE) for agentic workflows, coding, and computer use . Features a 1M-token context window and tunable thinking depth (low–max) . Scores 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, and 82% on CyberGym, while delivering 200+ TPS output speed at 70% lower agent-task cost than its predecessor
Playground Chat
Start a conversation with the AI model. You can ask anything.
AI-generated responses may vary in accuracy.
MiniMax M3.1 FlashAlways-On Thinking Chat with 1,000,000 Token Context Window
MiniMax-M3.1-Flash is MiniMax’s high-speed reasoning model featuring always-on thinking, 5-level reasoning_effort depth control, native multimodal audio/video/image comprehension, and an ultra-long 1,000,000 token context window.
At a Glance
M3.1 Flash Reasoning & Multimodal Stack
Deliberate reasoning depth combined with massive context and video intelligence.
Always-On Thinking & Effort Ladder
MiniMax-M3.1-Flash reasons on every prompt with no disable switch. Dial depth from low to max via reasoning_effort (default max) to match task complexity.
1,000,000 Token Context Window
A 1M combined token context window handles full repositories, video transcripts, research papers, and technical books in a single pass.
Native Multimodal Video & Image Input
Send text, images, or MP4/MOV/AVI/MKV video files with custom fps (0.2–5, default 1) and resolution detail presets (low/default/high).
Production Sampling & SSE Streaming
stream defaults to true for immediate UI paint, paired with balanced temperature (default 0.7), top-p (default 0.95), and custom stop sequences.
How It Works
High-depth reasoning in four steps.
Set Reasoning Effort
Pick low, medium, high, xhigh, or max (default max).
Attach Multimodal Media
Pass text, image URLs, or video files with target fps.
Stream Thought & Tokens
Receive progressive SSE stream as the model reasons.
Bound with Sampling
Tune temperature (0.7) and top-p (0.95) for brand tone.
M3.1 Flash Domains
Where deep reasoning meets massive context and video.
Codebase Architecture
Ingest multi-file repositories with 1M tokens.
Video Intelligence
Analyze recordings and tutorials frame by frame.
Complex Math & Proofs
Deep reasoning at max effort for verifiable proofs.
Document & Legal Synthesis
Synthesize contract suites and research papers in one prompt.
Prompt Tips
Get peak performance from M3.1 Flash.
Use low or medium for quick summaries and conversational tasks; keep max for complex architecture and multi-step proofs.
fps=1 is optimal for most lectures and tutorials; increase to 2–3 fps for high-speed action scenes.
Place large documents and files at the start of messages before prompt instructions.
MiniMax M3.1 Flash Quickstart
Always-on reasoning with 1M context.
curl -X POST "https://api.powertokens.ai/v1/chat/completions" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "MiniMax-M3.1-Flash",
"messages": [
{"role": "user", "content": "Analyze the architectural trade-offs in this distributed system design."}
],
"stream": true,
"temperature": 0.7
}'Technical Specifications
Confirmed parameters and runtime execution protocols.
Pricing Details
The actual billing for this model is dynamically calculated based on the specific parameters passed in your API request. Below are the specific combinations and their corresponding pricing:
| Modality | Input Credits | Output Credits | Input Price | Output Price | Implicit Cache Hit | Explicit Cache Hit | Cache Creation |
|---|---|---|---|---|---|---|---|
| Standard | 150/ 1M Tokens | 600/ 1M Tokens | $0.150 | $0.600 | $0.015 15/ 1M Tokens | $0.015 15/ 1M Tokens | -- |
Models from the Same Channel
Explore complementary models and alternative versions from the same provider channel.
MiniMax M3
MiniMax-M3
Flagship multimodal foundation model supporting text, image, and video inputs with text output. Features a 1M-token context window via MiniMax Sparse Attention (MSA), cutting per-token compute to ~1/20 of previous gen at full context. Excels at long-horizon agentic work, coding, and tool use. Native multimodal training from step zero ensures deep semantic alignment. Scores 59.0% on SWE-Bench Pro and 83.5 on BrowseComp, surpassing Opus 4.7
MiniMax M2.7
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 collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.
MiniMax M2.7 Highspeed
MiniMax-M2.7-highspeed
A high-speed variant of MiniMax’s flagship M2.7 LLM, delivering 100 TPS—~60% faster than standard M2.7—with identical top-tier quality. It features a 204,800-token context window, near-Opus-level SWE performance, and recursive self-improvement. Optimized for low-latency coding, office tasks, and agent workflows, it balances extreme speed, reliability, and cost-efficiency for high-throughput real-world applications。
MiniMax M2.5
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 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams
Recommended Related Models
Explore complementary video and multimodal models with your unified API key.
GLM-5.3
glm-5.3
Zhipu AI's flagship text model optimized for complex software engineering and long-horizon Agent tasks. Features a 1M-token context window with mandatory reasoning (3 levels: low/high/max). Coding capability improved 50% over GLM-5.2 on Z.ai Code Bench; scores SOTA on Terminal Bench 3.0. Excels in cybersecurity tasks (cyber vulnerability discovery)
GLM-5.3 Flash
glm-5.3-flash
Z.ai's native multimodal model (320B-A18B) with text, image, video, and file input. Features hybrid sparse + linear attention, reducing attention compute 3x and KV cache 4.4x vs. GLM-5.3. Scores 57 on Artificial Analysis Intelligence Index—matching Claude Opus 4.8—with 1M context and 128K max output. Excels in agentic coding, vision-based Computer Use, and CAD reproduction
Qwen3.8 Flash
qwen3.8-flash
Alibaba's cost-efficient multimodal reasoning model. Supports text, image, and video inputs with text output. Features a native 1M-token context window for long documents, codebases, and agentic workflows. Excels in coding assistance, desktop interaction, chart analysis, and long-video understanding. Compatible with OpenAI/Anthropic protocols for seamless integration
GLM-5.2
glm-5.2
Flagship text model purpose-built for long-horizon agentic workflows. Features a 1M context window supporting project-level engineering in a single session. Excels at autonomous coding: can complete development, testing, and multi-platform deployment from a single prompt. Top open-weight model per Artificial Analysis; #1 globally on Code Arena. MIT-licensed and Day-0 optimized for domestic AI chips
Frequently Asked Questions
Everything you need to know before integrating this model.
Start Building with MiniMax M3.1 Flash Today
Create an account in seconds to receive 100 free credits and start generating immediately. No credit card or upfront contract required.