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,...
Context
1Mtokens
About 1,498 pages of text at once
Max output
512Ktokens
About 731 pages in one answer
Intelligence
18.7/ 100
Above 26% of the catalogue
Output speed
87tokens/s
A 500-word answer in about 8 s
From public market statistics for this model
First token
1.5s
Reasoning models start later
From public market statistics for this model
Health, 30 days
88.71%
15 of 30 days without a fault
IranRouter’s measurements
Price & cost
Every rate in Rial. A request pays only for the tokens it actually uses.
| Input | 822,298 | IRR / 1M tokens |
|---|---|---|
| Output | 3,289,192 | IRR / 1M tokens |
| Reasoning tokensThe output rate | 3,289,192 | IRR / 1M tokens |
| Cache read | 164,460 | IRR / 1M tokens |
| Image input tokensThe input rate | 822,298 | IRR / 1M tokens |
With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.
What would this model cost you a month?
Monthly cost
133.21MIRR
4.44M IRR a day, 2,220 IRR each request
The same work on peer models
30 days at today’s rate.
Rial price over 90 days
It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.
Performance, 30 days
Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.
Daily health88.71%
Time to first token1.55 s
Output speed74 tokens/s
Place in the market
By usage across the global model market.
Daily rank
Share of the day’s tokens
Among its peers
Cost of one message against intelligence; this model is highlighted.
Cost of one message, IRR (log scale)
Capabilities
- Input
- TextImageVideo
- Output
- Text
Parameters it accepts
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pOther benchmarks
Design contests
- WebsitesElo: 1,256Win rate: 52%
- Code (overall)Elo: 1,245Win rate: 51%
- UI componentsElo: 1,241Win rate: 51%
- Data vizElo: 1,234Win rate: 51%
4 moreShow less
- Game devElo: 1,210Win rate: 46%
- 3DElo: 1,206Win rate: 50%
- ASCII artElo: 1,158Win rate: 46%
- SVGElo: 1,158Win rate: 45%
Standard tests
- GPQA DiamondScore: 90%Tasks: 2,376
- τ-bench Verified AirlineScore: 75%Tasks: 550
Start in a minute
The official OpenAI and Anthropic SDKs; only the address and the key change.
# pip install openai from openai import OpenAI client = OpenAI( base_url="https://iranrouter.com/v1", api_key="ir-...", ) r = client.chat.completions.create( model="minimax/minimax-m3", messages=[{"role": "user", "content": "Hello, introduce yourself"}], ) print(r.choices[0].message.content)
Peer models
Its family and models with a close score; the last column compares one message’s cost with this model.
| Model | Against this model | ||||
|---|---|---|---|---|---|
| MoonshotAI: Kimi K3Moonshot AI | 21,610 | 17.4 | 63 | 1M | 557% dearer |
| Qwen: Qwen3.8 27BQwen | 3,371 | 20.1 | 51 | 1M | 3% dearer |
| DeepSeek: DeepSeek V4 Pro 0813DeepSeek | 11,531 | 23.1 | 52 | 1M | 251% dearer |
| NVIDIA: Nemotron 3 UltraNVIDIA | 6,578 | 11.8 | 69 | 262K | 100% dearer |
| Google: Gemini 3.5 Flash LiteGoogle | 5,071 | 11.7 | 132 | 1M | 54% dearer |
Technical specs
- ID
minimax/minimax-m3- Maker
- Minimax
- Tokenizer
- Other
- Released
- May 31, 2026
- Added to IranRouter
- Aug 19, 2026
- Context
- 1,048,576 tokens
- Max output
- 512,000 tokens
- Weights
- MiniMaxAI/Minimax-M3
Default parameters
top_p=0.95temperature=1Scores by Artificial Analysis, Design Arena, as of Oct 31, 2026