How much does MiniMax M3.1 Flash cost?

On the Respan gateway, MiniMax M3.1 Flash costs from $0.07 per 1M input tokens and $0.30 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 10 providers, it costs $0.13 per 1M input tokens and $0.54 per 1M output tokens.

Which providers serve MiniMax M3.1 Flash on Respan?

MiniMax M3.1 Flash is available through 10 providers: OpenRouter, MiniMax, EmpirioLabs, Fireworks, Inference.net, Nebius, and 4 more.

What is MiniMax M3.1 Flash's context window?

MiniMax M3.1 Flash accepts up to 1M tokens of context on its largest provider route.

How do I use MiniMax M3.1 Flash with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "minimax/MiniMax-M3.1-Flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Where does MiniMax M3.1 Flash rank on the Respan Index?

MiniMax M3.1 Flash scores 51.8 out of 100 on the Respan Index v1.1, ranking #31 of 161 models. By category: Coding 40.7, Agents 56.3, Reasoning 55.4, Knowledge & language 54.0 (estimated), and Human preference 55.5. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

How does MiniMax M3.1 Flash score on benchmarks?

MiniMax M3.1 Flash has 19 published benchmark scores, including CyberGym 82.2%, OSWorld V2 61.7%, and HLE (without tools) 43.4%. Each score links to where it was published; the data is collected by Respan.

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,...

Model card on Hugging Face

Input / output, fromSave up to 30%: $0.07 / $0.30 per 1M
Context: 1M tokens
Released: Oct 19, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "minimax/MiniMax-M3.1-Flash".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="minimax/MiniMax-M3.1-Flash",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "minimax/MiniMax-M3.1-Flash",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "minimax/MiniMax-M3.1-Flash",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

10 providers, cheapest first, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read
OpenRouter`openrouter/minimax/minimax-m3.1-flash`	1M	$0.07/M	$0.30/M	$0.0075/M
MiniMaxSave 30%`minimax/MiniMax-M3.1-Flash`	1M	$0.10/M	$0.42/M	$0.01/M
EmpirioLabs`empiriolabs/minimax-m3-1-flash`	1M	$0.11/M	$0.45/M	$0.01/M
Fireworks`fireworks_ai/minimax-m3p1-flash`	1M	$0.15/M	$0.60/M	$0.01/M
Inference.net`inference_net/minimax-m3.1-flash`	1M	$0.15/M	$0.60/M	$0.01/M
Nebius`nebius/MiniMaxAI/MiniMax-M3.1-Flash`	1M	$0.15/M	$0.60/M	$0.01/M
Novita`novita/minimax/minimax-m3.1-flash`	1M	$0.15/M	$0.60/M	$0.01/M
Parasail`parasail/MiniMaxAI/MiniMax-M3.1-Flash`	1M	$0.15/M	$0.60/M	$0.01/M
Relace`relace/minimax/minimax-m3.1-flash`	1M	$0.15/M	$0.60/M	$0.01/M
TogetherAI`together_ai/MiniMaxAI/MiniMax-M3.1-Flash`	1M	$0.15/M	$0.60/M	$0.01/M

Is a provider down? OpenRouter status, MiniMax status, Fireworks AI status, Together AI status

Pricing

Averaged across 10 providers, in USD per 1M tokens after gateway discounts.

Average input: $0.13 per 1M
Average output: $0.54 per 1M
Average cache read: $0.01 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.15/MFireworks, Inference.net, Nebius, Novita, Parasail, Relace, and TogetherAILowest$0.07/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

117tokens/sacross providers

Faster than 85% of the other 470 models on the gateway

Time to first token

Lower is better

1.7sacross providers

Faster than 55% of the other 85 models on the gateway

Response latency

Lower is better

3.7sacross providers

Faster than 37% of the other 495 models on the gateway

Benchmarks

The Respan Index plus 19 published scores from 4 sources, each linked to where it was published.

51.8/ 100

Respan Index#31 of 161

161 ranked models. The shaded band is this model's 95% interval, 35.4 to 69.6. Gemini 3.7 Flash and GPT-5.4 Pro fall inside it, so the gap is within the margin of error.

31MiniMax M3.1 Flash51.8
30Gemini 3.7 Flash52.0
32GPT-5.4 Pro51.3

Published scores

Benchmark	Score	Source	Published
CyberGymhuggingface.co	82.2%	huggingface.co	Oct 19, 2026
DeepSWE v1.1minimax.io	73.7%	minimax.io	Oct 19, 2026
NL2Repo-Benchhuggingface.co	61.2%	huggingface.co	Oct 19, 2026
Terminal Bench 4.0huggingface.co	38.1%	huggingface.co	Oct 19, 2026
Terminal-Bench 4.0Vals AI	25.3%	Vals AI	Oct 28, 2026
SWE Refactor Benchhuggingface.co	23%	huggingface.co	Oct 19, 2026

Benchmark	Score	Source	Published
OSWorld V2minimax.io	61.7%	minimax.io	Oct 19, 2026
Agents' Last Examminimax.io	29.6%	minimax.io	Oct 19, 2026

Benchmark	Score	Source	Published
HLE (without tools)huggingface.co	43.4%	huggingface.co	Oct 19, 2026

Benchmark	Score	Source	Published
BabyVision (with tools)huggingface.co	91%	huggingface.co	Oct 19, 2026
CharXiv RQhuggingface.co	82.5%	huggingface.co	Oct 19, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1583 Elo · #32 of 113	LMArena	Oct 28, 2026
LMArena AgentLMArena	-0.0396 · #40 of 59	LMArena	Oct 28, 2026

Benchmark	Score	Source	Published
SAGE 1.1Vals AI	85.3%	Vals AI	Oct 31, 2026
BankerToolBenchminimax.io	76.2%	minimax.io	Oct 19, 2026
Automation-Bench v1.0.6huggingface.co	62.8%	huggingface.co	Oct 19, 2026
LOCA-Bench 256Khuggingface.co	60.3%	huggingface.co	Oct 19, 2026
PostTrain Bench v1.1huggingface.co	39.3%	huggingface.co	Oct 19, 2026
GDP.pdf AAhuggingface.co	20.8%	huggingface.co	Oct 19, 2026