MiniMax M3.1 Flash
New$0.15
$0.60
- Positioning
- Economy. The vendor doesn't give one, so it's placed by price among text models.
- Price
- Level 1 of 4 among text models ($ is the cheapest), by output price per 1M tokens: under $1.
- Vendor-stated speed
- Not shown: the vendor doesn't compare this model's speed.
Three separate signals, not a quality score.
The lighter M3 — built for everyday coding and agent loops. MiniMax M3.1 Flash is a text model on ATP Token, billed per 1M input and output tokens, with a lower cached-input rate.
Pricing
The lighter, lower-priced member of the M3 line, aimed at everyday coding and agent loops. Passthrough of the model's official list price — no ATP markup.
Cost per 1,000 typical requests
| Workload | USD / 1,000 |
|---|---|
| Short chat turn800 / 400 | $0.36 |
| RAG answer4,000 / 500 | $0.9 |
| Agent step with tools20,000 / 1,500 | $3.90 |
Same controls on every model: project keys, per-project model access, credit budgets, and a log of every request.Set up your organization
Cost estimator
- Input$1.50
- Output$1.20
$2.70 USD / month · 270 credits / month
Quickstart
from openai import OpenAI
client = OpenAI(
base_url="https://api.atptoken.ai/v1",
api_key="atp-•••"
)
r = client.chat.completions.create(
model="minimax-m3-1-flash",
messages=[{"role":"user","content":"hi"}],
)Compare with similar models
- GLM-5.3 FlashZ.aiPositioning: Economy. Price level 1 of 4 among text models.$0.15 / $0.50In / out · per 1M tokens
- GPT-6 LunaOpenAIPositioning: Economy. Price level 1 of 4 among text models.$0.10 / $0.50In / out · per 1M tokens
- Qwen3.8 FlashQwen (Alibaba)Positioning: Economy. Price level 1 of 4 among text models.$0.15 / $0.47In / out · per 1M tokens
FAQ
- Can MiniMax M3.1 Flash use tools, read images, or think before answering?
- MiniMax M3.1 Flash supports tool calling, vision input and extended thinking, but not audio.
- Is cached input cheaper on MiniMax M3.1 Flash?
- You pay per 1M input tokens and per 1M output tokens. Cached input costs 10% of the normal input price. You only pay when a request succeeds. $1 = 100 credits. See pricing
- How do I call MiniMax M3.1 Flash on ATP?
- Create a project API key and point any OpenAI-compatible SDK at https://api.atptoken.ai/v1. Set model to "minimax-m3-1-flash" (the API id, not the display name). Make sure the model is turned on for your project.
Start with $5. Credits never expire.
Create a project key, turn this model on, and pay only for what you use.