MiniMax API pricing
Every MiniMax model we track, per 1M tokens, from the official pricing page.
MiniMax API prices run from $0.15 in and $0.60 out per 1M tokens (MiniMax-M3.1 Flash) up to $0.30 in and $1.20 out (MiniMax-M3). Its cheapest model is number 13 of 77 on our full list. Checked Oct 29, 2026 against the official pricing page.
MiniMax's models: 2 are priced here, from $0.15 in and $0.60 out per 1M tokens (MiniMax-M3.1 Flash) to $0.30 in and $1.20 out (MiniMax-M3). Each model name below opens its own page with workload costs, LMArena ranks and cheaper alternatives.
| Model | Input | Cached | Output | Context |
|---|---|---|---|---|
| MiniMax-M3.1 Flashminimax-m3.1-flash | $0.15 | $0.015 | $0.60 | n/a |
| MiniMax-M3minimax-m3Prompts up to 512K tokens. Longer prompts cost $0.60 in, $2.40 out. MiniMax lists these as permanent 50% off its $0.60 in, $2.40 out list price. | $0.30 | $0.06 | $1.20 | n/a |
Which MiniMax model should you pick?
- Cheapest: MiniMax-M3.1 Flash at $0.15 in and $0.60 out, number 13 of 77 on our full price list.
- Best on LMArena: MiniMax-M3.1 Flash, #26 of 50 priced models on Code Arena, at $0.15 in and $0.60 out.
- Flagship: MiniMax-M3 at $0.30 in and $1.20 out.
How it compares
Cheapest models from other providers, blended per 1M tokens: Qwen3.7 Flash (Qwen) $0.06 · Step 3.5 Flash (StepFun) $0.15 · Qwen3.5 Flash (Qwen) $0.17. See the full API price table, the best model for each task or the plan vs API calculator.
Looking for the lowest price per token? See the cheapest LLM API ranking.
Head-to-head comparisons
FAQ
How much does the MiniMax API cost?
From $0.15 input and $0.60 output per 1M tokens for MiniMax-M3.1 Flash, up to $0.30 and $1.20 for MiniMax-M3.
What is the cheapest MiniMax model?
MiniMax-M3.1 Flash, with a blended price of $0.2625 per 1M tokens (3 parts input to 1 part output).
Is a subscription cheaper than the MiniMax API?
It depends on how much you use it. Try our plan vs API calculator with your own usage.
Which MiniMax model is the best?
By LMArena rank among the models we price, MiniMax-M3.1 Flash ranks highest at #26 on Code Arena.
Does the MiniMax API have cheaper cached input?
Yes, for 2 of 2 models: cached input is listed at $0.015 to $0.06 per 1M tokens.
How does MiniMax compare with other models?
We have head-to-head pages for GLM-5.3 vs MiniMax-M3, MiniMax-M3 vs DeepSeek V4.1 Flash, MiniMax-M3 vs Claude Sonnet 5.5.
Other providers: OpenAI · Anthropic · Google · Meta · DeepSeek · Qwen · Mistral · xAI · Kimi · GLM (Z.ai) · ByteDance Seed · Tencent Hunyuan · Baidu ERNIE · StepFun · Xiaomi MiMo