MiniMax M3 Thinking
NanoGPTOpen weights
MiniMax M3 Thinking by NanoGPT costs $0.23 per 1M input tokens and $0.96 per 1M output tokens, with a 512K-token context window.
Pricing
Input (per 1M tokens)
$0.23
Output (per 1M tokens)
$0.96
Cached input (per 1M)
$0.05
Specifications
- Provider
- NanoGPT
- Context window
- 512K tokens
- Parameters
- —
- Released
- Jun 2026
- Open weights
- Yes
- Frontier model
- No
Benchmarks
- LiveBench
- 70.0
Compare MiniMax M3 Thinking with…
MiniMax M3 Thinking vs Llama-4-Maverick-17B-128E-Instruct-FP8$0.97/1MMiniMax M3 Thinking vs DeepSeek V3.1$0.95/1MMiniMax M3 Thinking vs DeepSeek V3.1 Terminus$1.00/1MMiniMax M3 Thinking vs Qwen2.5 Coder 32B Instruct$1.00/1MMiniMax M3 Thinking vs Nemotron 3 Super 120B A12B$1.00/1MMiniMax M3 Thinking vs MiniMax M2$1.02/1M
FAQ
How much does MiniMax M3 Thinking cost?
MiniMax M3 Thinking is priced at $0.23 per 1M input tokens and $0.96 per 1M output tokens. Output tokens cost more than input.
What is MiniMax M3 Thinking's context window?
MiniMax M3 Thinking supports a context window of 512K tokens — the maximum prompt plus response length it can handle in a single request.
Is MiniMax M3 Thinking open weight?
Yes — MiniMax M3 Thinking has openly available weights.
Data as of 2026-10-30. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.