MiniMax M2 API Pricing
Open-weight · 1000K context · Available from 7 hosts. Cheapest: Novita at $0.24 input / $0.96 output per 1M tokens.
MiniMax M2 ($0.3/$1.2 per 1M tokens) is priced the same as Qwen 3 Coder ($0.3/$1.2) and priced the same as Llama 4 Maverick (Together) ($0.35/$1.15) among the 294 open-weight models tracked here. Its 1000K context window is well above the open-weight category's typical range.
MiniMax M2 price by host (7 providers)
| Host | Input /1M | Output /1M | In+Out |
|---|---|---|---|
| Novita | $0.24 | $0.96 | $1.2 |
| DeepInfra | $0.255 | $1.02 | $1.275 |
| Groq | $0.285 | $1.14 | $1.425 |
| MiniMax | $0.3 | $1.2 | $1.5 |
| Together | $0.3 | $1.2 | $1.5 |
| OpenRouter | $0.3 | $1.2 | $1.5 |
| Fireworks | $0.315 | $1.26 | $1.575 |
Prices per 1M tokens, USD. Snapshot 2026-07 — verify with the provider before relying on them.
MiniMax M2 cost calculator
Frequently asked
MiniMax M2 costs $0.24 per 1M input tokens and $0.96 per 1M output tokens at its cheapest host (Novita).
MiniMax M2 supports a context window of about 1000K tokens. Remember every token in the context is billed on each call.
Across 7 hosts, Novita is currently cheapest at $0.24/$0.96 per 1M tokens, versus Fireworks at $0.315/$1.26. Prices change often — use the comparison table above.