Model comparison
MiniMax M2 vs Kimi K2-Instruct-0905
- Input
- $0.30 / 1M tokens
- Output
- $1.20 / 1M tokens
- Context
- 204K
- Released
- 2025-10-27
- Input
- $0.60 / 1M tokens
- Output
- $2.50 / 1M tokens
- Context
- 256K
- Released
- 2025-09-09
MiniMax M2 scores higher on 3 of the 3 benchmarks both models report; MiniMax M2 is cheaper on input tokens ($0.3 vs $0.6 per 1M, 2×); Kimi K2-Instruct-0905 has the larger context window (256K vs 204K).
Specs and pricing side by side
| Spec | MiniMax M2 | Kimi K2-Instruct-0905 |
|---|---|---|
| Maker | MiniMax | Moonshot AI (Kimi) |
| Released | 2025-10-27 | 2025-09-09 |
| Context window | 204K | 256K |
| Max output | Not publicly disclosed | ~33K tokens |
| Input price | $0.30 / 1M tokens | $0.60 / 1M tokens |
| Output price | $1.20 / 1M tokens | $2.50 / 1M tokens |
| Parameters | 230B total / 10B active (MoE) | 1T total / 32B active (MoE) |
| License | MIT (modified) | Modified MIT License |
| Weights | Open weights | Open weightssame |
| Modalities | Text | Textsame |
| Knowledge cutoff | Not publicly disclosed | Not publicly disclosedsame |
Benchmarks both models report
| Benchmark | MiniMax M2 | Kimi K2-Instruct-0905 |
|---|---|---|
| SWE-bench Verified | 69.4% | 69.2% |
| Multi-SWE-Bench | 36.2% | 33.5% |
| Terminal-Bench | 46.3% | 44.5% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick MiniMax M2 if…
- You care about SWE-bench Verified, Multi-SWE-Bench, Terminal-Bench (it scores higher on 3 shared benchmarks).
- Cost matters: input tokens cost 2× less ($0.3 vs $0.6 per 1M).
- Your use case is: autonomous and semi-autonomous coding agents that do multi-file edits and run-fix loops.
Pick Kimi K2-Instruct-0905 if…
- You need the longer context (256K vs 204K).
- Your use case is: autonomous coding agents that edit, build, and test across multi-file repositories.
FAQ
Which is better, MiniMax M2 or Kimi K2-Instruct-0905?
MiniMax M2 scores higher on 3 of the 3 benchmarks both models report; MiniMax M2 is cheaper on input tokens ($0.3 vs $0.6 per 1M, 2×); Kimi K2-Instruct-0905 has the larger context window (256K vs 204K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is MiniMax M2?
MiniMax M2: $0.30 / 1M tokens input, $1.20 / 1M tokens output. Kimi K2-Instruct-0905: $0.60 / 1M tokens input, $2.50 / 1M tokens output (list API prices as published by each maker).
What are the context windows of MiniMax M2 and Kimi K2-Instruct-0905?
MiniMax M2 offers 204K with up to Not publicly disclosed output; Kimi K2-Instruct-0905 offers 256K with up to ~33K tokens output.
Is MiniMax M2 newer than Kimi K2-Instruct-0905?
MiniMax M2 was released 2025-10-27; Kimi K2-Instruct-0905 was released 2025-09-09.
Go deeper
- MiniMax M2: full specs, pricing and benchmarks
- Kimi K2-Instruct-0905: full specs, pricing and benchmarks
- minimax m2 1 vs minimax m2
- kimi k2 instruct 0905 vs kimi k2
- kimi k2 7 code vs kimi k2 instruct 0905
- glm 4 7 flash vs minimax m2
- glm 4 7 vs kimi k2 instruct 0905
- minimax m2 vs claude haiku 4 5
- All model comparisons