Model comparison
Kimi K2-Instruct-0905 vs Kimi K2
- Input
- $0.60 / 1M tokens
- Output
- $2.50 / 1M tokens
- Context
- 256K
- Released
- 2025-09-09
- Input
- $0.55 / 1M tokens
- Output
- $2.20 / 1M tokens
- Context
- 128K
- Released
- 2025-07-11
Kimi K2-Instruct-0905 scores higher on 1 of the 2 benchmarks both models report; Kimi K2 is cheaper on input tokens ($0.6 vs $0.6 per 1M, 1.1×); Kimi K2-Instruct-0905 has the larger context window (256K vs 128K).
Specs and pricing side by side
| Spec | Kimi K2-Instruct-0905 | Kimi K2 |
|---|---|---|
| Maker | Moonshot AI (Kimi) | Moonshot AI (Kimi)same |
| Released | 2025-09-09 | 2025-07-11 |
| Context window | 256K | 128K |
| Max output | ~33K tokens | 128K |
| Input price | $0.60 / 1M tokens | $0.55 / 1M tokens |
| Output price | $2.50 / 1M tokens | $2.20 / 1M tokens |
| Parameters | 1T total / 32B active (MoE) | 1T total / 32B active (MoE)same |
| License | Modified MIT License | Modified MIT Licensesame |
| Weights | Open weights | Open weightssame |
| Modalities | Text | Textsame |
| Knowledge cutoff | Not publicly disclosed | not published |
Benchmarks both models report
| Benchmark | Kimi K2-Instruct-0905 | Kimi K2 |
|---|---|---|
| SWE-bench Verified | 69.2% | 65.8% |
| LiveCodeBench v6 | 53.7% | 53.7% |
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 Kimi K2-Instruct-0905 if…
- You care about SWE-bench Verified (it scores higher on 1 shared benchmark).
- You need the longer context (256K vs 128K).
- Your use case is: autonomous coding agents that edit, build, and test across multi-file repositories.
Pick Kimi K2 if…
- Cost matters: input tokens cost 1.1× less ($0.6 vs $0.6 per 1M).
- Your use case is: agentic coding assistants and automated software-engineering workflows.
FAQ
Which is better, Kimi K2-Instruct-0905 or Kimi K2?
Kimi K2-Instruct-0905 scores higher on 1 of the 2 benchmarks both models report; Kimi K2 is cheaper on input tokens ($0.6 vs $0.6 per 1M, 1.1×); Kimi K2-Instruct-0905 has the larger context window (256K vs 128K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Kimi K2?
Kimi K2-Instruct-0905: $0.60 / 1M tokens input, $2.50 / 1M tokens output. Kimi K2: $0.55 / 1M tokens input, $2.20 / 1M tokens output (list API prices as published by each maker).
What are the context windows of Kimi K2-Instruct-0905 and Kimi K2?
Kimi K2-Instruct-0905 offers 256K with up to ~33K tokens output; Kimi K2 offers 128K with up to 128K output.
Is Kimi K2-Instruct-0905 newer than Kimi K2?
Kimi K2-Instruct-0905 was released 2025-09-09; Kimi K2 was released 2025-07-11.