gpt-oss-120b vs Kimi K2.6
Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.
OpenAI · Aug 2025
OpenAI's open-weights MoE reasoning model under Apache 2.0 — near o4-mini quality, runnable on a single 80GB GPU.
Moonshot AI · Apr 2026
Moonshot's multimodal flagship that ties GPT-5.5 on several coding evaluations at a fraction of the price, with open weights.
The verdict
These two models don't yet share verified results on the benchmarks we track, so judge them on specs, pricing and intended use. On price the gap is dramatic: gpt-oss-120b works out roughly 8.6x cheaper per blended million tokens. Kimi K2.6 also takes 262K of context versus 131K for gpt-oss-120b.
Specs & pricing
| gpt-oss-120b | Kimi K2.6 | |
|---|---|---|
| modhub Index | — | — |
| Input price / 1M | $0.1 | $0.95 |
| Output price / 1M | $0.5 | $4 |
| Context window | 131K | 262K |
| Max output | 131K | 262K |
| Open weights | yes (Apache 2.0) | yes (Modified MIT) |
| Reasoning model | yes | yes |
| Multimodal input | text | text, image |
| Knowledge cutoff | Jun 2024 | Feb 2026 |
| Released | Aug 2025 | Apr 2026 |
| Example monthly cost* | $1.75 | $15.50 |
* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.
Frequently asked questions
- Which is better, gpt-oss-120b or Kimi K2.6?
- These two models don't yet share verified results on the benchmarks we track, so judge them on specs, pricing and intended use. On price the gap is dramatic: gpt-oss-120b works out roughly 8.6x cheaper per blended million tokens. Kimi K2.6 also takes 262K of context versus 131K for gpt-oss-120b.
- Which is cheaper, gpt-oss-120b or Kimi K2.6?
- gpt-oss-120b costs $0.1/$0.5 per million input/output tokens, while Kimi K2.6 costs $0.95/$4. For a typical workload of 10M input and 1.5M output tokens per month, that's $1.75 versus $15.50.
- Which model is better for coding, gpt-oss-120b or Kimi K2.6?
- We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.