gpt-oss-120b is 28.7× cheaper per million tokens (blended). Kimi K2 Thinking has the larger context window (262,144 vs 131,072 tokens, 2.0×).
Kimi K2 Thinking vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Kimi K2 Thinkingopen
Moonshotai · moonshotai__kimi-k2-thinking
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | moonshotai__kimi-k2-thinking | openai__gpt-oss-120b |
|---|---|---|
| Provider | Moonshotai | OpenAI |
| Slug | moonshotai__kimi-k2-thinking | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | moonshotai/Kimi-K2-Thinking | openai/gpt-oss-120b |
Quality
| Field | moonshotai__kimi-k2-thinking | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | moonshotai__kimi-k2-thinking | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.60 | $0.02 |
| Cached input $ / 1M | $0.15 | $0.02 |
| Output $ / 1M tokens | $2.50 | $0.09 |
Context
| Field | moonshotai__kimi-k2-thinking | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 262,144 | 131,072 |
| Max output tokens | 98,304 | 65,536 |
Modalities
| Field | moonshotai__kimi-k2-thinking | openai__gpt-oss-120b |
|---|---|---|
| Input | text | text |
| Output | text | text |