gpt-oss-20b is 19.4× cheaper per million tokens (blended). Kimi K2 0905 has the larger context window (262,144 vs 131,072 tokens, 2.0×).
Kimi K2 0905 vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Kimi K2 0905open
Moonshotai · moonshotai__kimi-k2-0905
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | moonshotai__kimi-k2-0905 | openai__gpt-oss-20b |
|---|---|---|
| Provider | Moonshotai | OpenAI |
| Slug | moonshotai__kimi-k2-0905 | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | moonshotai/Kimi-K2-Instruct-0905 | openai/gpt-oss-20b |
Quality
| Field | moonshotai__kimi-k2-0905 | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | moonshotai__kimi-k2-0905 | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.60 | $0.03 |
| Cached input $ / 1M | — | $0.03 |
| Output $ / 1M tokens | $2.50 | $0.13 |
Context
| Field | moonshotai__kimi-k2-0905 | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 262,144 | 131,072 |
| Max output tokens | 98,304 | 117,964 |
Modalities
| Field | moonshotai__kimi-k2-0905 | openai__gpt-oss-20b |
|---|---|---|
| Input | text | text |
| Output | text | text |