gpt-oss-20b is 4.7× cheaper per million tokens (blended). gpt-oss-20b has the larger context window (131,072 vs 128,000 tokens).
LFM2.5-24B-A2B vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
LFM2.5-24B-A2Bopen
Liquid · liquid__lfm-2.5-24b-a2b
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | liquid__lfm-2.5-24b-a2b | openai__gpt-oss-20b |
|---|---|---|
| Provider | Liquid | OpenAI |
| Slug | liquid__lfm-2.5-24b-a2b | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | LiquidAI/LFM2.5-24B-A2B | openai/gpt-oss-20b |
Quality
| Field | liquid__lfm-2.5-24b-a2b | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | liquid__lfm-2.5-24b-a2b | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.05 | $0.03 |
| Cached input $ / 1M | $0.03 | $0.03 |
| Output $ / 1M tokens | $0.70 | $0.13 |
Context
| Field | liquid__lfm-2.5-24b-a2b | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 128,000 | 131,072 |
| Max output tokens | 8,192 | 117,964 |
Modalities
| Field | liquid__lfm-2.5-24b-a2b | openai__gpt-oss-20b |
|---|---|---|
| Input | text | text |
| Output | text | text |