gpt-oss-20b is 23.1× cheaper per million tokens (blended). Step 5 Preview has the larger context window (1,000,000 vs 131,072 tokens, 7.6×).
gpt-oss-20b vs Step 5 Preview
Live catalog fields. Best-in-row is highlighted.
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Step 5 Previewopen
Stepfun · stepfun__step-5-preview
Identity
| Field | openai__gpt-oss-20b | stepfun__step-5-preview |
|---|---|---|
| Provider | OpenAI | Stepfun |
| Slug | openai__gpt-oss-20b | stepfun__step-5-preview |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-20b | stepfun-ai/Step-5-Preview |
Quality
| Field | openai__gpt-oss-20b | stepfun__step-5-preview |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-20b | stepfun__step-5-preview |
|---|---|---|
| Input $ / 1M tokens | $0.03 | $1.00 |
| Cached input $ / 1M | $0.03 | $0.10 |
| Output $ / 1M tokens | $0.13 | $2.70 |
Context
| Field | openai__gpt-oss-20b | stepfun__step-5-preview |
|---|---|---|
| Max context tokens | 131,072 | 1,000,000 |
| Max output tokens | 117,964 | 64,000 |
Modalities
| Field | openai__gpt-oss-20b | stepfun__step-5-preview |
|---|---|---|
| Input | text | text, image, video |
| Output | text | text |