gpt-oss-20b is 2.5× cheaper per million tokens (blended). Step 3.5 Flash has the larger context window (262,144 vs 131,072 tokens, 2.0×).
gpt-oss-20b vs Step 3.5 Flash
Live catalog fields. Best-in-row is highlighted.
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Step 3.5 Flashopen
Stepfun · stepfun__step-3.5-flash
Identity
| Field | openai__gpt-oss-20b | stepfun__step-3.5-flash |
|---|---|---|
| Provider | OpenAI | Stepfun |
| Slug | openai__gpt-oss-20b | stepfun__step-3.5-flash |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-20b | stepfun-ai/Step-3.5-Flash |
Quality
| Field | openai__gpt-oss-20b | stepfun__step-3.5-flash |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-20b | stepfun__step-3.5-flash |
|---|---|---|
| Input $ / 1M tokens | $0.03 | $0.10 |
| Cached input $ / 1M | $0.03 | — |
| Output $ / 1M tokens | $0.13 | $0.30 |
Context
| Field | openai__gpt-oss-20b | stepfun__step-3.5-flash |
|---|---|---|
| Max context tokens | 131,072 | 262,144 |
| Max output tokens | 117,964 | 65,536 |
Modalities
| Field | openai__gpt-oss-20b | stepfun__step-3.5-flash |
|---|---|---|
| Input | text | text |
| Output | text | text |