StepFunAuto-detectedStep 2
Not yet ranked: too few independent results so far. Released 1 Jan 2025.
- Blended price
- $8.02/M
- $5.21 in · $16.44 out
- Output speed
- –
- First answer
- –
- Context
- 16k
- Reasoning49
- Coding50
- Human preference50
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| LMArena Hard Prompts | 1338#202 | LMArena |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1371#199 | LMArena |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1334#199 | LMArena |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $1.04 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0070 | $0.0058 | – |
| Summarise a 30-page report | 12,000 / 600 | $0.072 | $0.035 | – |
| Code edit | 6,000 / 1,500 | $0.056 | $0.037 | – |
| Agentic coding session | 60,000 / 4,000 | $0.378 | $0.191 | – |
| Structured extraction | 2,000 / 200 | $0.014 | $0.0075 | – |
See also
Data as of 9 Sept 2026. Compare with another model.