Step-3.5-Flash: Benchmarks, Pricing & Context Window
Step-3.5-Flash is a language model from StepFun, released in February 2026, with pricing from $0.100/M input, $0.020/M cached input, $0.400/M output.
Step-3.5-Flash is StepFun's fast, cost-effective text model optimized for quick inference. Built on their Step3 architecture, it offers strong performance across text tasks with low latency and efficient token usage, ideal for production
Step-3.5-Flash benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Step-3.5-Flash across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Step-3.5-Flash holds up as conversations get longer.
Quality Tracker
Step-3.5-Flash Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Oct 02 2026Step-3.5-Flash pricing
Providers
Step-3.5-Flash starts at $0.100 per million input tokens and $0.400 per million output tokens via StepFun. Reused prompt prefixes cost $0.0200 per million cached input tokens.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 StepFun | $0.100 | $0.0200 | $0.400 | 65.5K/8.2K | 0.30 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Step-3.5-Flash model size
Step-3.5-Flash has 196 billion parameters. See how it compares to other models in the same parameter range.
Step-3.5-Flash context window
Input and output token limits for Step-3.5-Flash, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Step-3.5-Flash.
Step-3.5-Flash latency
Step-3.5-Flash time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Step-3.5-Flash examples
Recent arena outputs from Step-3.5-Flash, picked from the highest-ranked matchups.
Step-3.5-Flash license
Step-3.5-Flash is released under the Apache 2.0 license, which permits commercial use, has 196.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 196.0B
Apache License 2.0 - allows commercial use
Step-3.5-Flash resources
Official sources for Step-3.5-Flash: provider documentation, official playground, official launch post, source repository.
Step-3.5-Flash vs other models
The most-compared alternatives to Step-3.5-Flash are GPT-5.1 Medium, Seed 2.0 Pro, GPT-5.2. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Step-3.5-Flash
Models ranked just above and below Step-3.5-Flash by LLM Stats score.
FAQ
Common questions about Step-3.5-Flash.