Deepinfra
100.00%Context262.1K
Max output262.1K
p50 latency871 ms
Throughput159.0 t/s
Input price$0.09
Output price$0.3
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
stepfun/step-3.5-flash
StepFun 3.5 Flash
Step 3.5 Flash is an open-source reasoning model by StepFun with 196B total parameters (11B active) using Mixture of Experts. It features a 256K context window, deep reasoning, tool calling, and agentic capabilities, achieving 97.3 on AIME 2025 and 74.4% on SWE-bench Verified.
Input / 1M tokens$0.09
Output / 1M tokens$0.3
Maximum context262.1K
Inference providers1
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Deepinfra | 262.1K | 262.1K | 871 ms | 159.0 t/s | 100.000% | $0.09 | $0.3 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageAdvanced reasoningTool useAutomatic cachingVisionTools
Reasoning options
LowMediumHigh
Technical profile
- Model type
- Language model
- Release date
- Jan 29, 2026
- Knowledge cutoff
- 2025-01
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
stepfun/step-3.5-flashModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.