This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
StepFun has launched a newer release, Step 3.5 Flash 2603. We suggest considering it instead.
Step 3.5 Flash API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Step 3.5 Flash for your use-case.
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 2 providers
Lowest Cost per Task
Cost per Intelligence Index task
Total 2 providers
Step 3.5 Flash is available through 2 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
Pricing
Cost per Intelligence Index Task: Step 3.5 Flash
Pricing: Cache Hit, Input, and Output: Step 3.5 Flash
Output Speed vs. Cost per Task: Step 3.5 Flash
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: Step 3.5 Flash
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Step 3.5 Flash
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Step 3.5 Flash
Caching
Cache Hit Rate: Step 3.5 Flash
Cost per Task vs. Cache Hit Rate: Step 3.5 Flash
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Step 3.5 Flash providers
Step 3.5 Flash is available through 2 API providers: StepFun and SiliconFlow (FP8). Each provider offers different performance characteristics and pricing.
Step 3.5 Flash is currently available through 2 API providers that we benchmark and track.
The providers with the lowest time to first answer token for Step 3.5 Flash are StepFun (20.68s) and SiliconFlow (FP8) (91.92s). Lower latency means faster initial response time.
The most affordable providers for Step 3.5 Flash by blended price are StepFun ($0.064 per 1M tokens) and SiliconFlow (FP8) ($0.12 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The providers with the lowest input token pricing for Step 3.5 Flash are StepFun ($0.10 per 1M input tokens) and SiliconFlow (FP8) ($0.10 per 1M input tokens).
The providers with the lowest output token pricing for Step 3.5 Flash are StepFun ($0.30 per 1M output tokens) and SiliconFlow (FP8) ($0.30 per 1M output tokens).
Prices for Step 3.5 Flash vary up to 1.9x across providers. The most affordable is StepFun at $0.064 per 1M tokens, while SiliconFlow (FP8) charges $0.12 per 1M tokens.
1 of 2 providers support JSON mode for Step 3.5 Flash: StepFun.
All 2 providers of Step 3.5 Flash support function calling (tool use).
When choosing a provider for Step 3.5 Flash, consider: time per task (how quickly the provider completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Step 3.5 Flash's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview