Traffic rank on Composite
#101 of 194
0.01% of tokens and 0.02% of requests over 30 days.
AI model
StepFun: Step 3.5 Flash
stepfun/step-3.5-flash
StepFun: Step 3.5 Flash is a 262,144-token model served on Composite at $0.125 per million tokens in and $0.375 per million tokens out. Ranked #101 of 194 models by traffic on Composite over the last 30 days, taking 0.01% of tokens and 0.02% of requests.
Try in PlaygroundSpecifications
| Model ID | stepfun/step-3.5-flash |
|---|---|
| Provider | cv11 |
| Context window | 262,144 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.125 per million tokens |
| Output price | $0.375 per million tokens |
| Prompt caching | Not offered for this model |
| Thinking | Always on for this model |
| Moderated | No |
| Cost on a monthly plan | About 1.1 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 2 (base plus 1 routing variant) |
Routing variants
The same model behind 1 alternative endpoint. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| cheapThink | stepfun/step-3.5-flash:cheapThink |
cv11 | $0.125 per million tokens input · $0.375 per million tokens output |
Pricing
$0.125 per million tokens input · $0.375 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 1.1 plan credits, at the provider's own price.
Provider
cv11
Roleplay fit
StepFun models are a China-based lab entry with competitive pricing for their capability class.
Context behavior
With a 262,144-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
Cost for regular use
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
From the provider
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
Supplied by cv11, not written by Composite.
Related models
Composite Anthropic Router · Composite Gemini Router · Composite GPT Router