StepFun: Step 3.5 Flash pricing and limits

id stepfun/step-3.5-flash · listed 2026-01-29

Input (per 1M tokens)	$0.100
Output (per 1M tokens)	$0.300
Context window	262,144 tokens
Max output	65,536 tokens
Modalities	text → text
Reasoning	yes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $0.19.

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....

Cheaper on both input and output, with at least half the context

Model	In / 1M	Out / 1M	Context
Auto Router (Beta)	$-1000000.000	$-1000000.000	2,000,000
Pareto Code Router	$-1000000.000	$-1000000.000	2,000,000
Auto Router	$-1000000.000	$-1000000.000	2,000,000
OpenAI: GPT-6 Luna Pro (batch)	$0.050	$0.250	1,050,000
OpenAI: GPT-6 Luna (batch)	$0.050	$0.250	1,050,000
DeepSeek: DeepSeek V4.1 Flash (batch)	$0.050	$0.150	1,048,576

Other stepfun models

StepFun: Step 3.7 Flash ($0.200 / $1.150) · StepFun: Step 5 Preview ($1.000 / $2.700)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=stepfun/step-3.5-flash (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=stepfun. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with stepfun. Agent Exchange