API Provider1 active models1 organization

StepFun: API pricing, speed & models

StepFun hosts 1 active AI models, with input pricing from $0.10 per 1M tokens, with median throughput of 1,025 characters/sec, and P95 time to first token of 732ms, with 100% success rate over 7 days. Compare StepFun's API speed, pricing, and reliability against other inference providers.

First-party only
Median throughput1,025 c/s
Median TTFT674ms
P95 TTFT732ms
Success rate (7d)100%
From$0.10 /M tok

Catalog

Type
Price
2 models
Model
At a glance

StepFunpricing, performance & catalog

The citable facts about StepFun's 1 model — sourced from provider APIs and refreshed continuously.

Lowest price
Step-3.5-Flash at $0.100 per 1M input tokens
Highest median throughput
Step-3.5-Flash at 1025 chars/s
Lowest median TTFT
Step-3.5-Flash at 0.67s
Largest context
Step-3.5-Flash at 66K tokens
Catalog
1 active models from 1 organization

Fastest median throughput

  1. 1Step-3.5-Flash1025 c/s

Largest context

  1. 1Step-3.5-Flash66K

FAQ

Common questions about StepFun.

What is StepFun?

StepFun is an API provider that hosts large language models. Active models: 1; From (input): $0.10 / 1M tok; Median throughput: 1,025 c/s; Median TTFT: 674ms; Success rate (7d): 100%.

How many models does StepFun offer?

StepFun currently serves 1 active models out of 1 historical offerings on LLM Stats.

What is StepFun's API pricing?

StepFun input pricing starts from $0.10 per 1M tokens, with the most expensive offering at $0.1 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

How fast is StepFun?

StepFun delivers a median throughput of 1,025 characters per second and P95 time to first token of 732ms across its model catalog. See the Models tab for per-model throughput and TTFT breakdowns.

Is StepFun reliable?

StepFun has a 100% success rate across 7 API calls in the last 7 days, with a 0% error rate.

Does StepFun support function calling?

Yes. 2 of 1 models on StepFun support function calling (tool use). The Capabilities tab lists which specific models accept tool definitions.

Does StepFun support JSON mode and structured output?

Yes. 2 of 1 models on StepFun support structured output (JSON mode / schema-constrained generation). The Capabilities tab shows which specific models accept response_format or json_schema parameters.

Does StepFun support multimodal models?

Yes. StepFun's catalog includes 1 vision-capable models. See the Models and Capabilities tabs for the full per-model breakdown.

Whose models does StepFun host?

StepFun hosts models from StepFun. See the Models tab for the full catalog grouped by creator.

How do I start using StepFun?

Sign up at https://platform.stepfun.com to get an API key, then call StepFun's API directly from your application. Most clients work out of the box by pointing the OpenAI SDK at StepFun's base URL with your key. Use the Models and Pricing tabs above to pick the right model for your latency, cost, and context-window requirements.