StepFunWeights not listed·1000K context·600B params

Step 5 Previewstepfun/step-5-preview

Name: Step 5 Preview API
Brand: StepFun
Availability: InStock

StepFun’s preview flagship accepts text, images and video and returns text. Its sparse architecture has 600B total parameters with 27B active per token. The API supports tool calling, structured output and adjustable reasoning for coding and multimodal workflows.

Cheapest blended:$1.43 / 1M tokenson StepFun · 1 provider listed

Availability and billing notes

Reviewed September 21, 2026 · check the linked provider documentation for later changes.

API available. StepFun announced a planned weight release for October 15, 2026; downloadable weights were not available at this review.

Input is $1.00, cached input $0.05 and output $2.70 per million tokens on the international platform. Output billing includes reasoning tokens.

Official source 1 →Official source 2 →Official source 3 →

Pricing across providers

Sort by:

Provider	Input /1M	Output /1M	Blended /1M	Latency p50	Format	Freshness	Action
StepFun step-5-preview International platform, USD. Preview; reasoning tokens count as output.	$1.00 Cached $0.05	$2.7	$1.425	—	OpenAI-compatible	Price 1mo ago	Try →

Affiliate disclosure: We may earn a commission from qualified signups. Pricing independence is enforced at the data layer — see our Editorial Independence Policy.

Works with

Point any of these clients at a hosting's base URL — they all speak at least one of this model's endpoint protocols (OPENAI_COMPATIBLE).

Capabilities

reasoning
code
vision
tool_calling
structured_output

Code samples

Example using StepFun — the cheapest hosting for this model as of last verification. Swap base_url and model to use a different provider from the matrix above.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.stepfun.ai/v1",
)

response = client.chat.completions.create(
    model="step-5-preview",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Technical specs

Context: 1000K
Max output: 64K
Parameters: 600B
Release: 2026-09-20
Training cutoff: —
License: —

Official documentation →

Similar models

Compare with

Step 5 Preview vs DeepSeek V4.1 Flash
Comparison planned — not yet published
Step 5 Preview vs GLM 5.3 Flash
Comparison planned — not yet published
Step 5 Preview vs Qwen3.5 397B A17B
Comparison planned — not yet published

Frequently asked

How much does Step 5 Preview cost?+

The cheapest public hosting is $1.43 per 1M blended tokens on StepFun. 1 total providers are listed above with per-input / per-output / cached pricing.

Is Step 5 Preview open-source?+

Downloadable weights are not listed in this directory for Step 5 Preview. See the official documentation and availability notes for API, subscription or planned weight-release details.

Is Step 5 Preview OpenAI-compatible?+

At least one listed hosting exposes an OpenAI-compatible API, so you can point an existing openai SDK client at the Provider's base_url and use the Provider's model name. See the Code Samples above for a copy-pasteable example.

What's the maximum context window for Step 5 Preview?+

The model supports up to 1,000,000 tokens of context (input + output). Some hosted versions may impose a smaller limit — check the "Context" column in the pricing matrix for each provider.