StepFun: Step 5 Preview

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and p…

stepfun/step-5-preview-20261008

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance.

It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.

Specifications & capabilities

Input
text, image, video
Output
text
Context window · tokens
1000000
Published model ID
step-5-preview
Capabilities
multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Description source ↗

Evaluations

1–1 / 1

Published prices

1–18 / 18

stepfun/step-5-preview ↗

$0.10

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

stepfun/step-5-preview ↗

$1.00

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

stepfun/step-5-preview ↗

$2.70

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

step-5-preview ↗

$0.10

Inference provider
stepFun
Platform
StepFun
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input / 1M tokens

step-5-preview ↗

$1.00

Inference provider
stepFun
Platform
StepFun
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input / 1M tokens (cache miss)

step-5-preview ↗

$2.70

Inference provider
stepFun
Platform
StepFun
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output / 1M tokens

stepfun/step-5-preview ↗

$0.10

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | stepfun/step-5-preview
model_type
language
quantization
fp8
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$1.00

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | stepfun/step-5-preview
model_type
language
quantization
fp8
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$2.70

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | stepfun/step-5-preview
model_type
language
quantization
fp8
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$0.10

Inference provider
vercelAIGatewayCatalog
Platform
stepfun
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
stepfun | stepfun/step-5-preview
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$1.00

Inference provider
vercelAIGatewayCatalog
Platform
stepfun
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
stepfun | stepfun/step-5-preview
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$2.70

Inference provider
vercelAIGatewayCatalog
Platform
stepfun
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
stepfun | stepfun/step-5-preview
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$0.10

Inference provider
vercelAIGatewayCatalog
Platform
tencent
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
tencent | stepfun/step-5-preview
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$1.00

Inference provider
vercelAIGatewayCatalog
Platform
tencent
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
tencent | stepfun/step-5-preview
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$2.70

Inference provider
vercelAIGatewayCatalog
Platform
tencent
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
tencent | stepfun/step-5-preview
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$0.10

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$1.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
input_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

stepfun/step-5-preview ↗

$2.70

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–3 / 3

Step 5 Preview ↗

source model id
step-5-preview
hosting
stepfun-global-hosted
platforms
  • StepFun
context length
1000000
max input tokens
1000000
max output tokens
64000
architecture
input_modalities
  • text
  • image
  • video
output_modalities
  • text
capabilities
  • multimodal
  • promptCaching
  • reasoning
  • streaming
  • structuredOutputs
  • toolCalling
  • videoInput
  • visionInput

Step 5 Preview ↗

source model id
stepfun-ai/step-5-preview
hosting
nvidia-catalog
platforms
  • NVIDIA Build / NIM
context length
1048576
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • toolCalling
  • reasoning

Step 5 Preview ↗

source model id
stepfun/step-5-preview
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
1048576
max output tokens
1048576
architecture
input_modalities
  • text
  • image
  • video
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • videoInput
  • visionInput

Source specification observations

1–8 / 8

nvidiaNim ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
nvidiaNim
confidence
1

openRouter ↗

field
context_length
value
1000000
normalized value
1000000
scope
source-model
source id
openRouter
confidence
1

stepFun ↗

field
context_length
value
1000000
normalized value
1000000
scope
source-model
source id
stepFun
confidence
1

vercelAIGatewayCatalog ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

stepFun ↗

field
max_input_tokens
value
1000000
normalized value
1000000
scope
source-model
source id
stepFun
confidence
1

openRouter ↗

field
max_output_tokens
value
64000
normalized value
64000
scope
source-model
source id
openRouter
confidence
1

stepFun ↗

field
max_output_tokens
value
64000
normalized value
64000
scope
source-model
source id
stepFun
confidence
1

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
1048576
normalized value
1048576
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

Original sources

1–12 / 12

StepFun · Model reference ↗

Hugging Face · stepfun-ai/Step-5-Preview ↗

NVIDIA · Model page ↗

OpenRouter · Model page ↗

Vercel AI Gateway · Model page ↗

NVIDIA · Documentation ↗

StepFun · Model documentation ↗

Epoch AI · Catalog ↗

NVIDIA · Catalog ↗

OpenRouter · Catalog ↗

StepFun · Catalog ↗

Vercel AI Gateway · Catalog ↗

Source links

1–7 / 7

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace