Skip to main content

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).

Input / output price
$1.00 / $2.70 per 1M
Context
1M tokens
Released
Sep 20, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "stepfun/step-5-preview".

Read docs

Providers

4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
EmpirioLabsempiriolabs/step-5-preview
$1.00/M$2.70/M
Novitanovita/step-5-preview
$1.00/M$2.70/M
StepFunstepfun/step-5-preview
$1.00/M$2.70/M
OpenRouteropenrouter/step-5-preview
$1.00/M$2.70/M

Is a provider down? OpenRouter status

Pricing

Averaged across 4 providers, in USD per 1M tokens after gateway discounts.

Average input
$1.00 per 1M
Average output
$2.70 per 1M
Average cache read
$0.10 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$1.00/MEmpirioLabs, Novita, StepFun, and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

43tokens/sacross providers

Faster than 63% of the other 596 models on the gateway

Response latency

Lower is better

7.0sacross providers

Faster than 24% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 5 published scores from 2 sources, each linked to where it was published.

55.4/ 100

Respan Index#28 of 176

176 ranked models. The shaded band is this model's 95% interval, 41.7 to 67.8. Claude Opus 4.8 and GPT-5.6 Terra fall inside it, so the gap is within the margin of error.
Step 5 Preview by category: Coding 45.4, Agents 56.3, Reasoning 63.9 (estimated), Knowledge & language 56.6 (estimated), Human preference 55.3
  1. 28Step 5 Preview55.4
  2. 27Claude Opus 4.855.7
  3. 29GPT-5.6 Terra55.3

Published scores

BenchmarkScore
Terminal-Bench 4.0Vals AI31.8%

Compare Step 5 Preview: Step 5 Preview vs Muse Spark 1.3, Step 5 Preview vs Step 3.5 Flash

Apps

Use Step 5 Preview in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Step 5 Preview FAQ

Short answers, built from the data on this page.

Step 5 Preview is a model from StepFun, released on Sep 20, 2026. Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).

On the Respan gateway, Step 5 Preview costs $1.00 per 1M input tokens and $2.70 per 1M output tokens on every provider, after gateway discounts.

Step 5 Preview is available through 4 providers: EmpirioLabs, Novita, StepFun, and OpenRouter.

Step 5 Preview accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "stepfun/step-5-preview". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Step 5 Preview scores 55.4 out of 100 on the Respan Index v1.1, ranking #28 of 176 models. By category: Coding 45.4, Agents 56.3, Reasoning 63.9 (estimated), Knowledge & language 56.6 (estimated), and Human preference 55.3. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Step 5 Preview has 5 published benchmark scores, including Terminal-Bench 4.0 31.8% and LMArena WebDev 1570. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.