Frontier multimodal reasoning with a 1M token context, image and video input, parallel tool calling, and strict JSON schema output.
StepFunText Generation1.02M contextReleased Sep 15, 2026InternationalProprietary EndpointNewFrontier multimodal reasoning with a 1M token context, image and video input, parallel tool calling, and strict JSON schema output.
Use reasoning_effort low, medium, or high to control the reasoning budget. The model returns its reasoning in reasoning_content, and those tokens bill as output tokens. Prompt-cache hits are billed at the cache-read rate. Linkup web search is available through web_search_linkup and adds $0.013 per call when invoked.
Also known as StepFun Step 5 Preview
step-5-preview/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/step-5-preview:generateContentstepfun/step-5-previewLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Step 5 Preview serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id step-5-preview. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "step-5-preview",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="step-5-preview",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the Step 5 Preview API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| temperature | number | 0.5 | 0 to 2 | Sampling temperature. |
| top_p | number | 0.9 | 0 to 1 | Nucleus sampling probability mass. |
| max_tokens | integer | 4096 | 1 to 131072 | Maximum output tokens. Reasoning tokens count toward this limit. |
| stop | array | - | - | Stop sequences. |
| frequency_penalty | number | 0 | 0 to 1 | Penalty for repeated tokens. |
| reasoning_effort | enum | low | low, medium, high | Controls how much the model reasons before it answers. Higher effort spends more tokens on reasoning. |
| reasoning_format | enum | general | general, deepseek-style | Format of the reasoning trace returned alongside the answer. |
| tools | array | - | - | OpenAI-compatible function tools. |
| tool_choice | string | - | - | OpenAI-compatible tool choice. |
| response_format | object | - | - | Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape. |
| web_search_linkup | boolean | false | - | Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model's normal token cost. Disabled by default. |
| disable_formatting | boolean | false | - | When enabled, the gateway will not append the "Sources" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another... |
Supports text, image, and video input with a 1M token context, parallel function tools, strict JSON schema output, and reasoning_effort low, medium, or high. Prompt-cache hits are billed at the cache-read rate. Video input supports MP4 under 128 MB, with clips under 5 minutes recommended. This is a preview release, so its behavior and identifier may change.
On EmpirioLabs, Step 5 Preview is billed pay as you go: Input $1.00 per 1M prompt tokens; Output $2.70 per 1M generated tokens; Implicit cache read $0.05 per 1M cached input tokens; Web Search (Linkup) $0.013 per call when invoked. The live rate card on this page always matches what the API charges.
Step 5 Preview supports a 1.02M-token context window with up to 131,072 output tokens per response.
Yes. Step 5 Preview serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to step-5-preview.
Yes. The EmpirioLabs playground runs Step 5 Preview in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Check out our pricing or reach out if you want your own model deployed on our stack.
