> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Step 5 Preview

> Frontier multimodal reasoning with a 1M token context, image and video input, parallel tool calling, and strict JSON schema output.

![Step 5 Preview](https://media.empiriolabs.ai/model-logos/step-5-preview.png)

[StepFun](/providers/stepfun) · Text Generation

`POST /v1/chat/completions`

Frontier multimodal reasoning with a 1M token context, image and video input, parallel tool calling, and strict JSON schema output.

## At a glance

| Field               | Value                                                                                                                        |
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| Model id            | `step-5-preview`                                                                                                             |
| Model release date  | 2026-09-15                                                                                                                   |
| Input modalities    | Text, Image, Video                                                                                                           |
| Output modalities   | Text                                                                                                                         |
| Context window      | 1.02M                                                                                                                        |
| Weight precision    | -                                                                                                                            |
| Max output tokens   | 131,072                                                                                                                      |
| Region              | International                                                                                                                |
| Features            | reasoning, function_calling, structured_output, vision, video, prompt_cache, agentic_coding                                  |
| Native inference    | No                                                                                                                           |
| New                 | Yes                                                                                                                          |
| Structured output   | JSON Schema                                                                                                                  |
| Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/step-5-preview:generateContent` |
| Alternate model ids | `stepfun/step-5-preview`                                                                                                     |

## Pricing

| Charge              | Spec                       | Rate    |
| ------------------- | -------------------------- | ------- |
| Input               | per 1M prompt tokens       | \$1.00  |
| Output              | per 1M generated tokens    | \$2.70  |
| Implicit cache read | per 1M cached input tokens | \$0.05  |
| Web Search (Linkup) | per call when invoked      | \$0.013 |

## Example request

```bash
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":"Hello"}]}'
```

## Parameters

| Parameter            | Type    | Required | Default     | Description                                                                                                                                                                                                                                                                         |
| -------------------- | ------- | -------- | ----------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `temperature`        | number  | no       | `0.5`       | Sampling temperature. · Range: 0 – 2                                                                                                                                                                                                                                                |
| `top_p`              | number  | no       | `0.9`       | Nucleus sampling probability mass. · Range: 0 – 1                                                                                                                                                                                                                                   |
| `max_tokens`         | integer | no       | `4096`      | Maximum output tokens. Reasoning tokens count toward this limit. · Range: 1 – 131072                                                                                                                                                                                                |
| `stop`               | array   | no       | -           | Stop sequences.                                                                                                                                                                                                                                                                     |
| `frequency_penalty`  | number  | no       | `0`         | Penalty for repeated tokens. · Range: 0 – 1                                                                                                                                                                                                                                         |
| `reasoning_effort`   | enum    | no       | `"low"`     | Controls how much the model reasons before it answers. Higher effort spends more tokens on reasoning. · Allowed: `low`, `medium`, `high`                                                                                                                                            |
| `reasoning_format`   | enum    | no       | `"general"` | Format of the reasoning trace returned alongside the answer. · Allowed: `general`, `deepseek-style`                                                                                                                                                                                 |
| `tools`              | array   | no       | -           | OpenAI-compatible function tools.                                                                                                                                                                                                                                                   |
| `tool_choice`        | string  | no       | -           | OpenAI-compatible tool choice.                                                                                                                                                                                                                                                      |
| `response_format`    | object  | no       | -           | 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 | no       | 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 | no       | 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 system that expects no decoration.                                                                              |

## Notes

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.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/step-5-preview`.