Type
Spec
Rate
Input
per 1M prompt tokens
$1.00
Output
per 1M generated tokens
$2.70
Implicit cache read
per 1M cached input tokens
$0.10
Web Search (Linkup)
per call when invoked
$0.013
Step 5 Preview and Muse Spark 1.3 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
StepFun 
Meta AI Text GenerationStep 5 Preview from StepFun and Muse Spark 1.3 from Meta AI are both in the Text Generation category, available through the EmpirioLabs API.
| Spec | Step 5 Preview | Muse Spark 1.3 |
|---|---|---|
| Model ID | step-5-preview | muse-spark-1-3 |
| Author | StepFun | Meta AI |
| Released | Sep 15, 2026 | Sep 2, 2026 |
| Context window | 1.02M tokens | 1M tokens |
| Max output | 131,072 tokens | 131,072 tokens |
| Input | Text Image Video | Text Image Video Document |
| Output | Text | Text |
| Structured output | JSON Schema | JSON Schema |
| Region | International | - |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/step-5-preview:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/muse-spark-1-3:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Step 5 Preview | Muse Spark 1.3 |
|---|---|---|
| temperature | 0 to 2 Default: 0.5 | 0 to 2 Default: 1 |
| top_p | 0.01 to 1 Default: 0.9 | 0.01 to 1 Default: 1 |
| max_tokens | 1 to 131072 Default: 4096 | 16 to 131072 Default: 16384 |
| stop | array | - |
| frequency_penalty | -2 to 2 Default: 0 | - |
| reasoning_effort | low, medium, high Default: low | minimal, low, medium, high, xhigh Default: medium |
| reasoning_format | general, deepseek-style Default: general | - |
| tools | array | array Default: [] |
| tool_choice | string | object |
| response_format | object | enum |
| web_search_linkup | boolean Default: false | - |
| disable_formatting | boolean Default: false | - |
| tool_web_search | - | boolean Default: false |
| parallel_tool_calls | - | boolean |
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.
Reasoning is always on and cannot be disabled. reasoning_effort accepts minimal through xhigh. On /v1/chat/completions the reasoning text is not returned; on /v1/responses you can request reasoning summaries with reasoning.summary, and reasoning tokens are billed as output tokens and count against the output budget either way. Text, image, MP4 video, and PDF inputs are supported; up to 50 images can be attached. Audio input is not supported on this checkpoint; the Muse Spark 1.1 and 1.2 checkpoints accept audio. PDFs use text from the first 100 pages and page images from the first 50 pages. Built-in web search adds $0.00825 per executed search query and reports the count in usage.tool_usage. OpenAI Responses requests also support custom tools and deferred tool search. tool_choice supports auto and none. Prompts and completions sent to this Standard checkpoint are not used by Meta to train its models.
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. Both models are called through the same endpoint. Set model to step-5-preview or muse-spark-1-3. 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."}
]
}'Prompt tests and comparison runs that cover both models.
Step 5 Preview is the newer release (Sep 15, 2026); Muse Spark 1.3 was released on Sep 2, 2026. Muse Spark 1.3 has the larger context window: 1M tokens, against 1.02M for Step 5 Preview. Input types only Muse Spark 1.3 accepts: Document. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Step 5 Preview is the newer release (Sep 15, 2026); Muse Spark 1.3 was released on Sep 2, 2026.
Step 5 Preview lists the lower rate for Input (per 1M prompt tokens) and Output (per 1M generated tokens). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.
