Type
Spec
Rate
Input
per 1M prompt tokens
$1.25
Output
per 1M generated tokens
$4.25
Implicit cache read
per 1M cached input tokens
$1.00
Web search
per search query
$0.00825
Muse Spark 1.3 and Seed 2.1 Turbo side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Meta AI 
ByteDance Text GenerationMuse Spark 1.3 from Meta AI and Seed 2.1 Turbo from ByteDance are both in the Text Generation category, available through the EmpirioLabs API.
| Spec | Muse Spark 1.3 | Seed 2.1 Turbo |
|---|---|---|
| Model ID | muse-spark-1-3 | seed-2-1-turbo |
| Author | Meta AI | ByteDance |
| Released | Sep 2, 2026 | Jul 13, 2026 |
| Context window | 1M tokens | 229.1K tokens |
| Max output | 131,072 tokens | 65,536 tokens |
| Input | Text Image Video Document | Text Image Video |
| Output | Text | Text |
| Structured output | JSON Schema | JSON Schema |
| Region | - | Malaysia |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/muse-spark-1-3:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/seed-2-1-turbo: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 | Muse Spark 1.3 | Seed 2.1 Turbo |
|---|---|---|
| max_tokens | 16 to 131072 Default: 16384 | 1 to 65536 |
| temperature | 0 to 2 Default: 1 | - |
| top_p | 0.01 to 1 Default: 1 | - |
| reasoning_effort | minimal, low, medium, high, xhigh Default: medium | low, medium, high Default: high |
| tool_web_search | boolean Default: false | - |
| tools | array Default: [] | - |
| tool_choice | object | - |
| parallel_tool_calls | boolean | - |
| response_format | enum | enum |
| frequency_penalty | - | -2 to 2 Default: 0 |
| presence_penalty | - | -2 to 2 Default: 0 |
| stop | - | string |
| enable_thinking | - | boolean Default: true |
| enable_web_search | - | boolean Default: false |
| max_tool_calls | - | 1 to 10 Default: 3 |
| image_detail | - | low, high, xhigh Default: high |
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.
Per-token pricing is flat across the full context window, with no higher rate above 128K. Reasoning is on by default; set enable_thinking to false to answer directly without it.
Muse Spark 1.3 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 muse-spark-1-3. Both models are called through the same endpoint. Set model to muse-spark-1-3 or seed-2-1-turbo. 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": "muse-spark-1-3",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Prompt tests and comparison runs that cover both models.
Muse Spark 1.3 is the newer release (Sep 2, 2026); Seed 2.1 Turbo was released on Jul 13, 2026. Muse Spark 1.3 has the larger context window: 1M tokens, against 229.1K for Seed 2.1 Turbo. Muse Spark 1.3 returns up to 131,072 output tokens per response, Seed 2.1 Turbo up to 65,536. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Muse Spark 1.3 is the newer release (Sep 2, 2026); Seed 2.1 Turbo was released on Jul 13, 2026.
Seed 2.1 Turbo 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.
