Meta / meta/muse-spark-1.2-contributor
Muse Spark 1.2 Contributor - access through LLMTR
Muse Spark 1.2 Contributor is the same checkpoint as Muse Spark 1.2; what differs is the price and the data policy. The prompts you send and the responses you receive are used by Meta to train future models, and in exchange tokens cost far less: $0.10 instead of $1.25 per 1M input tokens, and $0.20 instead of $4.25 per 1M output tokens. Its capabilities are identical to 1.2: a 1,048,576-token context window, image/video/PDF input, tool calling, JSON and schema-conforming structured output, and reasoning effort adjustable from minimal to xhigh. It suits work whose data is not sensitive, such as prototypes, load tests, and integration trials; leave confidential, personal, or customer data to Muse Spark 1.2 on the standard tier. This tier's rate limit is low and shared across the platform, so it is not suited to high-volume production traffic.
Technical specifications
| Canonical ID | meta/muse-spark-1.2-contributor |
|---|---|
| Provider | Meta |
| Context window | 1,048,576 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image, video |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $0.100000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.002000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $0.200000 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"meta/muse-spark-1.2-contributor","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- The real difference between Muse Spark Contributor and the standard version: not quality, price and data policy - The migration-to-standard article covers the mechanical steps of the move. This article covers why there's no output-quality gap to measure between the two identities, and what actually drives the decision.
- Handling timeout and connection errors in Muse Spark Contributor - The 429 retry article for Muse Spark Contributor covers quota exhaustion. This article covers a different error family, timeouts and connection drops, and why they call for a different response.
- Questions to ask before joining Muse Spark Contributor - The evaluation set article covers test methodology after joining the program. This article covers the join decision itself: clarifying what you're actually consenting to.
- Muse Spark 1.2 Contributor cost: cache and reasoning accounting - Separate ordinary input, cached input and total output when estimating Contributor costs. Apply verified rates and track spending per successfully completed task.
- What is Muse Spark 1.2 Contributor? Data policy and the standard tier - Choosing Contributor is a decision about which data your application may send. Evaluate training use, the limits of standard-tier assurances, and controls before the request.
- muse-spark-1.2-contributor: LLMTR model ID and endpoint - Calling Contributor through LLMTR requires the model ID, API base URL and credentials to match. This guide starts with the data warning, then builds a first text request and checks the relevant API contract.
- Building a tool calling loop with muse-spark-1.2-contributor - Muse Spark Contributor proposes tool calls; your application decides whether to execute them. Validate arguments, restrict available operations and return each result with its matching call identifier.
- A non-sensitive evaluation set for Muse Spark Contributor - Evaluate an agent workflow without copying customer records: use narrow tasks, reviewed examples, fixed expected values and local scoring.
- Moving a Muse Spark Contributor prototype to the standard tier - Move from meta/muse-spark-1.2-contributor to meta/muse-spark-1.2 with a practical checklist for data approval, configuration, a trial request, and rollback.
- Meta Muse Spark 1.2 Contributor 429 errors: bounded retries - Safe retries for Muse Spark Contributor require reading both HTTP status and error type. This guide excludes exhausted quotas from rapid retries and sets explicit waiting limits.
- Meta Muse Spark 1.2 Contributor: JSON objects versus JSON Schema - A response that parses as JSON is not necessarily a valid record or a faithful extraction. Keep these three checks separate when using Muse Spark Contributor.
Related models
- Muse Spark 1.3 meta/muse-spark-1.3
- Muse Glimmer 30B meta/muse-glimmer-30b
- Muse Image meta/muse-image-1.0
- Muse Spark 1.2 meta/muse-spark-1.2
- Muse Spark 1.1 meta/muse-spark-1.1
- Muse Spark 1.3 Contributor meta/muse-spark-1.3-contributor
- Llama 3.3 70B Instruct (12K) meta/llama-3.3-70b-instruct-12k
- Llama 3.1 8B Instruct meta/llama-3.1-8b-instruct-16k