# Meta Model API

> Source: https://aiwiki.ai/wiki/meta_model_api
> Updated: 2026-09-05
> Fact-checked: 2026-09-05
> Categories: AI Tools & Products, Developer Tools, Meta AI
> License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) - attribute to "AI Wiki (aiwiki.ai)"
> Cite as: AI Wiki. "Meta Model API." aiwiki.ai, 5 Sept 2026. https://aiwiki.ai/wiki/meta_model_api
> From AI Wiki (https://aiwiki.ai), the free encyclopedia of artificial intelligence. Reuse freely with attribution.

Meta Model API is a hosted artificial-intelligence inference service from [Meta Superintelligence Labs](https://aiwiki.ai/wiki/meta_superintelligence_labs). Meta opened it in public preview on July 9, 2026, with [Muse Spark 1.1](https://aiwiki.ai/wiki/muse_spark) as its initial model. The service is available through self-serve signup to developers in the United States and gives new accounts $20 in launch credits.[1][2] The service has since added Muse Spark 1.2 (August 5, 2026, with what Meta called "expanded global access") and Muse Spark 1.3 (September 2, 2026), whose max reasoning mode followed on September 4, while list prices have stayed at the July levels.[9][12][13][16]

The API is distinct from both the consumer [Meta AI](https://aiwiki.ai/wiki/meta_ai) service and Meta's open-weight Llama program. Muse Spark 1.1 also powers Thinking mode in Meta AI, but the Model API provides developer-controlled prompts, tools, and agent scaffolds through a paid endpoint. Meta's earlier [Llama API](https://aiwiki.ai/wiki/llama_api) preview served Llama models and offered different experimental capabilities.[1][8]

## Release and access

Meta describes the service as a public preview rather than a generally available product. Its public developer page limits eligibility to US developers, offers one-click API-key creation, and promotes compatibility with existing OpenAI SDK code. Meta has not announced a general-availability date, international rollout schedule, enterprise service-level agreement, or dedicated-capacity option on its accessible public pages.[2]

| Attribute | Public-preview information |
| --- | --- |
| Provider | Meta Superintelligence Labs |
| Launch date | July 9, 2026 |
| Eligible users | Developers in the United States |
| Initial model | `muse-spark-1.1` |
| Base URL | `https://api.meta.ai/v1` |
| Authentication | API key |
| Primary interface | OpenAI-compatible Responses API |
| Context window | 1 million tokens |
| Launch credit | $20 per account |
| General availability | Not announced |
| Later models | `muse-spark-1.2` (August 5, 2026) and `muse-spark-1.3` (September 2, 2026), each with a `-contributor` variant [9][13] |

Meta's developer landing page tells users to point an existing OpenAI-compatible client at the service. Current integration documentation identifies `POST /v1/responses` as the primary endpoint, with `/v1/chat/completions` and an Anthropic-compatible `/v1/messages` interface also documented. The Responses surface has the broadest advertised feature support, including built-in web search.[2][6][7]

Meta has published quick-start and agent-pattern resources, but its detailed API reference and current contractual documents redirect to a signed-in developer portal. No separate first-party Model API SDK or public source repository was identified at launch. Compatibility with the [OpenAI API](https://aiwiki.ai/wiki/openai_api) format lets developers reuse clients, but it does not imply that every OpenAI request field or behavior is supported.[2][4][6]

## Model roster after launch

Meta added Muse Spark 1.2 to the API on August 5, 2026, together with the [Muse Code](https://aiwiki.ai/wiki/muse_code) terminal agent, and said the model was available "in Muse Code and in Meta Model API with expanded global access" after the US-only July preview.[9] The same release introduced a second, cheaper route: a Contributor tier at $0.10 per million input tokens and $0.20 per million output tokens for developers who allow Meta to use their prompts and completions to train its models, which MacRumors reported alongside the unchanged Standard prices (CNBC quoted Wang calling the tier "more than 10 times cheaper" than pay-as-you-go). MacRumors gave the Contributor rate limits as 60 requests and 2,100,000 tokens per minute against 3,000 requests and 4,000,000 tokens per minute on the Standard tier, and CNBC reported that Meta had begun accepting requests for zero-data retention.[10][11]

Muse Spark 1.3 followed on September 2, 2026, available the same day through Muse Code and the API.[12] Winbuzzer and TechRepublic both reported that the standard rates did not move: $1.25 per million input tokens, $0.15 per million cached input tokens and $4.25 per million output tokens, the same as for 1.2. Winbuzzer added that the model has a one-million-token combined context window and accepts text, images and video as input while producing text.[14][15] Meta's own developer pages, as archived on September 3 and 4, list `muse-spark-1.3` at those prices and `muse-spark-1.3-contributor` at $0.10 input, $0.002 cached input and $0.20 output, each with a 1M context window, next to identical rows for the two 1.2 variants.[13][20]

| Model (Meta's developer pages, September 2026) | Context window | Input (per 1M tokens) | Cached input (per 1M tokens) | Output (per 1M tokens) | Meta's data-use label |
| --- | --- | --- | --- | --- | --- |
| `muse-spark-1.3` | 1M | $1.25 | $0.15 | $4.25 | "Not used to improve our products" |
| `muse-spark-1.3-contributor` | 1M | $0.10 | $0.002 | $0.20 | "Used to improve our products" |
| `muse-spark-1.2` | 1M | $1.25 | $0.15 | $4.25 | "Not used to improve our products" |
| `muse-spark-1.2-contributor` | 1M | $0.10 | $0.002 | $0.20 | "Used to improve our products" |

At launch Meta withheld the 1.3 model's `max` reasoning mode pending additional safety testing; the launch post said "Previously available reasoning modes are available today with max reasoning coming shortly after we finish additional safety testing."[17] On September 4, 2026, [Alexandr Wang](https://aiwiki.ai/wiki/alexandr_wang) posted that Meta had "publicly released Muse Spark 1.3 max," and the Meta for Developers account wrote that "Muse Spark 1.3 with max reasoning is now available on Muse Code and Meta Model API."[16][18] Meta then changed the launch post's availability line to that wording without an edit note.[12][17]

The Contributor discount drew its own coverage after the 1.3 release. Cryptopolitan, citing Meta's pricing page as viewed on September 3, described the tier as "up to 21x" cheaper (the $0.20 output rate against $4.25) and its cached-input rate as a 75x cut, quoted Meta's pricing guide as saying the tier "lowers the barrier to entry for prototyping, testing integrations, and scaling experiments where training on your data is acceptable," and gave the Contributor rate limit as 100 requests per minute against 3,000 on the standard plan, a higher Contributor figure than the 60 requests per minute MacRumors reported at the August launch.[11][19]

## Model and modalities

Muse Spark 1.1 is a proprietary multimodal reasoning model designed for coding, tool use, computer interaction, and long, multi-step tasks. Meta advertises a one-million-token [context window](https://aiwiki.ai/wiki/context_window) with active context management that can compact an ongoing task as it approaches the limit. Meta has not published a maximum output-token setting for the public preview.[1]

The launch materials describe understanding of text, images, video, PDF files, and audio. The direct API's output is text: Meta's evaluation report describes a query-only interface returning text completions, without exposing hidden chain-of-thought, gradients, or model activations.[1][3][5]

Audio availability needs qualification. Meta says Muse Spark can inspect audio, but current Promptfoo provider documentation marks both audio input and output unsupported in its direct Model API integration. Consequently, the public evidence establishes broad model-level audio capability, not reliable audio acceptance on the present API surface. No image-, video-, or audio-generation endpoint was announced.[1][6]

Meta has not disclosed Muse Spark 1.1's parameter count, architecture, training corpus, training compute, or downloadable checkpoint. It has also not announced Model API fine-tuning, checkpoint export, or self-hosting. These omissions distinguish the service from Meta's open-weight [Llama](https://aiwiki.ai/wiki/llama) releases.[1][8]

## Tools and agent workflows

The API supports developer-defined [function calling](https://aiwiki.ai/wiki/function_calling), developer prompts, and agent scaffolds. Meta says Muse Spark can generalize to native tools, custom skills, and [Model Context Protocol](https://aiwiki.ai/wiki/model_context_protocol) servers. It can operate as a main agent that creates subagents and can coordinate parallel work when the developer's harness supplies those facilities.[1][3]

Built-in web search can ground an answer with citations. Current integration documentation also lists JSON-schema [structured output](https://aiwiki.ai/wiki/structured_output), prompt caching, reasoning-effort controls, and seed values. These are preview features whose exact request fields and limits are governed by the signed-in documentation.[2][6]

Meta presents coding and [computer use](https://aiwiki.ai/wiki/computer_use) as important use cases. This does not give the model unrestricted access to a machine. A developer must provide a browser, shell, file system, application, or other tool and decide what the model may call. Similarly, MCP compatibility means the model can work with developer-connected servers; Meta is not hosting every MCP server on the user's behalf.[1][4]

Meta's multi-agent examples also describe a system pattern rather than a guaranteed server-side workflow. The model can propose and coordinate subagents, but the surrounding application remains responsible for running them, enforcing permissions, handling failures, and accounting for their token and tool costs.[1][4]

## Pricing and rate limits

Reuters reported launch pricing of $1.25 per million input tokens and $4.25 per million output tokens. Current Promptfoo documentation matches those prices and additionally lists cached input at $0.15 per million tokens and built-in web search at $2.50 per 1,000 queries.[5][6]

| Usage | Documented preview price |
| --- | --- |
| Input tokens | $1.25 per million |
| Cached input tokens | $0.15 per million |
| Output tokens | $4.25 per million |
| Web-search queries | $2.50 per 1,000 |

Promptfoo lists per-team limits of 60 requests per minute and 2 million tokens per minute for accounts using the initial credit, and 3,000 requests per minute and 4 million tokens per minute for paid use. Meta's public landing page confirms the $20 credit but does not characterize it as a permanent free tier. It also does not publicly list batch discounts or a capacity reservation program.[2][6]

The cached-token, search, and rate-limit figures come from current open-source integration documentation rather than an accessible public Meta pricing contract. They may change during the preview, so production users need to confirm the values shown in their Meta developer account.[6]

## Data handling and privacy

At the July 2026 launch, the accessible Meta pages did not state whether routine API prompts and responses were retained, used to train models, used for advertising, stored in a particular region, or deleted after a fixed period. The signed-in terms therefore matter for applications handling confidential, personal, or regulated information.

Since the August 2026 release of the Contributor tier, Meta's developer pages have drawn the training-use distinction explicitly: the standard `muse-spark` models are labeled "Not used to improve our products" and the `-contributor` variants "Used to improve our products."[13][20] Those labels cover training use; retention periods, storage regions, and the other terms remain in the signed-in documentation.

This gap should not be filled with the earlier Llama API policy. In 2025, Meta explicitly said it would not use prompts or model responses from that limited preview to train models. No accessible Model API source identified for the July 2026 launch restates that commitment, so it cannot be assumed to carry over.[8]

Meta's Muse Spark evaluation report does disclose a narrower safety practice: safeguards may aggregate and analyze longer-term activity patterns to identify persistent malicious use. That statement concerns abuse detection and is not a complete retention, training, or privacy policy.[3]

## Safety and acceptable use

Meta evaluated Muse Spark 1.1 under its Advanced AI Scaling Framework in Chemical and Biological, Cybersecurity, and Loss of Control risk domains. The report describes unmitigated high or possible-high capability findings in some tests. Meta says layered mitigations reduce the remaining risk to moderate or lower under its own framework.[3]

The deployed system combines refusal behavior, prompt-injection testing, abuse monitoring, and system-level safeguards. Meta reports testing direct jailbreaks, attacks hidden in untrusted tool data, and attempts to override developer instructions. The report refers to an API content-safety policy, but the complete current acceptable-use terms are not reproduced in the public report.[1][3]

Meta also assigns responsibility to application developers. Its report recommends strict tool allowlists, isolated workspaces, and system-level controls suited to the deployment. These controls are especially important for [AI agents](https://aiwiki.ai/wiki/ai_agents) that can execute code or act on external services, because a capable model-level defense does not eliminate application permissions, data-exfiltration, or [prompt-injection](https://aiwiki.ai/wiki/prompt_injection) risks.[3]

The safety findings are Meta's pre-deployment assessment, not an independent certification. The report exposes useful methods and results, but it does not show that every third-party agent configuration is safe or that all harmful uses will be detected.[3]

## Relationship to Meta AI and Llama API

Muse Spark 1.1 is the model, while Meta Model API is the hosted developer service. The same model appears in Thinking mode in Meta AI, where Meta controls the consumer interface and system scaffolding. A developer using the API supplies a different prompt, tool set, permission model, and application context, which can change both capability and risk.[1][3]

The Model API is also not simply a new name for the Llama API. Meta announced the Llama API in 2025 as a limited preview for Llama 4 Scout and Maverick, with Python and TypeScript SDKs, evaluation and fine-tuning experiments, and a path to export tuned weights. Current Promptfoo documentation says that preview was retired on July 6, 2026, three days before the Model API launch.[6][8]

The replacement-era service begins with a closed Muse model and usage-based pricing. It offers no public weight export or fine-tuning path. Developers seeking open-weight deployment therefore still need the Llama ecosystem or another model host, while those using Meta Model API depend on Meta's endpoint, preview availability, and evolving service terms.[1][2][6]

## Limitations

As a public preview, Meta Model API had a narrow launch region and one publicly documented model (by September 2026 its developer pages listed four model identifiers across Muse Spark 1.2 and 1.3 and access had been widened beyond the United States), and it still has no announced stability guarantee and no public general-availability schedule.[9][13] The detailed reference, terms, and account-specific limits sit behind sign-in, leaving important data-handling and enterprise-operational questions unanswered on the open web.[2][6]

The published one-million-token context window does not guarantee that every request can use the full amount with every tool or attachment, and active compaction may summarize earlier material. Likewise, model support for MCP, computer use, and subagents depends on developer-supplied infrastructure. These are capabilities for building an agent system, not a hosted promise that the API will safely operate arbitrary software by itself.[1][4]

Muse Spark 1.1's weights, architecture, training data, and parameter count remain undisclosed. Meta's benchmark and safety results are vendor-reported, and present audio support is unclear across public sources. The service is therefore usable as a documented preview, but its compatibility, policies, limits, and model roster should be treated as changeable until Meta publishes a stable general-availability contract.[1][2][3][6]

## References

1. Meta Superintelligence Labs. [Introducing Muse Spark 1.1](https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/). Meta AI, July 9, 2026.
2. Meta. [Muse Spark on Meta Model API](https://developer.meta.com/ai/). Meta for Developers. Accessed July 24, 2026.
3. Meta Superintelligence Labs. [Muse Spark 1.1 Evaluation Report](https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report). July 9, 2026.
4. Meta. [Build with Muse Spark, now available on Meta Model API](https://developer.meta.com/ai/resources/blog/build-with-muse-spark/). Meta for Developers, July 2026.
5. Mukherjee, Supantha. [Meta debuts Muse Spark 1.1 with preview open to developers](https://www.investing.com/news/stock-market-news/meta-debuts-muse-spark-11-with-preview-open-to-developers-4784384). Reuters, July 9, 2026.
6. Promptfoo. [Meta Model API provider](https://www.promptfoo.dev/docs/providers/meta/). Updated July 18, 2026.
7. OpenClaw. [Meta Model API](https://docs.openclaw.ai/providers/meta). Accessed July 24, 2026.
8. Meta. [The Llama Ecosystem: Past, Present, and Future](https://ai.meta.com/blog/llamacon-llama-news/). Meta AI, April 29, 2025.
9. Meta Superintelligence Labs. [Introducing Muse Code and Muse Spark 1.2](https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2). Meta AI Research, August 5, 2026.
10. Vanian, Jonathan. [Meta debuts first AI coding agent to take on Anthropic and OpenAI](https://www.cnbc.com/2026/08/05/meta-debuts-muse-code-to-take-on-anthropic-and-openai-.html). CNBC, August 5, 2026.
11. Clover, Juli. [Meta's New Mac Coding Agent Costs Up to 20x Less If You Let Meta Train on Your Data](https://www.macrumors.com/2026/08/05/meta-muse-code-for-mac/). MacRumors, August 5, 2026.
12. Meta Superintelligence Labs. [Introducing Muse Spark 1.3](https://research.meta.ai/blog/introducing-muse-spark-1-3). Meta AI Research, September 2, 2026; availability line updated in place by September 5, 2026.
13. Meta. [Muse Spark 1.3](https://web.archive.org/web/20260903083136/https://developer.meta.com/ai/models/muse-spark/). Meta for Developers, as archived by the Internet Archive on September 3, 2026.
14. Kasanmascheff, Markus. [Meta Releases Muse Spark 1.3 Model for Longer Tool-Based Work](https://winbuzzer.com/2026/09/04/meta-releases-muse-spark-1-3-model-longer-tool-based-work-xcxwbn/). Winbuzzer, September 4, 2026.
15. Abdullahi, Aminu. [Meta Says Muse Spark 1.3 Beats GPT-5.6 Sol at Coding: Independent Tests Are More Mixed](https://www.techrepublic.com/article/news-meta-muse-spark-1-3-ai-coding-2026/). TechRepublic, September 4, 2026.
16. Wang, Alexandr (@alexandr_wang). [1/ we just publicly released Muse Spark 1.3 max!](https://x.com/alexandr_wang/status/2095938990197329935). X, September 4, 2026.
17. Meta Superintelligence Labs. [Introducing Muse Spark 1.3, Internet Archive snapshot of September 2, 2026 (19:37 UTC)](https://web.archive.org/web/20260902193756/https://research.meta.ai/blog/introducing-muse-spark-1-3). Meta AI Research, September 2, 2026.
18. Meta for Developers (@MetaforDevs). [Muse Spark 1.3 with max reasoning is now available on Muse Code and Meta Model API](https://x.com/MetaforDevs/status/2095939388559720720). X, September 4, 2026.
19. Moses, Randa. [Meta cuts Muse Spark prices up to 21x for developers who hand over their prompts](https://www.cryptopolitan.com/meta-cuts-muse-spark-prices-21x/). Cryptopolitan, September 3, 2026.
20. Meta. [Muse Code](https://web.archive.org/web/20260904172529/https://developer.meta.com/ai/products/muse-code/). Meta for Developers, as archived by the Internet Archive on September 4, 2026.