# Meta models

Canonical HTML page: [Meta models](<https://impossibl.com/meta>)
Markdown alternative: [Meta models as Markdown](<https://impossibl.com/meta.md>)

Access 4 models from Meta through the Impossibl API, including Llama 3.3 70B Instruct, Muse Glimmer 30B, and Muse Spark 1.3. Compare API pricing, context windows, and capabilities.

Select two or three models to [compare specifications and API costs](<https://impossibl.com/compare.md>). Model types and billing units are not interchangeable.

## Models

### [Llama 3.3 70B Instruct](<https://impossibl.com/meta/llama-3.3-70b>)

Llama 3.3 70B Instruct is a text generation model from Meta, available through the Impossibl API. Its published context window is 128,000 tokens. The advertised input rate is $0.71 per million input tokens. The advertised output rate is $0.71 per million output tokens.

- API identifier: `meta/llama-3.3-70b`
- Creator: Meta; model type: Text generation.
- Context window: 128,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.71 per million input tokens; $0.71 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/meta/llama-3.3-70b.md>)

### [Muse Glimmer 30B](<https://impossibl.com/meta/muse-glimmer-30b>)

Muse Glimmer 30B is a text generation model from Meta, available through the Impossibl API. Its published context window is 131,072 tokens. The advertised input rate is $0.35 per million input tokens. The advertised output rate is $1.50 per million output tokens.

- API identifier: `meta/muse-glimmer-30b`
- Creator: Meta; model type: Text generation.
- Context window: 131,072 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.35 per million input tokens; $1.50 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/meta/muse-glimmer-30b.md>)

### [Muse Spark 1.3](<https://impossibl.com/meta/muse-spark-1.3>)

Muse Spark 1.3 is a text generation model from Meta, available through the Impossibl API. Its published context window is 1,048,576 tokens. The advertised input rate is $1.25 per million input tokens. The advertised output rate is $4.25 per million output tokens.

- API identifier: `meta/muse-spark-1.3`
- Creator: Meta; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $1.25 per million input tokens; $4.25 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/meta/muse-spark-1.3.md>)

### [Muse Spark 1.3 (Contributor)](<https://impossibl.com/meta/muse-spark-1.3-contributor>)

Muse Spark 1.3 (Contributor) is a text generation model from Meta, available through the Impossibl API. Its published context window is 1,048,576 tokens. The advertised input rate is $0.10 per million input tokens. The advertised output rate is $0.20 per million output tokens.

- API identifier: `meta/muse-spark-1.3-contributor`
- Creator: Meta; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.10 per million input tokens; $0.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/meta/muse-spark-1.3-contributor.md>)

## Compare Meta models

- [Llama 3.3 70B Instruct vs Muse Glimmer 30B](<https://impossibl.com/compare/meta/llama-3.3-70b/meta/muse-glimmer-30b>); [Markdown comparison](<https://impossibl.com/compare/meta/llama-3.3-70b/meta/muse-glimmer-30b.md>)
- [Llama 3.3 70B Instruct vs Muse Spark 1.3](<https://impossibl.com/compare/meta/llama-3.3-70b/meta/muse-spark-1.3>); [Markdown comparison](<https://impossibl.com/compare/meta/llama-3.3-70b/meta/muse-spark-1.3.md>)
- [Llama 3.3 70B Instruct vs Muse Spark 1.3 (Contributor)](<https://impossibl.com/compare/meta/llama-3.3-70b/meta/muse-spark-1.3-contributor>); [Markdown comparison](<https://impossibl.com/compare/meta/llama-3.3-70b/meta/muse-spark-1.3-contributor.md>)
- [Muse Glimmer 30B vs Muse Spark 1.3](<https://impossibl.com/compare/meta/muse-glimmer-30b/meta/muse-spark-1.3>); [Markdown comparison](<https://impossibl.com/compare/meta/muse-glimmer-30b/meta/muse-spark-1.3.md>)
- [Muse Glimmer 30B vs Muse Spark 1.3 (Contributor)](<https://impossibl.com/compare/meta/muse-glimmer-30b/meta/muse-spark-1.3-contributor>); [Markdown comparison](<https://impossibl.com/compare/meta/muse-glimmer-30b/meta/muse-spark-1.3-contributor.md>)
- [Muse Spark 1.3 vs Muse Spark 1.3 (Contributor)](<https://impossibl.com/compare/meta/muse-spark-1.3/meta/muse-spark-1.3-contributor>); [Markdown comparison](<https://impossibl.com/compare/meta/muse-spark-1.3/meta/muse-spark-1.3-contributor.md>)

## Frequently asked questions

### Which Meta models are available through Impossibl?

The directory lists 4 models from Meta available through the Impossibl API, including Llama 3.3 70B Instruct, Muse Glimmer 30B, and Muse Spark 1.3. Open each model page for its API identifier, capabilities, and current pricing.

### How much do Meta models cost?

Meta model prices vary by model and usage. All rates below are published base API rates in USD. For token-priced models, published input rates start at $0.10 per million input tokens. Published output rates start at $0.20 per million output tokens. Input and output minima may refer to different models. Individual model pages include published cache prices and billing units. Applicable fees and workspace-specific pricing can affect the amount paid.

### What context windows do Meta models support?

Among Meta models with a published limit on Impossibl, the largest context window is 1,048,576 tokens, listed for Muse Spark 1.3 and Muse Spark 1.3 (Contributor). Context limits vary by model and are separate from maximum output limits.

### What inputs and capabilities do Meta models support?

Available model types include text generation. Published input support includes image and text; support varies by model. Tool-calling support is unspecified for 4 models.

### How do I use Meta models through an API?

Use the exact model identifier from the model page with the Impossibl API. For example, select meta/llama-3.3-70b with /v1/chat/completions. Endpoint compatibility depends on the selected model. The API quickstart explains how to create an API key and send a request.

## Sources and related links

Prices, capabilities, limits, and availability describe the public Impossibl API offering. An unpublished fact is unknown; a published zero price is zero. Compare matching billing units and check context tiers before estimating costs.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Model directory as Markdown](<https://impossibl.com/models.md>)
- [API quickstart](<https://impossibl.com/docs/agent-quickstart>)
- [Model documentation](<https://impossibl.com/docs/models>)