The AI arena is free today

Open Superagent
API Provider3 active models1 organization

Meta Model API: API pricing, speed & models

Meta Model API hosts 3 active AI models, with input pricing from $0.10 per 1M tokens, with median throughput of 33 characters/sec, and P95 time to first token of 7.62s, with 99.6% success rate over 7 days. Compare Meta Model API's API speed, pricing, and reliability against other inference providers.

First-party only
Median throughput33 c/s
Median TTFT1.94s
P95 TTFT7.62s
Success rate (7d)99.6%
From$0.10 /M tok

Catalog

Type
Price
10 models
Model
Muse Spark 1.3cache pricing
Muse Spark 1.3cache pricing
Muse Spark 1.3cache pricing
Muse Spark 1.3cache pricing
Muse Spark 1.2cache pricing
Muse Spark 1.2cache pricing
Muse Spark 1.2cache pricing
Muse Spark 1.1cache pricing
Muse Spark 1.1cache pricing
Muse Spark 1.1cache pricing
At a glance

Meta Model APIpricing, performance & catalog

The citable facts about Meta Model API's 3 models — sourced from provider APIs and refreshed continuously.

Lowest price
Muse Spark 1.3 at $0.100 per 1M input tokens
Highest median throughput
Muse Spark 1.2 at 70 chars/s
Lowest median TTFT
Muse Spark 1.1 at 1.11s
Largest context
Muse Spark 1.3 at 1.0M tokens
Catalog
3 active models from 1 organization

FAQ

Common questions about Meta Model API.

What is Meta Model API?

Meta Model API is an API provider that hosts large language models. Active models: 3; From (input): $0.10 / 1M tok; Median throughput: 33 c/s; Median TTFT: 1.94s; Success rate (7d): 99.6%.

How many models does Meta Model API offer?

Meta Model API currently serves 3 active models out of 3 historical offerings on LLM Stats.

What is Meta Model API's API pricing?

Meta Model API input pricing starts from $0.10 per 1M tokens, with the most expensive offering at $1.25 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

How fast is Meta Model API?

Meta Model API delivers a median throughput of 33 characters per second and P95 time to first token of 7.62s across its model catalog. See the Models tab for per-model throughput and TTFT breakdowns.

Is Meta Model API reliable?

Meta Model API has a 99.6% success rate across 551 API calls in the last 7 days, with a 0.4% error rate.

Does Meta Model API support function calling?

Yes. 10 of 3 models on Meta Model API support function calling (tool use). The Capabilities tab lists which specific models accept tool definitions.

Does Meta Model API support JSON mode and structured output?

Yes. 10 of 3 models on Meta Model API support structured output (JSON mode / schema-constrained generation). The Capabilities tab shows which specific models accept response_format or json_schema parameters.

Does Meta Model API support multimodal models?

Yes. Meta Model API's catalog includes 3 vision-capable models. See the Models and Capabilities tabs for the full per-model breakdown.

Whose models does Meta Model API host?

Meta Model API hosts models from Meta. See the Models tab for the full catalog grouped by creator.

How do I start using Meta Model API?

Sign up at https://ai.meta.com/ to get an API key, then call Meta Model API's API directly from your application. Most clients work out of the box by pointing the OpenAI SDK at Meta Model API's base URL with your key. Use the Models and Pricing tabs above to pick the right model for your latency, cost, and context-window requirements.