Meta’s Llama 3.1 8B instruct-tuned model, designed for fast and efficient dialogue. It performs strongly in human evaluations and is ideal for applications requiring a balance of speed and quality.
$0.01market price $0.02
$0.01market price $0.02
$0.02market price $0.04
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Not enough throughput data
Not enough TTFT data
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
Meta’s Llama 3.1 8B instruct-tuned model, designed for fast and efficient dialogue. It performs strongly in human evaluations and is ideal for applications requiring a balance of speed and quality.
On NagaAI, Llama 3.1 8B Instruct costs $0.01 per 1M input tokens and $0.02 per 1M output tokens. You pay only for what you use, with no subscription.
Llama 3.1 8B Instruct reads up to 16.4k tokens in one request, counting the prompt and the answer together.
Yes. Llama 3.1 8B Instruct can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Muse Spark OpenMeta LlamaMuse WonderMeta LlamaMuse Spark 1.3 ContributorMeta Llama$0.05 / $0.10 per 1MMuse Spark 1.3Meta Llama$0.625 / $2.13 per 1MMuse Spark 1.2 ContributorMeta Llama$0.05 / $0.10 per 1MMuse Glimmer 30BMeta Llama