This is the 400B class of Llama3, with a 128k context window. This 405B instruct-tuned version is optimized for high-quality dialogue and demonstrates strong performance compared to leading closed-source models, including GPT-4o and Claude 3.5 Sonnet.
$1.50
$1.50
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.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Daily usage of this model on NagaAI.
This is the 400B class of Llama3, with a 128k context window. This 405B instruct-tuned version is optimized for high-quality dialogue and demonstrates strong performance compared to leading closed-source models, including GPT-4o and Claude 3.5 Sonnet.
On NagaAI, Llama 3.1 405B Instruct costs $1.50 per 1M input tokens and $1.50 per 1M output tokens. You pay only for what you use, with no subscription.
Llama 3.1 405B Instruct reads up to 131k tokens in one request, counting the prompt and the answer together.
Yes. Llama 3.1 405B 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 WonderMeta LlamaMuse Spark OpenMeta LlamaMuse Glimmer 30BMeta LlamaLlama 3.2 11B Vision InstructMeta Llama$0.10 / $0.10 per 1MLlama 4 Scout 17B 16E InstructMeta Llama$0.24 / $0.96 per 1MLlama 3.2 3B InstructMeta LlamaNot enough throughput data
Not enough TTFT data