Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the next Pareto version and may change without notice; use pareto-26.9 for stable behaviour.
$0.40
$0.015
$1.60
How fast the model answers over every route we serve it from: throughput is tokens written per second, time to first token is how soon the answer starts, end-to-end latency is the whole request.
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.
Tokens processed per day on NagaAI.
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the next Pareto version and may change without notice; use pareto-26.9 for stable behaviour.
On NagaAI, Pareto 26.10 Preview costs $0.40 per 1M input tokens and $1.60 per 1M output tokens. You pay only for what you use, with no subscription.
Pareto 26.10 Preview reads up to 1.0M tokens in one request, counting the prompt and the answer together.
Pareto 26.10 Preview can call your functions as tools. Answers in a JSON schema are not available for it.
It takes text and images 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.
Pareto 26.10UnbiasedPareto 26.9Unbiased
ERNIE-5.5-Flash-PreviewBaidu$0.14 / $0.565 per 1MERNIE-Light-DT-1.0Baidu
Gemini 4 CarbonGoogle
Nex-N2.6Nex AGINot enough activity data to display a chart
Not enough data yet
Not enough data yet
Not enough data yet