Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data engineering tasks, and is trained to complete them with substantially fewer reasoning and tool-call tokens while keeping accuracy close to its base model.
Free
Free calls share a limit of 10 requests a minute and 100 a day across all free models. The paid version has no per-minute limit.
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.
Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash.
Particle-1 is free on NagaAI: a free account calls it without topping up, up to 10 requests a minute and 100 a day across all free models.
Particle-1 reads up to 1.0M tokens in one request, counting the prompt and the answer together.
Yes. Particle-1 can call your functions as tools and can answer in a JSON schema you give 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.
Gemini 4 HydrogenGoogle$0.375 / $1.88 per 1M
ERNIE-5.5-Flash-PreviewBaidu$0.14 / $0.565 per 1MERNIE-Light-DT-1.0BaiduGemini 4 CarbonGoogle
Nex-N2.6Nex AGI
Claude Fable 5.2Anthropic