中文
AI tools

Coding & apps

Particle AI

Particle AI provides a developer inference API. You can call Particle-1, as well as open-weight models such as DeepSeek V4.1 Flash and GLM 5.3 Flash, through an OpenAI-compatible interface.

Visit website

Offers

Particle-1 is free on OpenRouter and Kilo Code

Particle-1 is free for a limited time on OpenRouter and Kilo Code, with about 1 million tokens of context

Eligibility
An OpenRouter or Kilo Code account can call the matching free route. The free routes are rate-limited, and prompts and outputs may be used to improve the model.
Benefit duration
Free for a limited time; no end date has been announced
Claim offerSourceRead details

What you can do

Developers who want an OpenAI-compatible API to use Particle-1 and other open-weight models in apps or coding agents.

Get started

Open https://platform.particle.ai/, sign in with Google, and create a key under API keys. The raw key starts with pai- and is shown once at creation, so save it immediately. Before you send inference requests, add Credits under Billing. Unless your key already has free access, the account needs a positive Credits balance. Set the base URL to https://api.particle.ai/v1 and send your key as a Bearer token to call /v1/chat/completions. For a first integration, use Particle-1: send particle-1 as the model name; the public ID returned in responses is particle-ai/particle-1. Particle-1 is Particle AI's model post-trained on DeepSeek V4.1 Flash, with a 1,048,576-token context window, and is intended for chat, agentic coding, and tool calling. The listed prices are $0.25 input, $0.03 cached input, and $1.00 output per million tokens. The same API also serves DeepSeek V4.1 Flash and GLM 5.3 Flash; the model catalog lists the models you can call. See https://docs.particle.ai/quickstart for the full setup guide.

Sources