Particle-1

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.

ChatParticle Ai1M tokens$0.2725 / $1.0901 · 1M

particle-ai/particle-1

Context
1M tokens
Completion cap
131,072
Tools
Yes
JSON
Yes
Released
2026-10-28

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "particle-ai/particle-1",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Particle-1?
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. Particle-1 runs on the Geek Hub API (OpenAI-compatible). Model id: particle-ai/particle-1.
Is Particle-1 free?
No. Input is $0.2725 per 1M tokens and output is $1.0901 per 1M tokens on Geek Hub (markup included).
What is the context length of Particle-1?
Particle-1 has a 1M tokens context window. It supports up to 131,072 completion tokens.
Does Particle-1 support tool calling and structured outputs?
Particle-1 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Particle-1 released?
Particle-1 was released on 2026-10-28.