How do I use Particle AI models through the OpenRouter API?

OpenRouter serves 2 Particle AI models behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as particle-ai/particle-1. The quickstart has request examples for every supported SDK.

Which Particle AI models are free on OpenRouter?

Particle-1 (free) is available at no cost through the OpenRouter API.

Which Particle AI model has the largest context window?

Particle-1 has the largest context window of any Particle AI model on OpenRouter, accepting up to 1,048,576 tokens per request.

What is the newest Particle AI model on OpenRouter?

Particle-1 is the most recently added Particle AI model on OpenRouter, listed on October 28, 2026.

Particle AI

Access 2 Particle AI models through the OpenRouter unified API including Particle-1 and Particle-1 (free). Compare pricing, context windows, benchmarks, and capabilities between different Particle AI models.

Particle AI tokens processed on OpenRouter

Particle AI: Particle-1Particle-1
164B tokens
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.
by particle-aiOct 28, 20261.05M context$0.05/M input tokens$0.50/M output tokens
Particle AI: Particle-1 (free)Particle-1 (free)
34.8B tokens
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.
by particle-aiOct 28, 20261.05M context$0/M input tokens$0/M output tokens

Particle AI

Access 2 Particle AI models through the OpenRouter unified API including Particle-1 and Particle-1 (free). Compare pricing, context windows, benchmarks, and capabilities between different Particle AI models.

Particle AI tokens processed on OpenRouter

Particle AI: Particle-1Particle-1
164B tokens
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.
by particle-aiOct 28, 20261.05M context$0.05/M input tokens$0.50/M output tokens
Particle AI: Particle-1 (free)Particle-1 (free)
34.8B tokens
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.
by particle-aiOct 28, 20261.05M context$0/M input tokens$0/M output tokens

Particle AI

Frequently asked questions

Particle AI

Frequently asked questions