Skip to content
ShilpBot
AI Models

Particle AI Particle-1 (Free): Specs, Limits and How to Use It

Particle AI Particle-1 free: agentic coding model post-trained on DeepSeek V4.1 Flash, text/image input, 1M context. Specs, limits, test prompts and how...

By ShilpBot Team · Published · 3 min read

Particle-1 is described as a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. The listing says it is suited to software engineering work such as terminal workflows and codebase changes.

"Token-efficient" matters for agents because they re-send context on every step. A model that reaches an answer in fewer tokens finishes sooner and costs less on the paid tier, so it is worth comparing on a real task rather than a single prompt.

Specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

Particle AI Particle-1 quick facts

DetailValue
DeveloperParticle AI
Model IDparticle-ai/particle-1:free
Added to the catalogue2026-10-28
TypeAgentic coding model post-trained on DeepSeek V4.1 Flash
ParametersNot listed
Context windowabout 1M tokens (1,048,576)
Maximum output131,072 tokens
Input typestext, image
PriceFree (paid listing: $0.060 in / $0.50 out per 1M tokens)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.

What Particle AI Particle-1 is good for

  • Agent loops in a coding tool, where the model reads files, runs commands and edits code.
  • Making a contained change across several files with a clear instruction.
  • Screenshot-based debugging, since image input is listed.

Limits of Particle AI Particle-1

  • Agentic coding can make unrequested edits. Review diffs and keep changes in version control.
  • Never paste secrets or private keys into a free endpoint, because prompts may be logged.
  • Measure it on your own repository. Marketing language about efficiency is not a substitute for a trial.

How Particle AI Particle-1 compares

  • Cohere North Mini Code: It has a larger context window (1,048,576 against 256,000 tokens); its output cap is 131,072 tokens against 64,000; it also accepts image input.
  • Recursive Flint: It has a larger context window (1,048,576 against 262,144 tokens); its output cap is 131,072 tokens against 235,929; it also accepts image input.
  • NVIDIA Nemotron 3 Ultra: It has a larger context window (1,048,576 against 1,000,000 tokens); its output cap is 131,072 tokens against 65,536; it also accepts image input.

Calling Particle AI Particle-1 from code

Use the model ID particle-ai/particle-1:free with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "particle-ai/particle-1:free", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what Particle AI Particle-1 can do

  1. Give it a failing test and the relevant file, and ask for the smallest fix with an explanation.
  2. Ask it to find where a configuration value is read in a small project and list every place it is used.
  3. Run the same task with this model and a second model, and compare the number of steps and the final diff.

What Particle AI Particle-1 costs

The free listing costs nothing, but the same model also has a paid listing at about $0.060 per million input tokens and $0.50 per million output tokens. As a rough guide, sending 1 million input tokens and receiving 100,000 output tokens would cost about $0.11 on the paid listing. Use the free tier to test, and move to the paid route if you need steadier availability. Free pricing is set by the provider and can change at any time, so check the model page before you plan around it.

Keep reading

All free models are compared in our free AI chat models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

What is Particle-1 based on?

The listing says it is post-trained on DeepSeek V4.1 Flash and tuned for agentic coding work.

Is a paid version available?

Yes, at about $0.06 per million input tokens and $0.50 per million output tokens per the catalogue.

Is Particle AI Particle-1 free, and what are its limits?

As of 2026-11-16 the catalogue lists it at zero price. About 1M tokens (1,048,576) context window, up to 131,072 output tokens, model ID particle-ai/particle-1:free. Free use can be rate limited and providers may change it.

#Particle AI Particle-1#Particle AI free model#free AI model#AI chat model#AI coding model#Kilo Gateway#OpenRouter