Skip to content

Particle-1 - Free Agentic Coding Model on OpenRouter, 1M Context

Model ID particle-ai/particle-1:free
The :free variant of Particle-1 is completely free: $0/M input tokens, $0/M output tokens.

Model Information

PropertyValue
Context length1,048,576 tokens
Max output131,072 tokens
Input price$0 / 1M tokens
Output price$0 / 1M tokens
ProviderParticle AI
StatusFree
Input modalitiesText + Image

Description

Particle-1 is a highly token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash for software engineering tasks such as terminal workflows, codebase modifications, and data processing. The model supports a 1,048,576-token context, 131,072 tokens of output, and text/image input, making it suitable for multi-step coding agents, repository-wide refactoring, and long-running tasks.

Usage Example

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": "Help me map out the test entry points in this repository"}]
  }'

Notes

  • Free variant: Only versions with the :free suffix are billed at $0; the standard paid version costs about $0.06/$0.50 per 1M tokens, subject to the OpenRouter page
  • Data usage: Prompts and outputs may be retained or used for model improvement
  • Limited-time trial: Free models may become paid at any time, so check regularly

Related Links

📚 Related Free Models

These models are also available for $0 on OpenRouter. Choose by context length and modality.

ModelContextDescription
Ling 3.2 Flash1MLing 3.2 Flash is inclusionAI’s hybrid reasoning model
ERNIE 5.5 Flash1MBaidu’s ERNIE 5.5 Flash Preview free model has 280B
LFM3 1.7B262KLiquid AI’s compact 1.7B text model with 262K context,
Recursive Flint262KRecursive’s 40B total / 2.5B active MoE model built for
Dots3 Note512KDots3-Note Preview is Dots Studio’s MoE model with 280B
Gemma 4 26B A4B - Free MoE Model on262KGemma 4 26B A4B is Google DeepMind’s multimodal MoE model
Gemma 4 31B - Free Multimodal Model on262KGemma 4 31B is Google DeepMind’s 30.7B dense multimodal
Lyria 3 Clip1MGoogle’s music clip generation model produces 30-second

📋 View all OpenRouter free models →

🔗 Site Navigation

Last updated on · Source: OpenRouter official documentation and pricing pages. Quotas and prices may change at any time.