Particle AI
Particle-1
Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash.
At a glance
- Input / 1M
- $0.07
- Output / 1M
- $0.50
- Context
- 1.05M
- Max output
- 131K
- Intelligence
- Not available
- Released
- Oct 2026
Pricing
Particle-1 API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.07 |
|---|---|
| Output tokensPer 1M tokens | $0.50 |
| Cached input (read)Per 1M tokens | $0.03 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.39
per 1,000 requests
Coding task
30K in, 4K out
$4.10
per 1,000 requests
Long document summary
150K in, 2K out
$11.50
per 1,000 requests
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 1.05M tokens
- Max output
- 131K tokens
- Input types
- Image, Text
- Output types
- Text
- Reasoning effort
- Max, Extra high, High, Medium, Low, Minimal, None
- Release date
- October 28, 2026
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Particle-1 vs other models
See how Particle-1 stacks up head to head on price, benchmarks, and features.
Particle-1 vs Hy4 flash
Particle AI vs Tencent
See comparisonParticle-1 vs DeepSeek V4.1 Flash 1017
Particle AI vs DeepSeek
See comparisonParticle-1 vs DeepSeek V4.1 Flash
Particle AI vs DeepSeek
See comparisonParticle-1 vs GPT-6 Luna
Particle AI vs OpenAI
See comparisonParticle-1 vs Hy4
Particle AI vs Tencent
See comparisonParticle-1 vs MiniMax M3.1 Flash
Particle AI vs MiniMax
See comparisonAlternatives
Particle-1 alternatives
Similar models worth considering, and where each one has the edge.
Anthropic
Claude Haiku 5.5
Meta
Muse Ember
Tencent
Hy4
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Particle-1 cost?
Particle-1 costs $0.07 per 1M input tokens and $0.50 per 1M output tokens through the API. A typical chat message costs about $0.39 per 1,000 messages.
What is the context window of Particle-1?
Particle-1 accepts up to 1.05M tokens of input and can write up to 131K tokens in a single response.
What is the best alternative to Particle-1?
Claude Haiku 5.5 from Anthropic is a strong alternative. It offers: accepts file.
Can I use Particle-1 alongside other models?
Yes. Shortcut Chat sends one prompt to Particle-1 and any other models you pick at the same time, so you can compare answers side by side.
Try Particle-1 next to every other model.
Use Particle-1 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.