Pricing
| Provider | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|
| Particle AI | $0.2125 | $0.0255 | $0.85 |
USD, as of October 29, 2026. Live prices
Particle-1 API
- 1.05MContext
- 131KMax output
- $0.2125/ $0.85From, per 1M in / out
- 1Provider
Providers
Cost
| Workload | Particle AI |
|---|---|
| 1,000 chat replies2K in, 500 out each | $0.85 |
| 1,000 agent tasks50K in, 5K out each | $14.88 |
| Monthly batch job500M in, 50M out | $148.75 |
Quickstart
curl https://api.routerplus.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "particle-ai/particle-1",
"messages": [{ "role": "user", "content": "Hello" }]
}'FAQ
How much does the Particle-1 API cost?
On RouterPlus, Particle-1 costs $0.2125 per million input tokens and $0.85 per million output tokens at Particle AI, the lowest listed prices and the provider where routing starts. Prices as of October 29, 2026.
Which providers serve Particle-1?
Particle AI serves Particle-1 on RouterPlus today.
What is the Particle-1 model ID?
Use "particle-ai/particle-1" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.
What is the Particle-1 context window?
1.05M tokens of context and up to 131K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.
Do any Particle-1 providers retain prompts?
None of the 1 providers serving Particle-1 on RouterPlus list prompt retention.
Can I reserve capacity for Particle-1?
Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.