# Particle AI models

[Get API key](https://vercel.com/d?to=%2F%5Bteam%5D%2F~%2Fai-gateway%3FshowCreateKeyModal%26utm_source%3Dgateway-providers-page%26utm_campaign%3Dai-gateway-providers&title=Get%20API%20key) [Read the docs](https://vercel.com/docs/ai-gateway)

Particle AI is an AI infrastructure company working to make intelligence as affordable, abundant, and accessible as electricity. By focusing on post-training, inference optimization, and scalable distributed systems, Particle aims to radically reduce the cost of running powerful AI models as demand for compute continues to grow.

| Model | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | ZDR | No Training | Regional Inference | Free Tier | Released |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |

| [zai/glm-5.3-flash](/ai-gateway/models/glm-5.3-flash) | 1M | 0.7 s | 7 tps | $0.15/M | $0.50/M | Read:$0.03/M Write:— | — | +1 |  |  |  |  | 08/26/2026 |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [deepseek/deepseek-v4-flash-0731](/ai-gateway/models/deepseek-v4-flash-0731) | 1M | 0.6 s | 160 tps | $0.14/M | $0.28/M | Read:$0.03/M Write:— | — |  |  |  |  |  | 07/31/2026 |  |