Pendra is a third-party gateway that routes to many upstream models through one API. Gateway quotes are often among the lowest on the site, but availability, rate limits and routing can vary between models, so a low headline price is worth verifying against your own workload.
It lists 6 models on this page. 6 are offered at $0. Coverage spans text and chat (6). The lowest-priced model hosted here is DeepSeek V4 Flash.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| DeepSeek V4 Flashdeepseek-v4-flash | Free | — | 1,000,000 | — | |
| GPT OSS 120Bgpt-oss:120b | Free | — | 131,072 | — | |
| Llama-3.3-70B-Instructllama3.3:70b | Free | — | 128,000 | — | |
| Qwen3.6 27Bqwen3.6:27b | Free | — | 262,144 | — | |
| GLM-4.7-Flashglm-4.7-flash | Free | — | 200,000 | — | |
| Qwen3-Coder 30B-A3B Instructqwen3-coder:30b | Free | — | 262,144 | — |