UberLLM lets you call GPT models at pass-through provider pricing (no inference markup), or drop to much cheaper open-weight models by changing the model id — all with the OpenAI SDK and one key. UberLLM gives you one OpenAI-compatible API key and base URL for 380+ models, routing each request to the cheapest healthy provider with no inference markup and free starter credits.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| GPT Image 1.5 (Venice) | $0.0000 | $0.0000 |
| GPT Image 2 (Venice) | $0.0000 | $0.0000 |
| GPT Image 2 — Edit (Venice) | $0.0000 | $0.0000 |
| GPT Image 1.5 — Edit (Venice) | $0.0000 | $0.0000 |
| Sora 2 (image-to-video) | $0.0000 | $0.0000 |
| Sora 2 Pro (image-to-video) | $0.0000 | $0.0000 |
| GPT-5.4 Mini | $0.0100 | $0.0500 |
| GPT-OSS 120B | $0.0100 | $0.0600 |
| GPT-OSS 20B | $0.0300 | $0.1300 |
| GPT-5.4 | $0.0300 | $0.1500 |
| GPT-5.6 Terra | $0.0300 | $0.1500 |
| GPT-4o Mini | $0.0400 | $0.1500 |
Live prices via UberLLM · full pricing table →
UberLLM charges GPT at pass-through pricing and makes it trivial to switch to cheaper models (DeepSeek, GLM, Qwen) for cost-sensitive workloads — same SDK, one key.