The cheapest LLM API is the one that always routes you to the lowest-cost healthy provider. UberLLM does exactly that across 380+ models: small open-weight models like DeepSeek, GLM and Qwen cost only a few cents per million tokens, and you reach all of them — plus GPT, Claude and Gemini — through a single OpenAI-compatible key with no inference markup. New accounts get free credits to start.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Tencent HY3 (Free) | $0.0000 | $0.0000 |
| Seedream 4.5 | $0.0000 | $0.0000 |
| FLUX.2 Flex | $0.0000 | $0.0000 |
| FLUX.2 Klein 4B | $0.0000 | $0.0000 |
| Z-Image Turbo (Venice) | $0.0000 | $0.0000 |
| Venice SD35 | $0.0000 | $0.0000 |
| Flux 2 Pro (Venice) | $0.0000 | $0.0000 |
| Flux 2 Max (Venice) | $0.0000 | $0.0000 |
| Grok Imagine (Venice) | $0.0000 | $0.0000 |
| Grok Imagine High Quality (Venice) | $0.0000 | $0.0000 |
| Grok Imagine Pro (Venice) | $0.0000 | $0.0000 |
| GPT Image 1.5 (Venice) | $0.0000 | $0.0000 |
Live prices via UberLLM · full pricing table →
For most workloads, small open-weight models (DeepSeek, GLM-4.x, Qwen) served through UberLLM are the cheapest — often a few cents per million tokens. UberLLM routes to the cheapest healthy provider automatically.
Yes — via UberLLM you can call GPT models at pass-through pricing, or switch to much cheaper open-weight models with one line of code (change the model id). Same OpenAI SDK.