With UberLLM you use one API key for all LLMs. Instead of separate OpenAI, Anthropic, Google and DeepSeek accounts and keys, you get a single OpenAI-compatible key and base URL that reaches every model in the catalog, with automatic routing to the cheapest healthy seller. Prices shown include UberLLM's 10% fee.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| JEV 1.13 (TypeSafe) | $0.0005 | $0.0000 |
| Qwen: Qwen3.8 Omni Flash | $0.0002 | $0.0005 |
| Gemma 3 4B IT | $0.0005 | $0.0007 |
| GPT-OSS 20B | $0.0002 | $0.0009 |
| DeepSeek V4.1 Flash | $0.0002 | $0.0009 |
| Ministral 3B | $0.0011 | $0.0011 |
| MiniMax M2.1 | $0.0004 | $0.0016 |
| Gemma 4 26B A4B IT | $0.0005 | $0.0016 |
| Gemma 3 12B IT | $0.0005 | $0.0016 |
| DeepSeek V4 Flash 0731 | $0.0010 | $0.0020 |
| GLM 4.7 Flash | $0.0003 | $0.0022 |
| Gemma 3 27B | $0.0009 | $0.0022 |
Live prices via UberLLM · full pricing table →
Sign up for UberLLM, set the base URL to the UberLLM endpoint, and switch models by changing the model id string. One key covers every model.
The marketplace matches a fresh seller on every call. If a call fails before any output starts, UberLLM retries it automatically (with short backoff) and you are not charged for the failed attempt.