Catalogue
Every model we serve, and what it costs
Open LLMs serves 5 open-source models through one OpenAI-compatible API, billed per model in that model's own unit from prepaid wallet credits.
Prices and specifications are read from the live catalogue on every request.
Each model is billed in the unit that matches what it does: chat and vision models per million tokens, speech-to-text per minute of audio, video per second of output. The rate in the table is the rate you are charged.
Which models can I call?
Every row is a model you can name in a request today. Follow a model for its endpoint, a working request, and its licence.
| Row label | Task | Context | Price | Licence |
|---|---|---|---|---|
| GLM-4.5-Air | Chat | 33K tokens | $1.50 / 1M tokens | MIT |
| Wan2.1-VACE Video | Video | — | $50.00 / 1M tokens | apache-2.0 |
| Qwen-3.5 | Vision | 33K tokens | $0.15 / 1M tokens | — |
| Whisper Large v3 | Speech to text | — | $0.004 / minute | MIT |
| Qwen-2.5 | Chat | 33K tokens | $0.15 / 1M tokens | Apache-2.0 |
How do two of these compare?
Each pair, side by side, from the same catalogue.