MLX
mlx, the name to use in providers=
- Models offered
- 14
- Billing currency
- USD
- Runs
- on your machine
- Fees
- none
Models
| Model | Model id here | Status | Input per 1M | Output per 1M |
|---|---|---|---|---|
| Gemma 3 12B IT | mlx-community/gemma-3-12b-it-4bit | ga | $0 | $0 |
| Gemma 3 27B IT | mlx-community/gemma-3-27b-it-4bit | ga | $0 | $0 |
| Gemma 3 4B IT | mlx-community/gemma-3-4b-it-4bit | ga | $0 | $0 |
| Gemma 4 31B IT | mlx-community/gemma-4-31b-it-4bit | ga | $0 | $0 |
| GPT OSS 20B | mlx-community/gpt-oss-20b-MXFP4-Q8 | ga | $0 | $0 |
| Llama-3.1-8B-Instruct | mlx-community/Meta-Llama-3.1-8B-Instruct-4bit | ga | $0 | $0 |
| Llama-3.3-70B-Instruct | mlx-community/Llama-3.3-70B-Instruct-4bit | ga | $0 | $0 |
| Qwen 2.5 7B Instruct Turbo | mlx-community/Qwen2.5-7B-Instruct-4bit | ga | $0 | $0 |
| Qwen3 30B-A3B Instruct 2507 | mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit | ga | $0 | $0 |
| Qwen3 32B | mlx-community/Qwen3-32B-4bit | ga | $0 | $0 |
| Qwen3 8B | mlx-community/Qwen3-8B-4bit | ga | $0 | $0 |
| Qwen3 8B | mlx-community/Qwen3-8B-8bit | ga | $0 | $0 |
| Qwen3.5 9B | mlx-community/Qwen3.5-9B-4bit | ga | $0 | $0 |
| Qwen3.6 27B | mlx-community/Qwen3.6-27B-4bit | ga | $0 | $0 |
Built from catalog version 2026-11-04.3 of . Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).