darkbloom
Darkbloom
Open-weight models on Apple Silicon. Quantized serving, with a floor price on every request.
6 models
- Serving
- Apple Silicon, alpha
- Precision
- 2-bit / 4-bit / 8-bit
- Floor per request
- $0.000105
Open weights, quantized. Output can differ from full precision.
Named per model in the comparison below.
Charged whenever the token cost is below it.
Rates against the default route
Per million tokens after markup, from the live catalog. The default route is what an unpinned request is billed at. The floor makes the comparison depend on request size; the guide draws where it stops mattering.
| Model | Input, $ per 1M tokens | Output, $ per 1M tokens |
|---|---|---|
| Qwen3 VL 30B A3B Instruct4-bit on Darkbloom | $0.095 — Darkbloom only | $0.42 — Darkbloom only |
| Qwen 3.5 9B4-bit on Darkbloom | $0.084 — Darkbloom only | $0.137 — Darkbloom only |
| Qwen 3.6 35B A3B4-bit on Darkbloom | $0.053 — Darkbloom only | $0.735 — Darkbloom only |
| Google Gemma 4 26B A4B4-bit on Darkbloom | $0.044 $0.158 3.6× lower on Darkbloom | $0.231 $0.63 2.7× lower on Darkbloom |
| GPT OSS 20B8-bit on Darkbloom | $0.021 $0.032 1.5× lower on Darkbloom | $0.105 $0.147 1.4× lower on Darkbloom |
| Bonsai 2 27B2-bit on Darkbloom | $0.079 — Darkbloom only | $0.525 — Darkbloom only |
Available models
6 models
- Context
- 262K
- Input / 1M
- $0.0788
- Output / 1M
- $0.525
- Max output
- 33K
- Accepts
- Context
- 262K
- Input / 1M
- $0.0525
- Output / 1M
- $0.735
- Max output
- 16K
- Accepts
- Context
- 262K
- Input / 1M
- $0.158
- Output / 1M
- $0.63
- Max output
- 131K
- Accepts
- Context
- 262K
- Input / 1M
- $0.084
- Output / 1M
- $0.137
- Max output
- 16K
- Accepts
- Context
- 131K
- Input / 1M
- $0.0945
- Output / 1M
- $0.42
- Max output
- 33K
- Accepts
- Context
- 131K
- Input / 1M
- $0.0315
- Output / 1M
- $0.147
- Max output
- 8K
- Accepts
