Darkbloom pricing overview
TokenWatch tracks 12 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Cheapest input price: gpt-oss-20b at $0.018 per million input tokens and $0.090 per million output tokens. 12 of 12 text models publish a cache-read price; 0 carry a zero-data-retention tag.
Darkbloom text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| openai | darkbloom | OpenAI: gpt-oss-20b | $0.018 | $0.090 | $0.0090 | $0.0096 |
| nvidia | darkbloom | NVIDIA: Nemotron 3.5 Super VL | $0.060 | $0.350 | $0.010 | $0.013 |
| nvidia | darkbloom | NVIDIA: Nemotron 3.5 Lightning | $0.025 | $0.120 | $0.012 | $0.013 |
| darkbloom | Google: Gemma 4 26B A4B | $0.042 | $0.220 | $0.021 | $0.023 | |
| qwen | darkbloom | Qwen: Qwen3.8 27B | $0.035 | $2.20 | $0.018 | $0.029 |
| qwen | darkbloom | Qwen: Qwen3.6 35B A3B | $0.050 | $0.700 | $0.025 | $0.029 |
| z-ai | darkbloom | Z.ai: GLM 5.3 Flash | $0.065 | $0.180 | $0.033 | $0.034 |
| qwen | darkbloom | Qwen: Qwen3.5-35B-A3B | $0.065 | $0.750 | $0.033 | $0.037 |
| prism-ml | darkbloom | PrismML: Ternary Bonsai 2 27B | $0.075 | $0.500 | $0.037 | $0.041 |
| prism-ml | darkbloom | PrismML: Ternary Bonsai 2 9B | $0.080 | $0.130 | $0.040 | $0.041 |
| qwen | darkbloom | Qwen: Qwen3.5-9B | $0.080 | $0.130 | $0.040 | $0.041 |
| xiaomi | darkbloom | Xiaomi: MiMo-V2.6-Flash | $0.100 | $0.280 | $0.050 | $0.052 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.