Darkbloom

Inference host · 9 models · 9 priced routes

Models on Darkbloom

Model	In / out per 1M	Vs headline
gpt-oss-20b fp8 · gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.	$0.018 / $0.09+397% vs headline	+397%	fp8 · gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
Nemotron 3.5 Lightning int4 · NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.	$0.025 / $0.12Same vs headline	Same	int4 · NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
Gemma 4 26B A4B Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.	$0.042 / $0.22+2% vs headline	+2%	Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Qwen3.5-9B fp4 · Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.	$0.08 / $0.13Same vs headline	Same	fp4 · Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.
GLM 5.3 Flash fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.065 / $0.18+93% vs headline	+93%	fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.
Nemotron 3.5 Super VL nvfp4 · NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.	$0.06 / $0.35Same vs headline	Same	nvfp4 · NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
Qwen3.6 35B A3B fp4 · Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.	$0.05 / $0.7+343% vs headline	+343%	fp4 · Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.
Qwen3.5-35B-A3B fp4 · The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency.	$0.065 / $0.75-47% vs headline	-47%	fp4 · The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency.
Qwen3.8 27B fp4 · Qwen3.8 27B is an open-weight dense vision-language model from Qwen.	$0.035 / $1.5-58% vs headline	-58%	fp4 · Qwen3.8 27B is an open-weight dense vision-language model from Qwen.