Skip to content

Darkbloom

Compact OpenAI-compatible gateway.

Darkbloom is a small OpenAI-compatible gateway with a tight model list. Its catalog publishes little metadata, so most of its cells on this site show model availability without prices or context windows — a limit of the upstream catalog, not of the model.

Small catalog Sparse published metadata
Status
Live
Models in catalog
12
Text / multimodal
12
Publishes pricing for
12 models
Largest context window
1M tokens
Model id style
OpenAI-shaped ids.
Billing
Usage-based.
Catalog last checked
Website
darkbloom.dev
Catalog

12 models on Darkbloom

The 12 most widely available are shown; the rest are searchable in the full model list. "Id on this gateway" is what Darkbloom calls the model — where it differs from the canonical id, that difference is what a router has to translate.

Search all 12 models on Darkbloom
ModelVendorTypeId on this gatewayAvailable onContextInput / Mtok
Qwen3.5 35B A3B qwen/qwen3.5-35b-a3b Qwen Multimodal qwen3.5-35b-a3b Cheaper InferenceCloudflareConcentrateDarkbloomExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRequesty 262.1K $0.057–$0.250
Qwen 3.5 9B qwen/qwen3.5-9b Qwen Multimodal Qwen3.5-9B Cheaper InferenceCloudflareConcentrateDarkbloomExperiential LabsLLM GatewayNanoGPTOpenRouterRequestyTogether 262.1K $0.040–$0.170
Gemma 4 26B google/gemma-4-26b-a4b-it Google Multimodal gemma-4-26b CloudflareConcentrateDarkbloomNanoGPTOpenRouterOrcaRouterRequestyVercel 262.1K $0.023–$0.150
GLM-5.3-Flash glm-5.3-flash Z.ai Multimodal glm-5.3-flash Cheaper InferenceConcentrateDarkbloomExperiential LabsIsoquantLLM GatewaySayGM 1M $0.060–$0.150
GPT-OSS 20B gpt-oss-20b OpenAI Text gpt-oss-20b Cheaper InferenceConcentrateDarkbloomExperiential LabsLLM GatewaySayGM 131.1K $0.018–$0.610
Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightning NVIDIA Text nvidia-nemotron-3.5-lightning CloudflareDarkbloomNanoGPTOpenRouterVercel 1M $0.025–$0.070
PrismML Bonsai 2 27B prism-ml/ternary-bonsai-2-27b Prism Ml Multimodal ternary-bonsai-2-27b CloudflareDarkbloomNanoGPTOpenRouter 262.1K $0.075
Qwen 3.8 27B eigenlabs/qwen3.8-27b-4bit-mtp Eigenlabs Multimodal EigenLabs/Qwen3.8-27B-4bit-mtp Darkbloom 262.1K $0.035
Ternary Bonsai 2 9B eigenlabs/ternary-bonsai-2-9b-mlx-2bit Eigenlabs Text EigenLabs/Ternary-Bonsai-2-9B-MLX-2bit Darkbloom 262.1K $0.080
MiMo-V2.6-Flash mimo-v2.6-flash-mopd Eigeninference Text mimo-v2.6-flash-mopd Darkbloom 1M $0.100
Nemotron 3.5 Super nvidia-nemotron-3.5-super Eigeninference Multimodal nvidia-nemotron-3.5-super Darkbloom 262.1K $0.060
Qwen 3.6 35B A3B qwen3.6-35b-a3b-vl-mtp-mxfp8 Qwen Multimodal qwen3.6-35b-a3b-vl-mtp-mxfp8 Darkbloom 262.1K $0.050
Cheapest here

Lowest input prices on Darkbloom

Ranked by what this gateway charges, not by the cheapest price anywhere.

ModelVendorAvailable onContextInput / MtokSpread
GPT-OSS 20B gpt-oss-20b OpenAI Cheaper InferenceConcentrateDarkbloomExperiential LabsLLM GatewaySayGM 131.1K $0.018–$0.610 33.89x
Gemma 4 26B google/gemma-4-26b-a4b-it Google CloudflareConcentrateDarkbloomNanoGPTOpenRouterOrcaRouterRequestyVercel 262.1K $0.023–$0.150 6.52x
Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightning NVIDIA CloudflareDarkbloomNanoGPTOpenRouterVercel 1M $0.025–$0.070 2.80x
Qwen 3.8 27B eigenlabs/qwen3.8-27b-4bit-mtp Eigenlabs Darkbloom 262.1K $0.035 —
Qwen 3.6 35B A3B qwen3.6-35b-a3b-vl-mtp-mxfp8 Qwen Darkbloom 262.1K $0.050 —
Nemotron 3.5 Super nvidia-nemotron-3.5-super Eigeninference Darkbloom 262.1K $0.060 —
Qwen3.5 35B A3B qwen/qwen3.5-35b-a3b Qwen Cheaper InferenceCloudflareConcentrateDarkbloomExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRequesty 262.1K $0.057–$0.250 4.39x
GLM-5.3-Flash glm-5.3-flash Z.ai Cheaper InferenceConcentrateDarkbloomExperiential LabsIsoquantLLM GatewaySayGM 1M $0.060–$0.150 2.50x
PrismML Bonsai 2 27B prism-ml/ternary-bonsai-2-27b Prism Ml CloudflareDarkbloomNanoGPTOpenRouter 262.1K $0.075 —
Qwen 3.5 9B qwen/qwen3.5-9b Qwen Cheaper InferenceCloudflareConcentrateDarkbloomExperiential LabsLLM GatewayNanoGPTOpenRouterRequestyTogether 262.1K $0.040–$0.170 4.25x
By model type

What Darkbloom carries

A gateway with 2,000 models is not necessarily a gateway with 2,000 chat models.

Multimodal 8 Text 4
Not exclusive

7 of these models are on other gateways too

Anything in this list can be served from somewhere other than Darkbloom without changing the model id your application sends.

ModelVendorAvailable onContextInput / MtokSpread
Qwen3.5 35B A3B qwen/qwen3.5-35b-a3b Qwen Cheaper InferenceCloudflareConcentrateDarkbloomExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRequesty 262.1K $0.057–$0.250 4.39x
Qwen 3.5 9B qwen/qwen3.5-9b Qwen Cheaper InferenceCloudflareConcentrateDarkbloomExperiential LabsLLM GatewayNanoGPTOpenRouterRequestyTogether 262.1K $0.040–$0.170 4.25x
Gemma 4 26B google/gemma-4-26b-a4b-it Google CloudflareConcentrateDarkbloomNanoGPTOpenRouterOrcaRouterRequestyVercel 262.1K $0.023–$0.150 6.52x
GLM-5.3-Flash glm-5.3-flash Z.ai Cheaper InferenceConcentrateDarkbloomExperiential LabsIsoquantLLM GatewaySayGM 1M $0.060–$0.150 2.50x
GPT-OSS 20B gpt-oss-20b OpenAI Cheaper InferenceConcentrateDarkbloomExperiential LabsLLM GatewaySayGM 131.1K $0.018–$0.610 33.89x
Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightning NVIDIA CloudflareDarkbloomNanoGPTOpenRouterVercel 1M $0.025–$0.070 2.80x
PrismML Bonsai 2 27B prism-ml/ternary-bonsai-2-27b Prism Ml CloudflareDarkbloomNanoGPTOpenRouter 262.1K $0.075 —
Recent churn

What Darkbloom has changed lately

From the daily catalog crawl. Every line below concerns this gateway, so it is not named on each one.

All gateway changes