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
7
Text / multimodal
Publishes pricing for
No prices published
Largest context window
Model id style
OpenAI-shaped ids.
Billing
Usage-based.
Catalog last checked
Availability data only in this snapshot. This build was generated from FreeRouter's model-map snapshot, which records which gateway serves which model but carries no pricing, context windows, or descriptions. Those columns fill in once the catalog refresh runs against the gateway APIs — see about the data.
Catalog

7 models on Darkbloom

The 7 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 7 models on Darkbloom
ModelVendorTypeId on this gatewayGatewaysContext
gpt-oss-20b gpt-oss-20b OpenAI Unclassified same as canonical 3
qwen3.5-9b qwen3.5-9b Qwen Unclassified same as canonical 3
gemma-4-26b gemma-4-26b Google Unclassified same as canonical 2
qwen3-vl-30b-a3b-instruct qwen3-vl-30b-a3b-instruct Qwen Unclassified same as canonical 2
qwen3.5-35b-a3b qwen3.5-35b-a3b Qwen Unclassified same as canonical 2
qwen3.8-27b-4bit-mtp eigenlabs/qwen3.8-27b-4bit-mtp Eigenlabs Unclassified same as canonical 1
qwen3.6-35b-a3b-vl-mtp-mxfp8 qwen3.6-35b-a3b-vl-mtp-mxfp8 Qwen Unclassified same as canonical 1
By model type

What Darkbloom carries

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

Not exclusive

5 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.

ModelVendorGatewaysContext
gpt-oss-20b gpt-oss-20b OpenAI 3
qwen3.5-9b qwen3.5-9b Qwen 3
gemma-4-26b gemma-4-26b Google 2
qwen3-vl-30b-a3b-instruct qwen3-vl-30b-a3b-instruct Qwen 2
qwen3.5-35b-a3b qwen3.5-35b-a3b Qwen 2