Darkbloom

Models served by Darkbloom

Model	Context	Input /M	Output /M	Latency	Throughput
Gemma 4 26B A4B INT8 google/gemma-4-26b-a4b-it:darkbloom	131k	$0.04/M	$0.23/M	2.1s	20 tps
Gemma 4 26B A4B (Thinking) INT4 google/gemma-4-26b-a4b-it:thinking:darkbloom	131k	$0.04/M	$0.23/M	2.1s	20 tps
GPT OSS 20B FP8 TEE attested openai/gpt-oss-20b:darkbloom	131k	$0.02/M	$0.11/M	2.9s	25 tps
Qwen 3.6 35B A3B FP4 TEE attested Qwen/Qwen3.6-35B-A3B:darkbloom	262k	$0.05/M	$0.73/M	3.8s	56 tps
Qwen3.5 35B A3B FP4 TEE attested qwen3.5-35b-a3b:darkbloom	262k	$0.08/M	$0.79/M	N/A	N/A
Qwen3.5 9B qwen/qwen3.5-9b:darkbloom	262k	$0.08/M	$0.14/M	N/A	N/A
Qwen3.8 27B INT4 TEE attested qwen3.8-27b:darkbloom	262k	$0.16/M	$2.10/M	2.5s	29 tps
Qwen3.8 27B Thinking INT4 TEE attested qwen3.8-27b:thinking:darkbloom	262k	$0.16/M	$2.10/M	2.5s	29 tps

Prices are per million tokens. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using Darkbloom via the API

For models with provider selection, append :darkbloom to the model ID, set "provider": "darkbloom" in the request body, or send an X-Provider: darkbloom header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-26b-a4b-it:darkbloom",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.