Skip to content
llmwaves

Inference provider

Darkbloom

10 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.

Models served

10

Median output speed

108 t/s

Median latency

402ms

Median price / 1M

$0.159

Catalogue

Strongest and fastest on this provider

What the catalogue looks like at the top end, on the two axes that usually decide the choice.

Highest Intelligence Index

Among models this provider serves

View as table
ModelIntelligence
MiMo-V2.6-Flash (Xiaomi)37.9
Qwen3.8 27B (Qwen)33.7
Qwen3.5-35B-A3B (Qwen)19.3
Qwen3.6 35B A3B (Qwen)18.2
gpt-oss-20b (free) (OpenAI)15.2
Nemotron 3.5 Lightning (NVIDIA)12.9
Qwen3.5-9B (Qwen)11.2
gpt-oss-20b (OpenAI)9.0

Fastest output

Median tokens per second

View as table
ModelTokens/s
gpt-oss-20b (OpenAI)410
Qwen3.8 27B (Qwen)409
Nemotron 3.5 Lightning (NVIDIA)226
Qwen3.6 35B A3B (Qwen)128
Qwen3.5-35B-A3B (Qwen)121
Gemma 4 26B A4B (Google)95
MiMo-V2.6-Flash (Xiaomi)82
Qwen3.5-9B (Qwen)67
Ternary Bonsai 2 27B (Prism Ml)18
gpt-oss-20b (free) (OpenAI)18

Full catalogue

All 10 models on Darkbloom

Filter by creator
10 of 10 models
MiMo-V2.6-Flash
Xiaomiopen
37.9$0.03
Qwen3.8 27B
Qwenopen
33.7$0.19
Qwen3.5-35B-A3B
Qwenopen
19.3$0.09
Qwen3.6 35B A3B
Qwenopen
18.2$0.09
gpt-oss-20b (free)
OpenAIopen
15.2Free
Nemotron 3.5 Lightning
NVIDIAopen
12.9$0.02
Qwen3.5-9B
Qwenopen
11.2$0.02
gpt-oss-20b
OpenAIopen
9.0$0.008
Ternary Bonsai 2 27B
Prism Mlopen
—$0.04
Gemma 4 26B A4B
Googleopen
—$0.03