The Known Good Updated 16 Sep 2026 Subscribe
Providers· Inference host· 10 tracked models

Darkbloom — pricing & performance

Compare models All providers Data sources
Models served
10
of 1,128 tracked models
Mean output speed
26
tokens per second, averaged over
10 measured endpoints
Mean latency
2.8s
time to first token, averaged over
10 measured endpoints
Cheapest blended
$0.000
per 1M tokens at a 3:1
input:output blend
Output speed on Darkbloom

Output tokens per second for all 10 models on Darkbloom with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 10 of 10 models⇩
59
51
32
28
27
20
16
12
10
6
The Known Good
10 models on Darkbloom
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Google: Gemma 4 26B A4B Google $0.042 $0.22 $0.086 16 3.1s 131k
Google: Gemma 4 26B A4B (free) Google $0.000 $0.000 $0.000 12 5.5s 131k
NVIDIA: Nemotron 3.5 Lightning NVIDIA $0.065 $0.18 $0.094 32 1.7s 262k
OpenAI: gpt-oss-20b OpenAI $0.020 $0.10 $0.040 27 2.9s 131k
OpenAI: gpt-oss-20b (free) OpenAI $0.000 $0.000 $0.000 20 3.7s 131k
Qwen: Qwen3 VL 30B A3B Instruct Alibaba $0.090 $0.40 $0.17 6 1.7s 131k
Qwen: Qwen3.5-35B-A3B Alibaba $0.080 $0.75 $0.25 59 0.8s 262k
Qwen: Qwen3.5-9B Alibaba $0.080 $0.13 $0.092 28 1.0s 262k
Qwen: Qwen3.6 35B A3B Alibaba $0.050 $0.70 $0.21 51 5.0s 262k
Qwen: Qwen3.8 27B Alibaba $0.15 $2.00 $0.61 10 2.2s 262k
The Known Good
Source. Prices, endpoint availability and throughput for Darkbloom are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.