De Providers· Inference host· 11 tracked models

DekaLLM — pricing & performance

Compare models All providers Data sources

Models served

of 1,191 tracked models

Mean output speed

tokens per second, averaged over
11 measured endpoints

Mean latency

0.9s

time to first token, averaged over
11 measured endpoints

Cheapest blended

$0.021

per 1M tokens at a 3:1
input:output blend

Output speed on DekaLLM

Output tokens per second for all 11 models on DekaLLM with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

⇩

130

DeepSeek V4.1
Flash

Qwen3.6 35B A3B

Qwen3 30B A3B
Instruct 2507

The Known Good

11 models on DekaLLM

Full leaderboard →

Model	Creator	Input $/M	Output $/M	Blended	Speed	TTFT	Context
DeepSeek: DeepSeek V4.1 Flash	DeepSeek	$0.12	$1.20	$0.39	130	0.9s	1.05M
Google: Gemma 4 26B A4B	Google	$0.060	$0.33	$0.13	80	0.5s	262k
Google: Gemma 4 31B	Google	$0.10	$0.33	$0.16	16	1.4s	262k
Mistral: Mistral Nemo	Mistral	$0.018	$0.030	$0.021	27	0.5s	131k
NVIDIA: Nemotron 3 Super	NVIDIA	$0.080	$0.45	$0.17	13	2.5s	262k
OpenAI: gpt-oss-120b	OpenAI	$0.030	$0.18	$0.068	20	0.6s	131k
OpenAI: gpt-oss-20b	OpenAI	$0.029	$0.14	$0.057	32	0.6s	131k
Qwen: Qwen3 30B A3B Instruct 2507	Alibaba	$0.090	$0.30	$0.14	85	0.4s	262k
Qwen: Qwen3.6 35B A3B	Alibaba	$0.10	$1.00	$0.33	96	0.6s	262k
Qwen: Qwen3.8 27B	Alibaba	$0.049	$3.00	$0.79	80	0.8s	262k
Z.ai: GLM 5.3 Flash	Z.ai	$0.10	$1.00	$0.33	57	1.3s	1.05M

The Known Good

Source. Prices, endpoint availability and throughput for DekaLLM 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.