Cr Providers· Inference host· 12 tracked models

Crusoe — pricing & performance

Compare models All providers Data sources

Models served

of 1,191 tracked models

Mean output speed

102

tokens per second, averaged over
11 measured endpoints

Mean latency

0.6s

time to first token, averaged over
11 measured endpoints

Cheapest blended

$0.087

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

Output speed on Crusoe

Output tokens per second for the 11 of 12 models on Crusoe with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 12, measured or not. Higher is better. We do not run these measurements ourselves.

⇩

260

190

152

127

100

Nemotron 3 Nano
30B A3B

Qwen3 235B A22B
Instruct 2507

DeepSeek V3 0324

Gemma 4 31B

The Known Good

12 models on Crusoe

Full leaderboard →

Model	Creator	Input $/M	Output $/M	Blended	Speed	TTFT	Context
DeepSeek: DeepSeek V3 0324	DeepSeek	$0.50	$1.50	$0.75	39	0.4s	164k
DeepSeek: DeepSeek V4.1 Flash	DeepSeek	$0.29	$1.20	$0.52	152	0.3s	1.05M
Google: Gemma 4 31B	Google	$0.14	$0.40	$0.20	17	0.7s	262k
Meta: Llama 3.3 70B Instruct	Meta	$0.25	$0.75	$0.38	—	—	131k
MoonshotAI: Kimi K2.6	Moonshot AI	$0.70	$3.50	$1.40	54	1.0s	262k
NVIDIA: Nemotron 3 Nano 30B A3B	NVIDIA	$0.050	$0.20	$0.087	260	0.2s	262k
OpenAI: gpt-oss-120b	OpenAI	$0.050	$0.25	$0.10	190	0.2s	131k
Qwen: Qwen3 235B A22B Instruct 2507	Alibaba	$0.22	$0.80	$0.36	44	0.3s	262k
Z.ai: GLM 5.1	Z.ai	$1.20	$4.40	$2.00	74	0.6s	203k
Z.ai: GLM 5.2	Z.ai	$1.40	$4.40	$2.15	100	1.2s	1.05M
Z.ai: GLM 5.3	Z.ai	$1.40	$4.40	$2.15	127	1.0s	1.05M
Z.ai: GLM 5.3 Flash	Z.ai	$0.15	$0.50	$0.24	70	1.0s	1.05M

The Known Good

Source. Prices, endpoint availability and throughput for Crusoe 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.