OpenAI compatible API. Attested gateway. Public status.

Crusoe

Crusoe models on TrustedRouter with prices, routes, policy notes, and source links.

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`crusoe`

No provider claim

All providers

Provider	Crusoe
Models	15 public models
Prepaid routes	15
BYOK routes	15
Zero data retention	not claimed
Confidential compute	not claimed
Provider E2EE	not claimed
Policy note	No provider-ZDR claim is tracked here. Crusoe's Managed Inference docs and pricing/catalog pages are linked for model and API data-handling review. Policy source

Measured performance

234 samples

Continuously sampled across Crusoe's routed models — p50 TTFT, throughput, and success rate. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	4367 ms
Throughput	20 tok/s
Uptime	94.44%

Model	p50 TTFT	p50 TTFB	Throughput	Uptime	Config excluded	Samples
nvidia/nemotron-3-super-120b-a12b	888 ms	888 ms	—	100.00%	13 `probe_config_error`	3
deepseek/deepseek-v3-0324	2182 ms	2181 ms	—	100.00%	—	21
qwen/qwen3-235b-a22b-2507	2390 ms	2390 ms	—	100.00%	—	18
yutori/n1.5	2571 ms	2571 ms	—	100.00%	—	16
z-ai/glm-5.2	3011 ms	3011 ms	—	100.00%	—	17
z-ai/glm-5.1	3985 ms	3984 ms	—	100.00%	—	22
nvidia/nemotron-3-ultra-550b	4182 ms	4181 ms	—	92.86%	—	14
deepseek/deepseek-v4-pro	4367 ms	4366 ms	—	100.00%	—	17
openai/gpt-oss-120b	4571 ms	4570 ms	—	100.00%	—	17
google/gemma-4-31b-it	4595 ms	4594 ms	20 tok/s	70.83%	—	24
deepseek/deepseek-v4-flash	4957 ms	4956 ms	—	94.44%	—	18
nvidia/nemotron-3-nano-omni-reasoning-30b-a3b	5221 ms	5221 ms	—	100.00%	—	15
meta-llama/llama-3.3-70b-instruct	6237 ms	6236 ms	—	100.00%	—	18
moonshotai/kimi-k2.6	7834 ms	7833 ms	—	71.43%	—	14

Full provider & model leaderboard.

Provider models

Models served by Crusoe.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	AI IQ	Context	Endpoints	Prompt	Completion	Routes
`deepseek/deepseek-v3-0324` DeepSeek V3 0324 benchmarks performance api	—	163,840	2	$0.55/1M	$1.65/1M	prepaid BYOK
`deepseek/deepseek-v4-flash` DeepSeek: DeepSeek V4 Flash benchmarks performance api	IQ 104#36	1,048,576	2	$0.154/1M	$0.308/1M	prepaid BYOK
`deepseek/deepseek-v4-pro` DeepSeek: DeepSeek V4 Pro benchmarks performance api	IQ 108#30	1,048,576	2	$1.914/1M	$3.828/1M	prepaid BYOK
`google/gemma-4-31b-it` Google: Gemma 4 31B benchmarks performance api	IQ 96#53	262,144	2	$0.154/1M	$0.44/1M	prepaid BYOK
`meta-llama/llama-3.3-70b-instruct` Meta: Llama 3.3 70B Instruct benchmarks performance api	—	131,072	2	$0.275/1M	$0.825/1M	prepaid BYOK
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks performance api	IQ 117#10	262,144	2	$0.77/1M	$3.85/1M	prepaid BYOK
`nvidia/nemotron-3-nano-30b-a3b` nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B benchmarks performance api	—	262,144	2	$0.055/1M	$0.22/1M	prepaid BYOK
`nvidia/nemotron-3-nano-omni-reasoning-30b-a3b` nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B benchmarks performance api	—	262,144	2	$0.33/1M	$2.013/1M	prepaid BYOK
`nvidia/nemotron-3-super-120b-a12b` nemotron 3 super 120b a12b benchmarks performance api	—	131,072	2	$0.33/1M	$2.64/1M	prepaid BYOK
`nvidia/nemotron-3-ultra-550b` nvidia/NVIDIA-Nemotron-3-Ultra-550B benchmarks performance api	—	262,144	2	$1.1/1M	$3.52/1M	prepaid BYOK
`openai/gpt-oss-120b` OpenAI: gpt-oss-120b benchmarks performance api	IQ 94#56	131,072	2	$0.055/1M	$0.275/1M	prepaid BYOK
`qwen/qwen3-235b-a22b-2507` Qwen: Qwen3 235B A22B Instruct 2507 benchmarks performance api	—	262,144	2	$0.242/1M	$0.88/1M	prepaid BYOK
`yutori/n1.5` yutori/n1.5 benchmarks performance api	—	128,000	2	$1.65/1M	$5.5/1M	prepaid BYOK
`z-ai/glm-5.1` Z.ai: GLM 5.1 benchmarks performance api	IQ 112#20	202,752	2	$1.32/1M	$4.84/1M	prepaid BYOK
`z-ai/glm-5.2` GLM 5.2 benchmarks performance api	IQ 116#11	1,048,576	2	$1.54/1M	$4.84/1M	prepaid BYOK