OpenAI compatible API. Attested gateway. Public status.

Parasail

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

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`parasail`

No provider claim

All providers

Provider	Parasail
Models	31 public models
Prepaid routes	29
BYOK routes	31
Zero data retention	not claimed
Confidential compute	not claimed
Provider E2EE	not claimed
Policy note	Parasail documents no input logging/storage for serverless and dedicated service paths, with different handling for batch service. Policy source

Measured performance

255 samples

Continuously sampled across Parasail'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	1000 ms
Throughput	—
Uptime	82.35%

Model	p50 TTFT	p50 TTFB	Throughput	Uptime	Config excluded	Samples
qwen/qwen3-next-80b-a3b-instruct	696 ms	694 ms	—	92.31%	—	13
openai/gpt-oss-20b	703 ms	701 ms	—	100.00%	—	11
google/gemma-3-27b-it	788 ms	787 ms	—	100.00%	—	8
qwen/qwen3-coder-next	799 ms	796 ms	—	100.00%	—	4
meta-llama/llama-3.3-70b-instruct	809 ms	807 ms	—	100.00%	—	10
meta-llama/llama-4-maverick	815 ms	712 ms	—	100.00%	—	8
qwen/qwen3-vl-8b-instruct	867 ms	763 ms	—	100.00%	—	10
bytedance/ui-tars-1.5-7b	869 ms	765 ms	—	100.00%	—	13
thedrummer/skyfall-36b-v2	870 ms	784 ms	—	100.00%	—	10
mistralai/mistral-small-3.2-24b-instruct	880 ms	879 ms	—	91.67%	—	12
z-ai/glm-5.1	908 ms	906 ms	—	88.89%	—	9
thedrummer/cydonia-24b-v4.1	991 ms	885 ms	—	100.00%	—	7
google/gemma-4-26b-a4b-it	1000 ms	897 ms	—	93.75%	—	16
qwen/qwen2.5-vl-72b-instruct	1058 ms	996 ms	—	83.33%	—	12
qwen/qwen3-vl-235b-a22b-instruct	1079 ms	1027 ms	—	100.00%	—	9
deepseek/deepseek-v3.2	1100 ms	997 ms	—	88.24%	—	17
openai/gpt-oss-120b	1159 ms	1056 ms	—	85.71%	—	7
google/gemma-4-31b-it	1426 ms	1425 ms	—	70.00%	—	10
arcee-ai/trinity-large-thinking	1428 ms	1325 ms	—	91.67%	—	12
moonshotai/kimi-k2.6	2097 ms	1993 ms	—	60.00%	—	15
moonshotai/kimi-k2.5	2806 ms	2804 ms	—	80.00%	—	10
z-ai/glm-4.7	6293 ms	6190 ms	—	88.89%	—	9
deepseek/deepseek-v4-pro	—	—	—	0.00%	14 `probe_config_error`	3
stepfun/step-3.5-flash	—	—	—	0.00%	—	17
deepseek/deepseek-v4-flash	—	—	—	0.00%	10 `probe_config_error`	1
qwen/qwen3.6-35b-a3b	—	—	—	0.00%	8 `probe_config_error`	2

Full provider & model leaderboard.

Provider models

Models served by Parasail.

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

Model	Context	Endpoints	Prompt	Completion	Routes
`arcee-ai/trinity-large-thinking` Arcee AI: Trinity Large Thinking benchmarks performance api	262,144	2	$0.242/1M	$0.935/1M	prepaid BYOK
`bytedance/ui-tars-1.5-7b` ByteDance: UI-TARS 7B benchmarks performance api	128,000	2	$0.11/1M	$0.22/1M	prepaid BYOK
`deepseek/deepseek-v3.2` DeepSeek: DeepSeek V3.2 benchmarks performance api	163,840	2	$0.308/1M	$0.495/1M	prepaid BYOK
`deepseek/deepseek-v4-flash` DeepSeek: DeepSeek V4 Flash benchmarks performance api	1,048,576	2	$0.154/1M	$0.308/1M	prepaid BYOK
`deepseek/deepseek-v4-pro` DeepSeek: DeepSeek V4 Pro benchmarks performance api	1,048,576	2	$1.914/1M	$3.828/1M	prepaid BYOK
`google/gemma-3-27b-it` Google: Gemma 3 27B benchmarks performance api	131,072	2	$0.088/1M	$0.495/1M	prepaid BYOK
`google/gemma-4-26b-a4b-it` Google: Gemma 4 26B A4B benchmarks performance api	262,144	2	$0.143/1M	$0.44/1M	prepaid BYOK
`google/gemma-4-31b-it` Google: Gemma 4 31B benchmarks performance api	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	$0.242/1M	$0.55/1M	prepaid BYOK
`meta-llama/llama-4-maverick` Meta: Llama 4 Maverick benchmarks performance api	1,048,576	2	$0.385/1M	$1.1/1M	prepaid BYOK
`minimax/minimax-m2.5` MiniMax: MiniMax M2.5 benchmarks performance api	204,800	2	$0.33/1M	$1.32/1M	prepaid BYOK
`mistralai/mistral-small-3.2-24b-instruct` Mistral: Mistral Small 3.2 24B benchmarks performance api	131,072	2	$0.099/1M	$0.66/1M	prepaid BYOK
`moonshotai/kimi-k2.5` MoonshotAI: Kimi K2.5 benchmarks performance api	262,144	2	$0.66/1M	$3.08/1M	prepaid BYOK
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks performance api	262,144	2	$0.88/1M	$3.85/1M	prepaid BYOK
`openai/gpt-oss-120b` OpenAI: gpt-oss-120b benchmarks performance api	131,072	2	$0.11/1M	$0.825/1M	prepaid BYOK
`openai/gpt-oss-20b` OpenAI: gpt-oss-20b benchmarks performance api	131,072	2	$0.044/1M	$0.22/1M	prepaid BYOK
`qwen/qwen2.5-vl-72b-instruct` Qwen: Qwen2.5 VL 72B Instruct benchmarks performance api	131,072	2	$0.88/1M	$1.1/1M	prepaid BYOK
`qwen/qwen3-235b-a22b-2507` Qwen: Qwen3 235B A22B Instruct 2507 benchmarks performance api	262,144	1	$0.11/1M	$0.66/1M	BYOK
`qwen/qwen3-coder-next` Qwen: Qwen3 Coder Next benchmarks performance api	262,144	2	$0.132/1M	$0.88/1M	prepaid BYOK
`qwen/qwen3-next-80b-a3b-instruct` Qwen: Qwen3 Next 80B A3B Instruct benchmarks performance api	262,144	2	$0.11/1M	$1.21/1M	prepaid BYOK
`qwen/qwen3-vl-235b-a22b-instruct` Qwen: Qwen3 VL 235B A22B Instruct benchmarks performance api	262,144	2	$0.231/1M	$2.09/1M	prepaid BYOK
`qwen/qwen3-vl-8b-instruct` Qwen: Qwen3 VL 8B Instruct benchmarks performance api	262,144	2	$0.275/1M	$0.825/1M	prepaid BYOK
`qwen/qwen3.5-35b-a3b` Qwen: Qwen3.5-35B-A3B benchmarks performance api	262,144	2	$0.165/1M	$1.1/1M	prepaid BYOK
`qwen/qwen3.5-397b-a17b` Qwen: Qwen3.5 397B A17B benchmarks performance api	262,144	2	$0.55/1M	$3.96/1M	prepaid BYOK
`qwen/qwen3.6-35b-a3b` Qwen: Qwen3.6 35B A3B benchmarks performance api	262,144	2	$0.165/1M	$1.1/1M	prepaid BYOK
`stepfun/step-3.5-flash` StepFun: Step 3.5 Flash benchmarks performance api	262,144	2	$0.11/1M	$0.33/1M	prepaid BYOK
`thedrummer/cydonia-24b-v4.1` TheDrummer: Cydonia 24B V4.1 benchmarks performance api	131,072	2	$0.33/1M	$0.55/1M	prepaid BYOK
`thedrummer/skyfall-36b-v2` TheDrummer: Skyfall 36B V2 benchmarks performance api	32,768	2	$0.605/1M	$0.88/1M	prepaid BYOK
`z-ai/glm-4.7` Z.ai: GLM 4.7 benchmarks performance api	202,752	2	$0.495/1M	$2.31/1M	prepaid BYOK
`z-ai/glm-5` Z.ai: GLM 5 benchmarks performance api	204,800	1	$1.1/1M	$3.52/1M	BYOK
`z-ai/glm-5.1` Z.ai: GLM 5.1 benchmarks performance api	202,752	2	$1.54/1M	$4.84/1M	prepaid BYOK