Parasail
Explore Parasail models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Parasailparasail
No logs
| Provider | Parasail |
|---|---|
| Provider website | https://www.parasail.io/ |
| Models | 27 public models |
| Prepaid routes | 27 |
| BYOK routes | 26 |
| Zero data retention | yes |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | Tracked as ZDR for serverless and dedicated inference. Parasail documents no storage or logging of submitted input on those service paths, retention only while generating and delivering output, and no training on input or output. Batch service is excluded from this claim; TrustedRouter does not route Parasail traffic through batch. Policy source |
Measured performance
44 samplesContinuously sampled across Parasail's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 2305 ms |
|---|---|
| Effective throughput | 38 tok/s n=9 |
| Uptime | 90.91% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| bytedance/ui-tars-1.5-7b | 929 ms | 929 ms | — | 100.00% | — | 4 |
| qwen/qwen3-coder-next | 949 ms | 949 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3 | 1075 ms | 1075 ms | 50 tok/s n=1 | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1820 ms | 1820 ms | 40 tok/s n=1 | 100.00% | — | 2 |
| meta-llama/llama-3.3-70b-instruct | 2161 ms | 2161 ms | — | 100.00% | — | 3 |
| thedrummer/skyfall-36b-v2 | 2305 ms | 2304 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.1 | 2691 ms | 2691 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-20b | 2703 ms | 2702 ms | — | 100.00% | — | 4 |
| qwen/qwen3-vl-235b-a22b-instruct | 3782 ms | 3782 ms | — | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 3846 ms | 3846 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 3877 ms | 3877 ms | 38 tok/s n=1 | 100.00% | — | 1 |
| z-ai/glm-5.2 | 3944 ms | 3944 ms | 111 tok/s n=1 | 100.00% | — | 6 |
| moonshotai/kimi-k2.6 | 3973 ms | 3973 ms | — | 100.00% | — | 1 |
| meta-llama/llama-4-maverick | 4149 ms | 4149 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash | 4179 ms | 4179 ms | 38 tok/s n=2 | 100.00% | — | 3 |
| google/gemma-4-31b-it | 4271 ms | 4271 ms | 19 tok/s n=2 | 100.00% | — | 1 |
| thedrummer/cydonia-24b-v4.1 | 938 ms | 937 ms | — | 66.67% | — | 3 |
| deepseek/deepseek-v4-pro-0423 | 1935 ms | 1935 ms | 32 tok/s n=1 | 66.67% | — | 3 |
| arcee-ai/trinity-large-thinking | 1782 ms | 1782 ms | — | 33.33% | — | 3 |
Parasail performance history · Full provider & model leaderboard.
Models served by Parasail.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
arcee-ai/trinity-large-thinkingArcee AI: Trinity Large Thinking |
IQ 97#87 | 262,144 | 2 | $0.2321/1M | $0.89675/1M | prepaid BYOK |
bytedance/ui-tars-1.5-7bByteDance: UI-TARS 7B |
— | 128,000 | 2 | $0.1055/1M | $0.211/1M | prepaid BYOK |
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 113#41 | 1,048,576 | 2 | $0.1477/1M | $0.2954/1M | prepaid BYOK |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro |
IQ 117#31 | 1,048,576 | 2 | $1.8357/1M | $3.6714/1M | prepaid BYOK |
deepseek/deepseek-v4-pro-0423DeepSeek V4 Pro 0423 |
— | 1,048,576 | 1 | $1.8357/1M | $3.6714/1M | prepaid |
google/gemma-3-27b-itGoogle: Gemma 3 27B |
— | 262,144 | 2 | $0.0844/1M | $0.47475/1M | prepaid BYOK |
google/gemma-4-26b-a4b-itGoogle: Gemma 4 26B A4B |
IQ 96#89 | 262,144 | 2 | $0.13715/1M | $0.422/1M | prepaid BYOK |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#73 | 262,144 | 2 | $0.15825/1M | $0.422/1M | prepaid BYOK |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | 2 | $0.2321/1M | $0.5275/1M | prepaid BYOK |
meta-llama/llama-4-maverickMeta: Llama 4 Maverick |
IQ 90#103 | 1,048,576 | 2 | $0.36925/1M | $1.055/1M | prepaid BYOK |
minimax/minimax-m3MiniMax: MiniMax M3 |
IQ 114#39 | 1,048,576 | 2 | $0.3165/1M | $1.266/1M | prepaid BYOK |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#23 | 262,144 | 2 | $0.79125/1M | $3.6925/1M | prepaid BYOK |
moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code |
IQ 118#28 | 262,144 | 2 | $0.79125/1M | $3.6925/1M | prepaid BYOK |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#61 | 131,072 | 2 | $0.1055/1M | $0.79125/1M | prepaid BYOK |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
IQ 100#77 | 131,072 | 2 | $0.0422/1M | $0.211/1M | prepaid BYOK |
qwen/qwen2.5-vl-72b-instructQwen: Qwen2.5 VL 72B Instruct |
— | 128,000 | 2 | $0.844/1M | $1.055/1M | prepaid BYOK |
qwen/qwen3-coder-nextQwen: Qwen3 Coder Next |
— | 262,144 | 2 | $0.1266/1M | $0.844/1M | prepaid BYOK |
qwen/qwen3-next-80b-a3b-instructQwen: Qwen3 Next 80B A3B Instruct |
— | 262,144 | 2 | $0.1055/1M | $1.1605/1M | prepaid BYOK |
qwen/qwen3-vl-235b-a22b-instructQwen: Qwen3 VL 235B A22B Instruct |
— | 262,144 | 2 | $0.22155/1M | $2.0045/1M | prepaid BYOK |
qwen/qwen3-vl-8b-instructQwen: Qwen3 VL 8B Instruct |
— | 262,144 | 2 | $0.26375/1M | $0.79125/1M | prepaid BYOK |
qwen/qwen3.5-35b-a3bQwen: Qwen3.5-35B-A3B |
— | 262,144 | 2 | $0.15825/1M | $1.055/1M | prepaid BYOK |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
— | 262,144 | 2 | $0.5275/1M | $3.798/1M | prepaid BYOK |
qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B A3B |
IQ 100#78 | 262,144 | 2 | $0.15825/1M | $1.055/1M | prepaid BYOK |
thedrummer/cydonia-24b-v4.1TheDrummer: Cydonia 24B V4.1 |
— | 131,072 | 2 | $0.3165/1M | $0.5275/1M | prepaid BYOK |
thedrummer/skyfall-36b-v2TheDrummer: Skyfall 36B V2 |
— | 32,768 | 2 | $0.58025/1M | $0.844/1M | prepaid BYOK |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 114#38 | 204,800 | 2 | $1.477/1M | $4.642/1M | prepaid BYOK |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#19 | 1,048,576 | 2 | $1.477/1M | $4.642/1M | prepaid BYOK |
Questions
Does Parasail have zero data retention?
TrustedRouter records Parasail as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.
Is Parasail end-to-end encrypted?
TrustedRouter does not currently mark Parasail as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Parasail models are available through TrustedRouter?
This page currently lists 27 public Parasail models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.