Providers /Parasail
Inference provider

Parasail

Models
37
Regions
00

Our take

Editorial by LLMap · updated Aug 3, 2026

Parasail is a mid-size host for downloadable models with a zero-retention data policy and measured throughput on every tracked offer. It sits between budget floors and premium tiers, with 37 open-weight models available.

Use this when zero data retention is required — it is explicitly offered. Pick it for throughput-sensitive workloads where 72 TPS on Llama 3.2 3B Instruct or 44 TPS on DeepSeek V4 Flash meets latency needs. Choose it for exploratory access to 37 open-weight models without premium pricing. Skip it if you need verified SOC 2, a confirmed EU-region endpoint, or documented headquarters location for your compliance review.

Strengths
  • Explicit zero-retention data policy, paired with a commitment not to train on prompts.
  • Throughput transparency on every sampled offer — 12 of 12 include measured throughput, ranging from 16 to 72 TPS.
  • Competitive input pricing on several models, including Mistral Nemo and Llama 3.2 3B Instruct.
Trade-offs
  • Compliance and geographic documentation is thin: SOC 2, EU endpoint and headquarters country are all unverified in our data.
  • Output prices can spike relative to input on smaller models — Llama 3.2 3B Instruct output is 6.6× its input, and Gemma 4 26B A4B output is 3.1× its input.
  • Some throughput figures lag for mid-size models: Qwen3.5 9B at 16 TPS, Gemma 4 26B A4B at 27 TPS and Gemma 4 31B at 28 TPS, versus 72 TPS on Llama 3.2 3B Instruct.
01

Privacy & data handling

Yes
No
No answer on record

The colour says whether the answer favours you, not whether it is a yes — not training on your prompts earns a green cross, no zero-retention option earns a red one.

Trains on your prompts
No
Logs prompts
No
Offered
No answer on record

Prompt retention: none.

02

Models & pricing

Cydonia 24B V4.123.6B$0.30 / $0.50 /1M131K5h agoDeepSeek V4 Flash291B$0.14 / $0.28 /1M1M5h agoDeepSeek V4 Pro1.6T$1.74 / $3.48 /1M1M5h agoGemma 3 27B27.4B$0.080 / $0.45 /1M131K5h agoGemma 4 26B A4B26.5B$0.13 / $0.40 /1M262K5h agoGemma 4 31B32.7B$0.15 / $0.40 /1M262K5h agoGLM 5754B$1.00 / $3.20 /1M203K5h agoGLM 5.1754B$1.40 / $4.40 /1M203K5h agoGLM 5.2753B$1.40 / $4.40 /1M262K5h agogpt-oss-120b120B$0.10 / $0.75 /1M131K5h agoKimi K2.61.1T$0.75 / $3.50 /1M262K5h agoKimi K2.7 Code1.1T$0.76 / $3.50 /1M262K5h agoLlama 3.2 3B Instruct3.2B$0.050 / $0.33 /1M131K5h agoLlama 3.3 70B Instruct70.6B$0.22 / $0.50 /1M131K19h agoLlama 3 8B Lunaris8B$0.040 / $0.050 /1M8K5h agoLlama 4 Maverick402B$0.35 / $1.00 /1M524K5h agoMiMo-V2.5311B$0.14 / $0.28 /1M1M5h agoMiniMax M2.5229B$0.30 / $1.20 /1M197K5h agoMiniMax M3427B$0.30 / $1.20 /1M1M7h agoMistral Nemo12.2B$0.030 / $0.030 /1M131K5h agoMistral Small 3.2 24B24B$0.090 / $0.30 /1M131K5h agoMythoMax 13B13B$0.080 / $0.11 /1M4K5h agoQwen2.5 VL 72B Instruct73.4B$0.80 / $1.00 /1M128K5h agoQwen3 235B A22B Instruct 2507235B$0.14 / $0.80 /1M131K5h agoQwen3.5-35B-A3B36B$0.15 / $1.00 /1M262K19h agoQwen3.5 397B A17B403B$0.50 / $3.60 /1M262K5h agoQwen3.5-9B9.7B$0.10 / $0.25 /1M262K5h agoQwen3.6 35B A3B36B$0.15 / $1.00 /1M262K5h agoQwen3 Coder Next79.7B$0.12 / $0.80 /1M262K5h agoQwen3 Next 80B A3B Instruct81.3B$0.10 / $1.10 /1M262K5h agoQwen3 VL 235B A22B Instruct236B$0.21 / $1.90 /1M131K5h agoQwen3 VL 8B Instruct8.8B$0.25 / $0.75 /1M262K5h agoRocinante 12B12.2B$0.25 / $0.50 /1M66K5h agoSkyfall 36B V236.9B$0.55 / $0.80 /1M33K5h agoTrinity Large Thinking399B$0.22 / $0.85 /1M262K5h agoUI-TARS 7B8.3B$0.10 / $0.20 /1M128K5h agoUnslopNemo 12B12.2B$0.40 / $0.40 /1M1M5h ago
Something wrong on this page? Tell us