Index / providers / parasail

Parasail

US serverless GPU inference cloud with an OpenAI-compatible API serving TheDrummer's roleplay and creative fine-tunes alongside mainstream models.

Models3
Per-token price$0.35–$0.61/1M tok
Plans from—
Free tierNo
parasail.io ↗Pending review
[ 01 ] Models & prices

BILLINGPay per token, billed in arrears; your card is charged each time usage reaches $25.

ModelMethodContextIn $/1MOut $/1MPer 1K chats
Cydonia 24B v4.1Mistral Small 24B · 24B · Apache-2.0
Fine-tuned33K$0.30$0.50$0.55
Skyfall 36B v2Mistral Small (upscaled) · 36B · Apache-2.0
Fine-tuned131K$0.55$0.80$0.95
Fine-tuned131K$0.55$0.80$0.95

Per 1K chats = cost of 1,000 messages of ~1,000 tokens in and ~500 out. Click a model to compare it across providers.All models →

[ 02 ] At a glance
Method
Fine-tuned
Access
OpenAI-compatible API
Logging
No logs
Trains on prompts
No
Guarantee
Policy only
Jurisdiction
US
Signup
Account required
Payments
Card
Data checked
Oct 11, 2026

PRIVACYServerless inputs aren't stored or logged beyond generation (batch inputs kept about 30 days) and aren't used for training. Policy ↗

[ 03 ] Scores
Compliance
Benchmark pending
measured
Capability
Benchmark pending
measured
Privacy
48.0
from published policy & pricing
Truthfulness
Benchmark pending
measured
Cost
67.5
from published policy & pricing
Speed
Benchmark pending
measured

Composite: pending capability and compliance runs · method

[ 04 ] Notes & sources

Parasail, Inc. Context windows on Parasail's pages differ from what OpenRouter reports for the same models.

  1. https://www.parasail.io/models
  2. https://www.parasail.io/legal/privacy-policy
  3. https://docs.parasail.io/parasail-docs/billing/pricing