Parasail
AI infrastructure for developers and enterprises. Requesty routes to 5 Parasail models starting at $0.15 per 1M input tokens with context windows up to 262K tokens. One API key, OpenAI-compatible SDK, no markup.
All Parasail models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | SWE-Bench |
|---|---|---|---|---|---|---|
Kimi K2.5 | 262K | 131K | $0.60 | $2.80 | 👁🔧 | — |
parasail-kimi-k2-instruct | 131K | 16K | $0.99 | $2.99 | 🔧 | — |
parasail-qwen3-235b-a22b-instruct-2507 | 262K | 8K | $0.15 | $0.85 | 🔧 | — |
parasail-gemma3-27b-it | 128K | 8K | $0.30 | $0.50 | 🔧 | — |
parasail-qwen25-vl-72b-instruct | 33K | 8K | $0.70 | $0.70 | 👁🔧 | — |
About Parasail on Requesty
How many Parasail models are available through Requesty?
Requesty routes to 5 Parasail models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Parasail model?
The cheapest Parasail model starts at $0.15 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Parasail pricing?
No. Requesty passes through exactly what Parasail charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Parasail models?
Parasail's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Parasail models hosted?
Parasail models are hosted in 🇺🇸 US. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Parasail rows in the models explorer.