Parasail
Distributed AI inference network with serverless, dedicated, and batch endpoints. No rate limits, no contracts, up to 30x cheaper than legacy cloud.
At a glance: Parasail has 28 models listed on Inference Hub: 25 LLMs, 2 multimodal models and 1 coding model. The cheapest text model is gpt-oss-20b at $0.030 input and $0.150 output per 1M tokens, and the most expensive is Kimi K3 at $3.00 input and $15.00 output per 1M tokens. Free tier: Free credits on signup. Prices are checked against Parasail's own pricing every week.
Features
Compliance
None listed
Pricing Model
per tokenDetails
https://api.parasail.io/v1 Model Catalog (35)
Parasail guides
Parasail API FAQ
Is the Parasail API free?
Yes, Parasail has a free tier: Free credits on signup. Paid usage is billed per model.
What is the cheapest Parasail model?
Gpt-oss-20b at $0.03 in / $0.15 out per 1M tokens, based on the 35 models we track for Parasail.
How many models does Parasail offer?
We track 35 Parasail models: 31 LLM, 2 coding, 2 multimodal.
Is the Parasail API OpenAI-compatible?
Yes. Parasail exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.
Run Parasail? Add a "Prices tracked on Inference Hub" badge to your site, or email hello@inferencehub.org if a price here is wrong.