Parasail

Serverless

Distributed AI inference network with serverless, dedicated, and batch endpoints. No rate limits, no contracts, up to 30x cheaper than legacy cloud.

Features

OpenAI Compatible

Streaming

Batching

Fine-tuning

Embeddings

Vision

Audio

Function Calling

JSON Mode

Compliance

SOC 2

HIPAA

GDPR

Pricing Model

per token

Free tier: Free credits on signup

Details

Models 35

API Base https://api.parasail.io/v1

LLM Inference

Model Catalog (35)

Model	Type	Input $/1M	Output $/1M	Context	Speed
DeepSeek V3 DeepSeek · 671B MoE	llm	$0.280	$0.450	—	—
DeepSeek V3.2 DeepSeek · 671B MoE (37B active)	llm	$0.280	$0.450	—	—
DeepSeek V4 Flash DeepSeek	llm	$0.140	$0.280	—	—
DeepSeek V4 Flash DeepSeek 0731	llm	$0.140	$0.280	1.0M	—
DeepSeek V4 Pro DeepSeek	llm	$0.450	$3.48	—	—
DeepSeek V4 Pro DeepSeek 0813	llm	$1.32	$3.96	1.0M	—
DeepSeek V4.1 Flash DeepSeek	llm	$0.300	$1.20	1.0M	—
GLM 4.7 Zhipu AI	llm	$0.450	$2.10	—	—
GLM 5 Zhipu AI · 744B	llm	$1.00	$3.20	—	—
GLM 5.1 Z.ai · 744B MoE (40B active)	llm	$1.40	$4.40	—	—
GLM 5.2 Z.ai	llm	$1.40	$4.40	—	—
GLM 5.3 Z.ai	llm	$1.40	$4.40	1.0M	—
GLM 5.3 Flash Z.ai	llm	$0.150	$0.500	1.0M	—
GPT OSS 120B OpenAI · 117B MoE (5.1B active)	llm	$0.100	$0.750	—	—
Gemma 3 27B Google · 27B	llm	$0.080	$0.450	—	—
Gemma 4 26B A4B Google	llm	$0.130	$0.400	—	—
Kimi K2.5 Moonshot AI · 1T MoE (32B active)	llm	$0.600	$2.80	—	—
Kimi K2.6 Moonshot AI · 1T MoE (32B active)	llm	$0.750	$3.50	—	—
Kimi K2.7 Code Moonshot AI · 1T MoE (32B active)	code	$0.750	$3.50	262k	—
Kimi K3 Moonshot AI	llm	$3.00	$15.00	1.0M	—
Llama 3.2 3B Instruct Meta	llm	$0.050	$0.330	131k	—
Llama 3.3 70B Meta · 70B	llm	$0.220	$0.500	—	—
Llama 4 Maverick Meta · 400B (17B active)	llm	$0.350	$1.00	—	—
MiniMax M3 MiniMax	llm	$0.300	$1.20	—	—
Mistral Small 4 Mistral AI · 119B	llm	$0.090	$0.300	—	—
Qwen 3 235B Alibaba · 235B MoE	llm	$0.140	$0.800	—	—
Qwen 3.5 9B Alibaba · 9B	llm	$0.100	$0.250	262k	—
Qwen3 Coder Next Alibaba	code	$0.120	$0.800	—	—
Qwen3 VL 235B A22B Instruct Alibaba	multimodal	$0.210	$1.90	131k	—
Qwen3 VL 8B Instruct Alibaba	multimodal	$0.250	$0.750	262k	—
Qwen3.5 397B A17B Alibaba	llm	$0.500	$3.60	—	—
Qwen3.5-35B-A3B Alibaba	llm	$0.150	$1.00	262k	—
Qwen3.6 35B A3B Alibaba	llm	$0.150	$1.00	262k	—
Qwen3.8 27B Alibaba	llm	$0.240	$2.20	262k	—
gpt-oss-20b OpenAI	llm	$0.030	$0.150	—	—

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.