Parasail

Parasail Pricing

Visit parasail.io →

Per-token pricing for 48 open-source LLMs on Parasail — a privacy-focused serverless inference network with on-demand deployments and batch processing.

Last updated: Nov 21, 2026

Get our weekly newsletter on pricing changes, new releases, and tools.

Parasail free tier & credits

No ongoing free tier — see credits & cheapest models — see the full Parasail free tier guide

48
Models
$0.03
Cheapest Input/1M
$0.03
Cheapest Output/1M
13
Model Authors
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Context
Quant
Input/1M
Output/1M
131k
fp8
$0.030
$0.030
131k
fp4
$0.030
$0.150
131k
bf16
$0.040
$0.050
8k
bf16
$0.040
$0.050
131k
bf16
$0.050
$0.330
131k
fp8
$0.080
$0.450
4k
fp16
$0.080
$0.110
131k
bf16
$0.090
$0.300
128k
bf16
$0.100
$0.200
131k
fp4
$0.100
$0.750
262k
bf16
$0.100
$0.250
262k
fp8
$0.100
$0.900
262k
fp8
$0.100
$1.100
262k
bf16
$0.120
$0.800
262k
bf16
$0.130
$0.400
1049k
fp8
$0.140
$0.280
deepseek-ai/DeepSeek-V4-Flash-0731
1049k
fp8
$0.140
$0.280
131k
fp8
$0.140
$0.800
262k
fp8
$0.150
$0.400
1049k
fp8
$0.150
$0.600
131k
fp4
$0.150
$0.750
262k
fp8
$0.150
$1.000
1049k
fp8
$0.150
$0.500
1049k
fp4
$0.188
$0.625
131k
fp8
$0.210
$1.900
131k
fp8
$0.220
$0.500
262k
fp8
$0.240
$2.200
262k
bf16
$0.250
$0.750
1049k
fp8
$0.300
$1.200
deepseek/deepseek-v4.1-flash-1017
1049k
fp8
$0.300
$1.200
1049k
fp8
$0.300
$1.200
131k
bf16
$0.300
$0.500
524k
fp8
$0.350
$1.000
1024k
bf16
$0.400
$0.400
1049k
fp8
$0.450
$1.800
1049k
fp8
$0.450
$1.800
262k
fp8
$0.500
$3.600
33k
fp8
$0.550
$0.800
262k
int4
$0.750
$3.500
128k
fp8
$0.800
$1.000
deepseek/deepseek-v4-pro-0813
1049k
fp8
$1.320
$3.960
262k
fp4
$1.400
$4.400
1049k
fp4
$1.400
$4.400
deepseek/deepseek-v4-pro-0813
1049k
fp8
$1.980
$5.940
1049k
fp4
$2.000
$10.000
1049k
fp4
$2.100
$6.600
1049k
fp4
$3.000
$15.000
1049k
fp4
$4.500
$22.500

Pricing for Parasail endpoints aggregated via OpenRouter. Prices per 1M tokens.

About Parasail

Parasail is a serverless inference network offering pay-per-token access to open-source models, plus on-demand dedicated deployments and batch processing for large jobs. It is marketed on privacy — no data retention — and exposes an OpenAI-compatible API.

Many models are served at fp8, fp4 or int4 quantization to keep costs low. The table below shows the models Parasail currently serves with public per-token pricing, the quantization each price applies to, and context length.

Parasail Pricing FAQ

How much does Parasail cost?

Parasail charges per token, with input prices for smaller open models starting around $0.04–$0.10 per million tokens. See the live table above for current per-model input and output prices.

Does Parasail retain my data?

Parasail markets itself on privacy with a no-data-retention policy on its serverless inference. Check their current terms for the authoritative guarantee.

What is the difference between serverless and dedicated on Parasail?

Serverless is pay-per-token with no commitment. Dedicated deployments give you reserved capacity for steady or latency-sensitive workloads, and batch processing handles large offline jobs at lower cost.

Is Parasail OpenAI-compatible?

Yes. Parasail exposes an OpenAI-compatible API, so switching from another provider is usually just a base-URL and API-key change.