Skip to content
ModelCap

Inference provider

Parasail: AI models and API pricing

Every tracked model Parasail serves through OpenRouter, with Parasail's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Models with a position on a ModelCap board link to their model page, where every provider's deployment is listed side by side.

Snapshot as of 19 November 2026

Parasail serves 36 tracked models through 43 endpoints as of 19 November 2026; the highest-ranked is Kimi K3.1 Pro (ModelCap Index #11); mean measured uptime is 97.67%.

Models served
36
On the ModelCap Index
27
Cheapest output price
$0.03/1M

Language models on Parasail (36)

Ranked models first, in ModelCap Index order. Prices are the lowest Parasail lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Parasail, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Kimi K3.1 ProMoonshot AI#1180.0$2.00$10.001Mfp4100.0%1
2Kimi K3Moonshot AI#1779.0$3.00$15.001Mfp4100.0%2
3GLM 5.3Z.ai#1978.5$1.40$4.401Mfp4100.0%2
4GLM 5.3 FlashZ.ai#2676.4$0.15$0.501Mfp8, fp4100.0%2Open weights
5MiniMax M3.1 FlashMiniMax#3374.1$0.15$0.601Mfp8100.0%1
6DeepSeek V4 Pro 0813DeepSeek#3473.0$1.32$3.961Mfp8100.0%2Open weights
7Gemma 4 31BGoogle#4270.7$0.15$0.40262Kfp8100.0%1Open weights
8Qwen3.5 397B A17BQwen#5267.2$0.50$3.60262Kfp8100.0%1Open weights
9Gemma 4 26B A4BGoogle#6065.9$0.13$0.40262Kbf16100.0%1Open weights
10MiniMax M3MiniMax#6663.7$0.30$1.201Mfp8100.0%2
11Qwen3.8 27BQwen#6863.1$0.24$2.20262Kfp8100.0%1Open weights
12Qwen3 Coder NextQwen#8659.5$0.12$0.80262Kbf16100.0%1Open weights
13Qwen3 235B A22B Instruct 2507Qwen#9158.5$0.14$0.80131Kfp8100.0%1Open weights
14DeepSeek V4.1 Flash 1017DeepSeek#9258.5$0.30$1.201Mfp8100.0%1Open weights
15Qwen3 VL 235B A22B InstructQwen#10755.6$0.21$1.90131Kfp8100.0%1Open weights
16Qwen3.6 35B A3BQwen#11652.6$0.10$0.90262Kfp8100.0%1Open weights
17Qwen3 Next 80B A3B InstructQwen#12451.7$0.10$1.10262Kfp8100.0%1Open weights
18Gemma 3 27BGoogle#16042.7$0.08$0.45131Kfp8100.0%1
19Qwen3.5-9BQwen#16441.1$0.10$0.25262Kbf16100.0%1Open weights
20gpt-oss-120bOpenAI#17439.8$0.10$0.75131Kfp4100.0%2Open weights
21Qwen3 VL 8B InstructQwen#22134.7$0.25$0.75262Kbf16100.0%1Open weights
22Llama 4 MaverickMeta#22633.5$0.35$1.00524Kfp8100.0%1
23gpt-oss-20bOpenAI#23832.2$0.03$0.15131Kfp4100.0%1Open weights
24Llama 3.3 70B InstructMeta#24431.4$0.22$0.50131Kfp8100.0%1
25Mistral Small 3.2 24BMistral AI#25828.4$0.09$0.30131Kbf160.00%1Open weights
26Gemma 3 4BGoogle#26726.8$0.04$0.05131Kbf16100.0%1
27Llama 3.2 3B InstructMeta#3588.5$0.05$0.33131Kbf16100.0%1
28Mistral NemoMistral AI—$0.03$0.03131Kfp8100.0%1Open weights
29Qwen2.5 VL 72B InstructQwen—$0.80$1.00128Kfp8100.0%1
30UI-TARS 7BByteDance—$0.10$0.20128Kbf16100.0%1Open weights
31DeepSeek V4 Flash 0423DeepSeek—$0.14$0.281Mfp8100.0%1Open weights
32DeepSeek V4 Flash 0731DeepSeek—$0.14$0.281Mfp8100.0%1Open weights
33DeepSeek V4.1 FlashDeepSeek—$0.30$1.201Mfp8100.0%2Open weights
34GLM 5.2Z.ai—$1.40$4.40262Kfp4100.0%1Open weights
35Kimi K2.6Moonshot AI—$0.75$3.50262Kint4100.0%1
36Qwen3.5-35B-A3BQwen—$0.15$1.00262Kfp8100.0%1Open weights

Parasail on ModelCap: common questions

How many AI models does Parasail serve?

36 tracked models as of 19 November 2026: 36 language models (27 with a public ModelCap Index position), across 43 live endpoints observed through OpenRouter.

What is the best model available on Parasail?

Kimi K3.1 Pro from Moonshot AI is the highest-ranked language model Parasail serves, at ModelCap Index position #11 and $10.00 per 1M output tokens on Parasail. The table lists every model in Index order.

What is the cheapest model on Parasail?

Mistral Nemo at $0.03 per 1M output tokens ($0.03 per 1M input), the lowest positive language-token price Parasail lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Parasail model has the largest context window?

Kimi K3.1 Pro, served with a 1M-token context window on Parasail. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Parasail?

Mean measured uptime across Parasail endpoints is 97.67% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Parasail prices come from?

From the OpenRouter catalogue entry for each Parasail endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Parasail exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 19 November 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further