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. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 2 October 2026

Parasail serves 33 tracked models through 33 endpoints as of 2 October 2026; the highest-ranked is Kimi K3 (ModelCap Index #10); mean measured uptime is 99.75%.

Models served
33
On the ModelCap Index
23
Cheapest output price
$0.03/1M

Language models on Parasail (33)

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 K3Moonshot AI#1082.2$3.00$15.001Mfp499.21%1
2GLM 5.3Z.ai#1180.9$1.40$4.401Mfp899.76%1
3DeepSeek V4.1 FlashDeepSeek#1579.3$0.30$1.201Mfp899.89%1Open weights
4GLM 5.3 FlashZ.ai#1778.9$0.15$0.501Mfp499.66%1Open weights
5DeepSeek V4 Pro 0813DeepSeek#2476.4$1.32$3.961Mfp8100.0%1Open weights
6Gemma 4 31BGoogle#2872.9$0.15$0.40262Kfp899.51%1Open weights
7Qwen3.8 27BQwen#3968.9$0.24$2.20262Kfp8100.0%1Open weights
8MiniMax M3MiniMax#4068.5$0.30$1.201Mfp8100.0%1
9Gemma 4 26B A4BGoogle#4168.4$0.13$0.40262Kbf16100.0%1Open weights
10Qwen3.5 397B A17BQwen#4368.0$0.50$3.60262Kfp8100.0%1Open weights
11Qwen3 235B A22B Instruct 2507Qwen#6462.1$0.14$0.80131Kfp899.91%1Open weights
12Qwen3.6 35B A3BQwen#7260.7$0.15$1.00262Kfp8100.0%1Open weights
13Qwen3 VL 235B A22B InstructQwen#7859.5$0.21$1.90131Kfp899.87%1Open weights
14Qwen3.5-9BQwen#9554.9$0.10$0.25262Kbf16100.0%1Open weights
15Qwen3 Next 80B A3B InstructQwen#9854.7$0.10$1.10262Kfp8100.0%1Open weights
16Qwen3 Coder NextQwen#11053.3$0.12$0.80262Kbf1699.90%1Open weights
17gpt-oss-120bOpenAI#13244.6$0.10$0.75131Kfp4100.0%1Open weights
18Gemma 3 27BGoogle#13344.5$0.08$0.45131Kfp899.72%1
19Mistral Small 3.2 24BMistral AI#14143.1$0.09$0.30131Kbf16100.0%1Open weights
20gpt-oss-20bOpenAI#16637.8$0.03$0.15131Kfp4100.0%1Open weights
21Llama 4 MaverickMeta#17434.8$0.35$1.00524Kfp8100.0%1
22Llama 3.3 70B InstructMeta#17832.4$0.22$0.50131Kfp899.31%1
23Llama 3.2 3B InstructMeta#2628.4$0.05$0.33131Kbf16100.0%1
24Mistral NemoMistral AI—$0.03$0.03131Kfp899.86%1Open weights
25Qwen2.5 VL 72B InstructQwen—$0.80$1.00128Kfp8100.0%1
26Qwen3 VL 8B InstructQwen—$0.25$0.75262Kbf1699.37%1Open weights
27UI-TARS 7BByteDance—$0.10$0.20128Kbf16100.0%1Open weights
28DeepSeek V4 Flash 0423DeepSeek—$0.14$0.281Mfp899.82%1Open weights
29DeepSeek V4 Flash 0731DeepSeek—$0.14$0.281Mfp899.76%1Open weights
30DeepSeek V4 Pro 0423DeepSeek—$1.74$3.481Mfp898.06%1Open weights
31GLM 5.2Z.ai—$1.40$4.40262Kfp4100.0%1Open weights
32Kimi K2.6Moonshot AI—$0.75$3.50262Kint499.90%1
33Qwen3.5-35B-A3BQwen—$0.15$1.00262Kfp898.21%1Open weights

Parasail on ModelCap: common questions

How many AI models does Parasail serve?

33 tracked models as of 2 October 2026: 33 language models (23 with a public ModelCap Index position), across 33 live endpoints observed through OpenRouter.

What is the best model available on Parasail?

Kimi K3 from Moonshot AI is the highest-ranked language model Parasail serves, at ModelCap Index position #10 and $15.00 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, 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 99.75% 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 2 October 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