Skip to content
ModelCap

Inference provider

Wafer: AI models and API pricing

Every tracked model Wafer serves through OpenRouter, with Wafer'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

Wafer serves 12 tracked models through 22 endpoints as of 19 November 2026; the highest-ranked is Kimi K3.1 Pro (ModelCap Index #11); mean measured uptime is 100.0%.

Models served
12
On the ModelCap Index
8
Cheapest output price
$0.17/1M

Language models on Wafer (12)

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

Language models served by Wafer, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Kimi K3.1 ProMoonshot AI#1180.0$0.253$8.801Mmxfp4100.0%2
2Kimi K3Moonshot AI#1779.0$0.153$9.601Mmxfp4100.0%3
3GLM 5.3Z.ai#1978.5$0.07$1.401Mfp4100.0%2
4GLM 5.3 FlashZ.ai#2676.4$0.042$0.1841Mnvfp4100.0%2Open weights
5MiniMax M3.1 FlashMiniMax#3374.1$0.135$0.541Mnvfp4100.0%1
6DeepSeek V4 Pro 0813DeepSeek#3473.0$0.111$4.301Mmxfp4100.0%2Open weights
7Qwen3.8 27BQwen#6863.1$0.06$2.20262Kfp8100.0%1Open weights
8DeepSeek V4.1 Flash 1017DeepSeek#9258.5$0.036$0.501Mmxfp4100.0%2Open weights
9DeepSeek V4 Flash 0423DeepSeek—$0.12$0.171Mmxfp4100.0%1Open weights
10DeepSeek V4 Flash 0731DeepSeek—$0.05$0.231Mnvfp4100.0%2Open weights
11DeepSeek V4.1 FlashDeepSeek—$0.051$0.5671Mmxfp4100.0%2Open weights
12GLM 5.2Z.ai—$0.0070$6.801Mfp4100.0%2Open weights

Wafer on ModelCap: common questions

How many AI models does Wafer serve?

12 tracked models as of 19 November 2026: 12 language models (8 with a public ModelCap Index position), across 22 live endpoints observed through OpenRouter.

What is the best model available on Wafer?

Kimi K3.1 Pro from Moonshot AI is the highest-ranked language model Wafer serves, at ModelCap Index position #11 and $8.80 per 1M output tokens on Wafer. The table lists every model in Index order.

What is the cheapest model on Wafer?

DeepSeek V4 Flash 0423 at $0.17 per 1M output tokens ($0.12 per 1M input), the lowest positive language-token price Wafer lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Wafer model has the largest context window?

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

How reliable is Wafer?

Mean measured uptime across Wafer endpoints is 100.0% 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 Wafer prices come from?

From the OpenRouter catalogue entry for each Wafer endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Wafer 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