Skip to content
ModelCap

Inference provider

BaseTen: AI models and API pricing

Every tracked model BaseTen serves through OpenRouter, with BaseTen'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

BaseTen serves 13 tracked models through 23 endpoints as of 19 November 2026; the highest-ranked is Kimi K3 (ModelCap Index #17); mean measured uptime is 100.0%.

Models served
13
On the ModelCap Index
10
Cheapest output price
$0.26/1M

Language models on BaseTen (13)

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

Language models served by BaseTen, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Kimi K3Moonshot AI#1779.0$3.00$15.001Mfp8100.0%1
2GLM 5.3Z.ai#1978.5$1.40$4.401Mfp4, fp8100.0%4
3Muse Spark OpenMeta#2178.4$1.25$4.251Mfp4100.0%1
4GLM 5.3 FlashZ.ai#2676.4$0.15$0.501Mfp8100.0%1Open weights
5DeepSeek V4 Pro 0813DeepSeek#3473.0$1.32$3.961Mfp4100.0%1Open weights
6Beam 1.0 501B A23BReflection#6763.4$0.40$1.201Mfp4—1Open weights
7DeepSeek V4.1 Flash 1017DeepSeek#9258.5$0.30$1.201M—100.0%2Open weights
8Nemotron 3.5 Super VLNVIDIA#13350.9$0.20$0.501Mfp4100.0%1
9gpt-oss-120bOpenAI#17439.8$0.10$0.50128Kfp4100.0%2Open weights
10Nemotron 3 UltraNVIDIA#26128.0$0.60$2.40203Kfp4100.0%1
11DeepSeek V4 Flash 0731DeepSeek—$0.13$0.261Mfp8, fp32100.0%2Open weights
12DeepSeek V4.1 FlashDeepSeek—$0.30$1.201M—100.0%2Open weights
13GLM 5.2Z.ai—$1.40$4.401Mfp8100.0%4Open weights

BaseTen on ModelCap: common questions

How many AI models does BaseTen serve?

13 tracked models as of 19 November 2026: 13 language models (10 with a public ModelCap Index position), across 23 live endpoints observed through OpenRouter.

What is the best model available on BaseTen?

Kimi K3 from Moonshot AI is the highest-ranked language model BaseTen serves, at ModelCap Index position #17 and $15.00 per 1M output tokens on BaseTen. The table lists every model in Index order.

What is the cheapest model on BaseTen?

DeepSeek V4 Flash 0731 at $0.26 per 1M output tokens ($0.13 per 1M input), the lowest positive language-token price BaseTen lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which BaseTen model has the largest context window?

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

How reliable is BaseTen?

Mean measured uptime across BaseTen 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 BaseTen prices come from?

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