How many AI models does DekaLLM serve?
7 tracked models as of 12 September 2026: 7 language models (6 with a public ModelCap Index position), across 7 live endpoints observed through OpenRouter.
Inference provider
DekaLLM: AI models and API pricing
Every tracked model DekaLLM serves through OpenRouter, with DekaLLM'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 12 September 2026
DekaLLM serves 7 tracked models through 7 endpoints as of 12 September 2026; the highest-ranked is Gemma 4 26B A4B (ModelCap Index #40); mean measured uptime is 99.52%.
Models served
7
On the ModelCap Index
6
Cheapest output price
$0.03/1M
Language models on DekaLLM (7)
Ranked models first, in ModelCap Index order. Prices are the lowest DekaLLM lists for the model; the endpoint count shows how many deployments carry it.
DekaLLM on ModelCap: common questions
What is the best model available on DekaLLM?
Gemma 4 26B A4B from Google is the highest-ranked language model DekaLLM serves, at ModelCap Index position #40 and $0.33 per 1M output tokens on DekaLLM. The table lists every model in Index order.
What is the cheapest model on DekaLLM?
Mistral Nemo at $0.03 per 1M output tokens ($0.018 per 1M input), the lowest positive language-token price DekaLLM lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.
Which DekaLLM model has the largest context window?
Gemma 4 26B A4B, served with a 262K-token context window on DekaLLM. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.
How reliable is DekaLLM?
Mean measured uptime across DekaLLM endpoints is 99.52% 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 DekaLLM prices come from?
From the OpenRouter catalogue entry for each DekaLLM endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where DekaLLM 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?
It re-renders within a minute of every dataset refresh; this snapshot was published 12 September 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.