How many AI models does Together serve?
17 tracked models as of 17 August 2026: 17 language models (16 with a public ModelCap Index position), across 17 live endpoints observed through OpenRouter.
Inference provider
Together: AI models and API pricing
Every tracked model Together serves through OpenRouter, with Together'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 17 August 2026
Together serves 17 tracked models through 17 endpoints as of 17 August 2026; the highest-ranked is Kimi K3 (ModelCap Index #3); mean measured uptime is 95.28%.
Models served
17
On the ModelCap Index
16
Cheapest output price
$0.12/1M
Language models on Together (17)
Ranked models first, in ModelCap Index order. Prices are the lowest Together lists for the model; the endpoint count shows how many deployments carry it.
Together on ModelCap: common questions
What is the best model available on Together?
Kimi K3 from Moonshot AI is the highest-ranked language model Together serves, at ModelCap Index position #3 and $15.00 per 1M output tokens on Together. The table lists every model in Index order.
What is the cheapest model on Together?
Gemma 3n 4B at $0.12 per 1M output tokens ($0.06 per 1M input), the lowest positive language-token price Together lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.
Which Together model has the largest context window?
Llama Guard 4 12B, served with a 1M-token context window on Together. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.
How reliable is Together?
Mean measured uptime across Together endpoints is 95.28% 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 Together prices come from?
From the OpenRouter catalogue entry for each Together endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Together 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 17 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.
Explore further
- All inference providers68 providers compared
- Cheapest LLMsRanked models by listed price
- Compare AI modelsHead-to-head on benchmarks, price and context
- Kimi K3 vs GLM 5.2Both served by Together
- Kimi K3 vs MiniMax M3Both served by Together
- Kimi K3 vs InklingBoth served by Together
- GLM 5.2 vs MiniMax M3Both served by Together
- GLM 5.2 vs InklingBoth served by Together
- Kimi K3 on every providerHighest-ranked model Together serves