Skip to content
ModelCap

Inference provider

Cohere: AI models and API pricing

Every tracked model Cohere serves through OpenRouter, with Cohere'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 11 August 2026

Cohere serves 5 tracked models through 5 endpoints as of 11 August 2026; the highest-ranked is Command A (ModelCap Index #69); mean measured uptime is 97.74%.

Models served
5
On the ModelCap Index
5
Cheapest output price
$0.15/1M

Language models on Cohere (5)

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

Language models served by Cohere, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Command ACohere#6930.5$2.50$10.00256K——1
2Command R+ (08-2024)Cohere#20610.9$2.50$10.00128K——1
3North Mini CodeCohere#20710.3FreeFree256K—97.74%1Open weights
4Command R (08-2024)Cohere#2117.8$0.15$0.60128K——1
5Command R7B (12-2024)Cohere#2310.0$0.037$0.15128K——1

Cohere on ModelCap: common questions

How many AI models does Cohere serve?

5 tracked models as of 11 August 2026: 5 language models (5 with a public ModelCap Index position), across 5 live endpoints observed through OpenRouter.

What is the best model available on Cohere?

Command A from Cohere is the highest-ranked language model Cohere serves, at ModelCap Index position #69 and $10.00 per 1M output tokens on Cohere. The table lists every model in Index order.

What is the cheapest model on Cohere?

Command R7B (12-2024) at $0.15 per 1M output tokens ($0.037 per 1M input), the lowest positive language-token price Cohere lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Cohere model has the largest context window?

Command A, served with a 256K-token context window on Cohere. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Cohere?

Mean measured uptime across Cohere endpoints is 97.74% 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 Cohere prices come from?

From the OpenRouter catalogue entry for each Cohere endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Cohere 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 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further