// pricing · September 2026
Cohere API Pricing
Every Cohere model's list price per 1M tokens — input, output and cached input — with context windows, LiveBench scores and what a real workload costs per month.
5 Cohere models are listed, with a median list price of $1.32 per 1M input tokens and $5.30 per 1M output tokens. Paid prices run from $0.066 (Command R7B (12-2024)) to $4.38 (Command R+ (08-2024)) per 1M tokens blended. 1 has a free listing.
- Models
- 5
- 1 with a free listing
- Median input / 1M
- $1.32
- paid models
- Median output / 1M
- $5.30
- paid models
- Cheapest paid
- $0.066
- Command R7B (12-2024)
- Prompt caching
- 0
- publish a cached-input price
Cohere model prices
List prices in USD per 1M tokens. “Blended” is a 3:1 input:output mix; the per-month column prices the selected workload using each model's cached-input rate where it publishes one.
Showing 5 of 5 models · per-month column: 8K in / 600 out × 100K requests, 50% of input cached
| cohere/north-mini-code:free | Free | Free | — | Free | 256K | — | $0 |
|---|---|---|---|---|---|---|---|
| cohere/command-r7b-12-2024 | $0.037 | $0.150 | — | $0.066 | 128K | — | $39.00 |
| cohere/command-r-08-2024 | $0.150 | $0.600 | — | $0.262 | 128K | — | $156.00 |
| cohere/command-a | $2.50 | $10.00 | — | $4.38 | 256K | — | $2,600 |
| cohere/command-r-plus-08-2024 | $2.50 | $10.00 | — | $4.38 | 128K | — | $2,600 |
Cohere pricing FAQ
What is the cheapest Cohere model?
Command R7B (12-2024) is the cheapest paid Cohere model, at $0.037 per 1M input tokens and $0.150 per 1M output tokens. 1 Cohere models also have a free listing, usually with tighter rate limits.
Why do output tokens cost more than input tokens?
Generating a token takes a full forward pass per token, while input is processed in parallel. Across the paid Cohere models listed here the median output price is $5.30 per 1M against $1.32 for input — reasoning tokens bill as output too.
Which Cohere models support prompt caching?
None of them publish a separate cached-input price right now.
How current are these prices?
List prices are pulled from OpenRouter’s public models API and refreshed every 15 minutes. Batch discounts and enterprise pricing are not included.
Other providers
What these prices include
- List prices from OpenRouter's public models API, which mirrors provider pricing. Batch discounts and negotiated enterprise rates are not included.
- Variants —
:freeand:batchlistings are folded into their base model; its model page lists them. - Per-month cost is a floor: tokens you describe times list price. Cache writes and reasoning-token volume depend on your workload.