Skip to content
ModelPriceLab

Search model prices

Find source-linked rates by model, vendor, or platform.

Cohere API Pricing

Complete pricing for all Cohere models. Input/output costs per 1M tokens, context windows, and rate limits.

Billing terms: priced in USD per 1M tokens unless a row states otherwise; official direct rates are listed separately from third-party channels, and regional prices are kept distinct. Record updated 2026-10-10.

Cohere API Pricing Calculator

Select a model to estimate monthly cost using its listed rates on each channel.

Quick examples:
Input mode
Cache hit rate (share of input tokens served from cache)50%

Workloads reusing system prompts, long documents, or conversation history hit more; channels without a cached rate are billed at the full input rate.

Estimated monthly cost at current inputs
ChannelEffective inputOutput /1MEst. / month
official$2.50$10.00$13.00

Formula: monthly cost = (input tokens × effective input rate + output tokens × output rate) ÷ 1,000,000 × calls. The effective input rate blends list and cached rates at your cache-hit share. Rates share the selected model and billing basis; your vendor bill is authoritative.

Currently available rates

Aya Expanse 32B

LLMcohere-c4ai-aya-expanse-32b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
-
-
—
128K
4K
Sources: Official

Aya Expanse 8B

LLMcohere-c4ai-aya-expanse-8b
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
-
-
—
8K
4K

Aya Vision 32B

LLMcohere-c4ai-aya-vision-32b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
-
-
—
16K
4K
Sources: Official

Aya Vision 8B

LLMcohere-c4ai-aya-vision-8b
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
-
-
—
16K
4K

Command A

LLMcohere-command-a
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$2.50
$10.00
—
256K
8K
Sources: OpenRouter

Command A

LLMcohere-command-a-03-2025
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$2.50
$10.00
—
256K
8K
Sources: Official

Command A Plus

LLMcohere-command-a-plus-05-2026
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$2.50
$10.00
—
128K
64K
Sources: Official

Command A Reasoning

LLMcohere-command-a-reasoning-08-2025
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$2.50
$10.00
—
256K
32K
Sources: Official

Command A Translate

LLMcohere-command-a-translate-08-2025
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$2.50
$10.00
—
8K
8K
Sources: Official

Command A Vision

LLMcohere-command-a-vision-07-2025
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$2.50
$10.00
—
128K
8K
Sources: Official

Command A+

LLMcohere-command-a-plus
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.30
$1.50
$0.15
192K
64K
Sources: OpenRouter

Command R

LLMcohere-command-r-08-2024
View Details
Legacy / Superseded

Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.

Replacement reference: cohere-command-a-03-2025
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.15
$0.60
—
128K
4K
OpenRouter
global
1M Tokens
$0.15
$0.60
—
128K
4K
Sources: Official · OpenRouter

Command R+

LLMcohere-command-r-plus-08-2024
View Details
Legacy / Superseded

Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.

Replacement reference: cohere-command-a-03-2025
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$2.50
$10.00
—
128K
4K
OpenRouter
global
1M Tokens
$2.50
$10.00
—
128K
4K
Sources: Official · OpenRouter

Command R7B

LLMcohere-command-r7b-12-2024
View Details
Legacy / Superseded

Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.

Replacement reference: cohere-command-a-03-2025
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.04
$0.15
—
128K
4K
OpenRouter
global
1M Tokens
$0.04
$0.15
—
128K
4K
Sources: Official · OpenRouter

Command R7B Arabic

LLMcohere-command-r7b-arabic-02-2025
View Details
Legacy / Superseded

Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.

Replacement reference: cohere-command-a-03-2025
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.04
$0.15
—
128K
4K
Sources: Official

North Mini Code

LLMcohere-north-mini-code-1-0
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
256K
64K
Sources: Official

North Mini Code (free)

LLMcohere-north-mini-code-free
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.0000
$0.0000
—
256K
64K
Sources: OpenRouter

North Small Translate

LLMcohere-north-small-translate-09-2026
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
33K
16K
Sources: Official

Tiny Aya Earth

LLMcohere-tiny-aya-earth
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
-
-
—
8K
8K
Sources: Official

Tiny Aya Fire

LLMcohere-tiny-aya-fire
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
-
-
—
8K
8K
Sources: Official

Tiny Aya Global

LLMcohere-tiny-aya-global
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
-
-
—
8K
8K
Sources: Official

Tiny Aya Water

LLMcohere-tiny-aya-water
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
-
-
—
8K
8K
Sources: Official
AI Cost Optimization

Does this change your best option?

Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.