Last verified
MULTILINGUAL128K CONTEXTTEXT APINO CACHE ROW

Aya Expanse 32B API Pricing

Aya Expanse 32B is cohere's open-weight multilingual aya expanse model for 23 languages. The official pricing row lists $0.5/M input and $1.5/M output. Pulled directly from cohere.com.

Input - per 1M tokens
$0.50/M
Source Cohere flat
Output - per 1M tokens
$1.50/M
Context 128K flat
Cache N/A
$0.50/M
Cache no public row not listed
Effective - agentic blend
$0.58/M
92/8 split - no cache discount
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with current Aya Expanse 32B token rates. Tweak spend, output mix, or cache assumptions and share the URL to share the calculation.

$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
Words equivalent (English)
Effective rate
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Real-world presets.

§ 03 / TOKENIZER

Paste text. See tokens. See cost.

Estimate · cohere-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 350
Words 53
Tokens (estimated) 91 tokens
Cost as input · uncached $0.000046 USD
Cost as output · uncached $0.000137 USD
Cost as cached input $0.000046 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Aya Expanse 32B Current $0.50 $1.50 $0.58 agentic 92/8 128K Multilingual generation and translation
Reka Flash $0.80 $2.00 $0.90 pricier not listed Fast chat and production assistants
Sonar $1.00 $1.00 $1.00 pricier not listed Low-cost web-grounded answers
Reka Edge $0.10 $0.10 $0.10 cheaper not listed Lowest-cost Reka chat

Frequently asked.

Practical Aya Expanse 32B pricing questions, with public list prices separated from assumptions and add-on fees.

Q · 01 What is Aya Expanse 32B priced at? +
Aya Expanse 32B is listed at $0.5/M input and $1.5/M output on Cohere's official pricing page, verified 2026-06-14.
Q · 02 Is prompt caching priced separately? +
No separate cache-read token price is published for this row. AI//COST keeps cached input equal to the base input price, $0.5/M, instead of inventing a discount.
Q · 03 How is the effective price calculated? +
The effective tile uses AI//COST's standard 92/8 input-output blend. With no public cache discount, Aya Expanse 32B's token-only blended price is $0.58/M.
Q · 04 Does this include every possible fee? +
Yes for text tokens. Non-text meters, private deployments, enterprise contracts, and any custom dedicated-capacity plans are outside this page unless the vendor publishes them as token prices.
Q · 05 Are there free trials or production keys? +
Cohere says trial API keys are free but rate-limited and not for production. Production API keys are billed on a pay-as-you-go basis after the account goes through the production-key flow.
Q · 06 Which API model ID should I use? +
Use c4ai-aya-expanse-32b. If the vendor later changes aliases or retires snapshots, this page should be re-verified against the official pricing page.