Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Aya Expanse 32B

CohereOpen weights

Aya Expanse 32B by Cohere costs $0.50 per 1M input tokens and $1.50 per 1M output tokens, with a 128K-token context window.

Pricing

Input (per 1M tokens)
$0.50
Output (per 1M tokens)
$1.50
Cached input (per 1M)
—

Specifications

Provider
Cohere
Context window
128K tokens
Parameters
—
Released
Oct 2024
Open weights
Yes
Frontier model
No

Benchmarks

LMArena (Chatbot Arena) Elo
1224.0

Speed & latency

Time to first token
0.20s
Output speed
47 tok/s

Fastest host: cohere (via hf-router).

Compare Aya Expanse 32B with…

Aya Expanse 32B vs Gemini 3.1 Flash Lite$1.50/1MAya Expanse 32B vs Gemini 3.1 Flash Lite Preview$1.50/1MAya Expanse 32B vs GPT-3.5 Turbo$1.50/1MAya Expanse 32B vs Magistral Small$1.50/1MAya Expanse 32B vs Mistral Large 3 2512$1.50/1MAya Expanse 32B vs GPT-4.1 Mini$1.60/1M

FAQ

How much does Aya Expanse 32B cost?

Aya Expanse 32B is priced at $0.50 per 1M input tokens and $1.50 per 1M output tokens. Output tokens cost more than input.

What is Aya Expanse 32B's context window?

Aya Expanse 32B supports a context window of 128K tokens — the maximum prompt plus response length it can handle in a single request.

Is Aya Expanse 32B open weight?

Yes — Aya Expanse 32B has openly available weights.

Data as of 2026-10-29. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.