25 signals
HOlO V1 IS LIVEone ranked AI digest a day, scored in publicREAD HOW IT WORKS →HOlO V2 STARTSyour X account, your signals, every day

Model registry / Cohere / Tiny / Tiny Aya Earth

Tiny Aya Earth

Compact multilingual model specialized for West Asian and African languages

Line

Tiny

Weights

Open

Released

2026-02-17

Context

8K

Input

not stated

Output

not stated

Max output

8K

Coverage

not covered yet

Overview

Tiny Aya Earth is a compact multilingual model from Cohere, specialized for West Asian and African languages. It is the first version of the tiny line in the registry, released on 2026-02-17. The model has a context window of 8000 tokens and a maximum output of 8000 tokens. It accepts and returns text, supports tool calling, and does not have a reasoning mode. Weights are open. It is served by 1 host.

Specs

Released2026-02-17
LineCohere · Tiny
WeightsOpen
Context8K tokens
Max output8K tokens
Inputtext
Outputtext
ReasoningNo
Tool callingYes
Knowledge cutoffnot stated
API idtiny-aya-earth

Pricing

Inputnot stated
Cached inputnot stated
Outputnot stated

First version of its line in the registry.

Strengths

  • Specialized for West Asian and African languages
  • Compact multilingual model
  • 8000 token context and output window
  • Supports tool calling
  • Open weights

Best for

  • Reach for it for multilingual text tasks in West Asian and African languages
  • Reach for it for compact deployments with open weights
  • Reach for it for tool-calling workflows within an 8000 token window

How to access

ProviderModel id
Coheretiny-aya-earth

1 host serve this model at the price above · the maker's documentation

Tiny: every version

VersionReleasedContextInput
Tiny Aya Fire2026-02-178K
Tiny Aya Global2026-02-178K
Tiny Aya Water2026-02-178K

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

FAQ

What is the context window and output limit?
Both the context window and the maximum output are 8000 tokens.
Does it support tool calling?
Yes, it supports tool calling. It does not have a reasoning mode.
Are the model weights open?
Yes, the weights are open. The model accepts and returns text only.
Open weights8K context