Modeldex
Drag to turnCard front showing

CohereTextPromo

Tiny Aya Fire

Compact multilingual model specialized for South Asian languages

tiny-aya-fire
Type
Text
Quality
Not rated yet
Context window
8,000 tokens
Max output
8,000 tokens
Input price
—
Output price
—
Cache read
—
Cache write
—
Parameters
3.3B (3,349,227,520)
Downloads
700 in the last 30 days
Likes
29
Access to weights
Accept the license on Hugging Face first
Released
Feb 17, 2026
Knowledge cutoff
—
Takes in
Text
Puts out
Text
Reasoning
No
Tool calling
Yes
Structured output
No
File attachments
No
Access
Open weights
License
CC BY-NC 4.0
Rarity
Promo
Set number
788/1040
Open Cohere docsWeights on Hugging FaceWhere to run it 2Race it 134 tok/sMeet its creatureBattle Ring-1T

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 18, 2026. Official source: docs.cohere.com.

How good is it?

Public leaderboard scores for Tiny Aya Fire, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Tiny Aya Fire yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

1 provider sells Tiny Aya Fire through an API, and 1 Hugging Face host serves it. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
CohereOfficialtiny-aya-fire——8K

Hugging Face Inference Providers

HostInputOutputContextSpeedFirst token
Cohere———134 tok/s0.2s

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

More from Cohere

Cohere

North Small Translate

CTX33K
Text
TextInputFree
TextOutputFree

Open-weight translation model for more than 50 languages and locale variants

FreeCC BY-NC 4.01000/1040
Cohere

North-Micro-Vision-Instruct

SIZE2.5B
Vision
TextImageDownloads46K/mo
TextLikes150

Vision-language model from Cohere, 2.5B parameters.

Open weightsApache 2.0974/1040
Cohere

cohere-transcribe-arabic-07-2026

SIZE2.1B
Speech to text
AudioDownloads130K/mo
TextLikes230

Speech recognition model from Cohere, 2.1B parameters.

Open weightsApache 2.0927/1040
Cohere

North Mini Code

CTX256K
Reasoning · Tools
TextInputFree
TextOutputFree

Cohere coding model for practical software engineering and agentic edits

FreeApache 2.0921/1040
Cohere

Command A Plus

CTX128K
Reasoning · Vision · Tools
TextImageInput$2.50/M
TextOutput$10/M

Cohere's stronger command model for multilingual agents and enterprise workflows

Open weightsCC BY-NC 4.0901/1040
Cohere

cohere-transcribe-03-2026

SIZE2.1B
Speech to text
AudioDownloads120K/mo
TextLikes1.2K

Speech recognition model from Cohere, 2.1B parameters.

Open weightsApache 2.0837/1040
Cohere

Tiny Aya Water

CTX8K
Tools
TextDownloads520/mo
TextLikes47

Compact multilingual model specialized for European and Asia-Pacific languages

Open weightsCC BY-NC 4.0790/1040
Cohere

Tiny Aya Global

CTX8K
Tools
TextDownloads7.7K/mo
TextLikes180

Compact multilingual model balanced across 70 languages and regions

Open weightsCC BY-NC 4.0789/1040
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot