Cohere

Tiny Aya Fire

Generally availableOpen weights8K context

Summary

Tiny Aya Fire is an open-weight language model from Cohere, released on 17 Feb 2026. It accepts text and generates text, with a 8K-token context window and up to 8K output tokens per response.

Compact multilingual model specialized for South Asian languages

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperCohere
Release date17 Feb 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window8K (8,000 tokens) [models.dev]
Max output8K tokens [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]
Structured outputNo [models.dev]

Tiny Aya Fire API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Cohere API
tiny-aya-fire
–––8Kmodels.dev, 18 Nov 2026

Frequently asked questions

What is the context window of Tiny Aya Fire?

Tiny Aya Fire has a context window of 8,000 tokens (8K) and can generate up to 8,000 tokens in a single response, according to models.dev.

Is Tiny Aya Fire open source?

Tiny Aya Fire is an open-weight model. Check the license terms before commercial use.

When was Tiny Aya Fire released?

Cohere released Tiny Aya Fire on 17 Feb 2026, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
DeepSeek OCR 2DeepSeek27 Jan 20268K$0.03$0.03Open
llama-nemotron-embed-vl-1b-v2NVIDIA18 Dec 20258K––Open
Hy-MT2-1.8BTencent (Hunyuan)21 May 20268K$0.04$0.18Open
Hy-MT2-30B-A3BTencent (Hunyuan)21 May 20268K$0.07$0.29Open
llama-nemotron-rerank-vl-1b-v2NVIDIA18 Dec 202510K––Open
olmOCR 2 7BAllenai22 Oct 20258K––Open

Change history

  • Structured output changed from none to no

Sources