Cohere: Tiny Aya Fire

Compact multilingual model specialized for South Asian languages

Model lab: Cohere
Model family: —

Model resources

Hugging Face

Modalitiestext → text

Context window8,000

Maximum output8,000

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to cohere/tiny-aya-fire.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "cohere/tiny-aya-fire"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Tiny Aya Fire API Pricing

Price currently unavailable

Performance

Measured on the Moduck gateway across live traffic, hour by hour over the last 24 hours. Time to first token is how long before anything appears; throughput is how fast the answer is written after that; end-to-end latency is the whole round trip. Figures are medians unless the card says otherwise.

Performance trends

Throughput92.2 tok/sCurrent

Time to first token1.2 sCurrent

End-to-end latency7.2 sCurrent

Throughput

Current92.2 tok/s

Window average90.1 tok/s

Time to first token

Current1.2 s

Window average1.4 s

End-to-end latency

Current7.2 s

Window average7.5 s

Tail latency (P99)

Current14.1 s

Window average16.8 s

Prompt cache hit rate

Current26.1%

Window average24.7%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime is the share of time at least one provider serving this model responded. Availability is stricter: the share of requests actually served. A provider that answers but fails part of the traffic lowers availability without lowering uptime. Both cover the last three days.

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Tiny Aya Fire Compare models

Model	Input price	Output price	Context window	Capabilities
Tiny Aya FireThis page	Price currently unavailable	Price currently unavailable	8,000	Text output · Tool calling
Command A Translate	USD 2 / 1M tokens	USD 8 / 1M tokens	8,000	Text output · Tool calling
Command A Reasoning	USD 0.504 / 1M tokens	USD 4.04 / 1M tokens	256,000	Text output · Reasoning · Tool calling
Command A	USD 2 / 1M tokens	USD 8 / 1M tokens	256,000	Text output
Command A	USD 2 / 1M tokens	USD 8 / 1M tokens	256,000	Text output · Tool calling

Model specifications

Input: text
Output: text
Context window: 8,000
Maximum output: 8,000
Release date: 2026-02-17
Attachments: No
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Tiny Aya Fire for?

Compact multilingual model specialized for South Asian languages

What inputs and outputs does Tiny Aya Fire support?

Recorded inputs: text; outputs: text.

How is Tiny Aya Fire priced?

This page does not list a price for this model yet.

What specifications are recorded for Tiny Aya Fire?

Current model records list Context window 8,000 tokens; Maximum output 8,000 tokens.

What model parameter does the Quickstart use?

The example uses cohere/tiny-aya-fire. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.