Speka
Start free
All models
chatMeta

Llama 3.2 3B Instruct

The smallest Llama instruct model — the cheapest way to run classification, routing and short replies at scale.

meta/llama-3.2-3b-instruct
Running· verified just now · 150ms

What is Llama 3.2 3B Instruct?

Llama 3.2 3B Instruct is Meta's chat model. The smallest Llama instruct model — the cheapest way to run classification, routing and short replies at scale. It runs on Speka's OpenAI-compatible /v1/chat/completions endpoint at $0.03 / 1M input and $0.03 / 1M output tokens, using the model ID meta/llama-3.2-3b-instruct.

Test it live

Live playgroundLlama 3.2 3B Instructin-browser demo

Test Llama 3.2 3B Instruct live

Send a message and watch the model respond. Multi-turn — it remembers the conversation.

How to call Llama 3.2 3B Instruct via the API

Speka exposes Llama 3.2 3B Instruct on an OpenAI-compatible /v1/chat/completions endpoint. Point any OpenAI SDK at https://speka.me/v1, set model to meta/llama-3.2-3b-instruct, and your existing code runs unchanged.

quickstart.py
from openai import OpenAI

client = OpenAI(
    base_url="https://speka.me/v1",
    api_key="sk-speka-live-...",  # your Speka key
)

resp = client.chat.completions.create(
    model="meta/llama-3.2-3b-instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
FAQ

Frequently asked questions

Llama 3.2 3B Instruct is Meta's chat model. The smallest Llama instruct model — the cheapest way to run classification, routing and short replies at scale. It is available on Speka's OpenAI-compatible API using the model ID meta/llama-3.2-3b-instruct.
On Speka, Llama 3.2 3B Instruct is priced at $0.03 / 1M input and $0.03 / 1M output tokens. Pricing is per-token with no subscription or seat fee — usage is billed against your plan's monthly allowance, then at the same rate with no overage penalty. Rates are current as of June 2026; check the pricing page for updates.
Speka exposes Llama 3.2 3B Instruct on an OpenAI-compatible /v1/chat/completions endpoint. Set base_url to https://speka.me/v1, supply your Speka key, and set model to "meta/llama-3.2-3b-instruct" in any OpenAI SDK — no other code changes are required.
Llama 3.2 3B Instruct supports a 128,000-token context window — roughly 96,000 words of input, suitable for long documents, multi-turn agents, and large-context tasks.
Yes. Llama 3.2 3B Instruct is served through Speka's OpenAI-compatible endpoint, so any application built on the OpenAI Python or Node.js SDK, LangChain, or LlamaIndex can call it by changing only the base URL and model ID.

More chat models

NVIDIA logo

Nemotron 3 Ultra 550B

NVIDIA
chat

NVIDIA's flagship open model: 550B parameters with 55B active per token. Frontier quality for demanding generation, analysis and agentic work.

nvidia/nemotron-3-ultra-550b-a55b
Input / 1M
$0.90
Output / 1M
$2.70
Open model
Meta logo

Llama 3.3 70B Instruct

Meta
chat

Meta's flagship 70B instruct model — 405B-class quality at a fraction of the cost. A dependable default for production chat.

meta/llama-3.3-70b-instruct
Input / 1M
$0.20
Output / 1M
$0.20
Open model
Meta logo

Llama 3.1 8B Instruct

Meta
chat

Fast, cheap and capable. Ideal for high-volume classification, routing and lightweight chat.

meta/llama-3.1-8b-instruct
Input / 1M
$0.05
Output / 1M
$0.05
Open model