Llama 3 8B API Pricing

As of October 10, 2026, Llama 3 8B costs $0.05 per 1M input tokens and $0.25 per 1M output tokens from Replicate, the lowest of 3 providers. It has an 8,086-token context window and returns up to 8,086 tokens per response.

By MetaModel ID replicate/meta/llama-3-8bPrices updated October 10, 2026Checked October 10, 2026

Input: $0.05 / 1M tokens
Output: $0.25 / 1M tokens
Context window: 8,086 tokens
Max output: 8,086 tokens
Providers: 3
Added to LiteLLM: May 2024

Llama 3 8B pricing by provider

3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

Provider	Model name in LiteLLM	Input	Output	Context
Replicate	`replicate/meta/llama-3-8b`	$0.05	$0.25	8K
Snowflake Cortex	`snowflake/llama3-8b`	–	–	8K
Vercel AI Gateway	`vercel_ai_gateway/meta/llama-3-8b`	$0.05	$0.08	8K

What Llama 3 8B costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Replicate	$0.225
Vercel AI Gateway	$0.14

Use Llama 3 8B with LiteLLM

Call Llama 3 8B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK

from litellm import completion

response = completion(
    model="replicate/meta/llama-3-8b",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: llama-3-8b
    litellm_params:
      model: replicate/meta/llama-3-8b
      # credentials: see the provider's LiteLLM docs page

Call the proxy

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "llama-3-8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Llama 3 8B FAQ

How much does Llama 3 8B cost?

Llama 3 8B costs $0.05 per 1M input tokens and $0.25 per 1M output tokens from Replicate, the lowest of 3 providers.

What is the context window of Llama 3 8B?

Llama 3 8B has an 8,086-token context window and returns up to 8,086 tokens per response.

Which providers offer Llama 3 8B?

Llama 3 8B is available from 3 providers through LiteLLM: Replicate, Snowflake Cortex and Vercel AI Gateway.

How do I call Llama 3 8B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="replicate/meta/llama-3-8b", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add Llama 3 8B?

Llama 3 8B was added to LiteLLM's model price file in May 2024.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.

LiteLLM docs: Replicate, Snowflake Cortex, Vercel AI Gateway.

Provider pages: Replicate, Snowflake Cortex, Vercel AI Gateway.