Llama 3 70B API Pricing

Llama 3 70B 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.

What Llama 3 70B costs in practice

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

Use Llama 3 70B with LiteLLM

Call Llama 3 70B 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.

from litellm import completion

response = completion(
    model="vercel_ai_gateway/meta/llama-3-70b",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: llama-3-70b
    litellm_params:
      model: vercel_ai_gateway/meta/llama-3-70b
      # credentials: see the provider's LiteLLM docs page

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "llama-3-70b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Llama 3 70B FAQ

More Meta models

• Llama 3 70B Instruct Turbo$0.88 / $0.88 per 1M tokens
• Llama 3 8B Chat HF$0.20 / $0.20 per 1M tokens
• Llama 3.1 Nemotron 70B Instruct HF$0.88 / $0.88 per 1M tokens
• Llama 3.3 70B Instruct FP8 Fast$0.293 / $2.253 per 1M tokens
• Llama 3.3 70B Instruct FP8 Dynamic$0.72 / $0.72 per 1M tokens
• Llama 3.3 Nemotron Super 49B V1.5$0.10 / $0.40 per 1M tokens
• Llama 3.1 Nemotron 70B Instruct$0.60 / $0.60 per 1M tokens
• Llama 3.2 11B$0.16 / $0.16 per 1M tokens