Llama3.1 70B API Pricing

Llama3.1 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 Llama3.1 70B costs in practice

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

100 long-document requests with 100,000 input and 2,000 output tokens each

Llama3.1 70B features

• Function calling

Use Llama3.1 70B with LiteLLM

Call Llama3.1 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="cerebras/llama3.1-70b",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: llama3.1-70b
    litellm_params:
      model: cerebras/llama3.1-70b
      api_key: os.environ/CEREBRAS_API_KEY

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "llama3.1-70b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Llama3.1 70B FAQ

More Meta models

• Llama3.1Free
• 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 Prompt Guard 2 22M$0.03 / $0.03 per 1M tokens
• Llama Prompt Guard 2 86M$0.04 / $0.04 per 1M tokens
• Llama 2 7B Chat HF LoraFree
• Llama 3.3 70B Instruct FP8 Fast$0.293 / $2.253 per 1M tokens