Llama 2 70B API Pricing

Llama 2 70B pricing by provider

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

What Llama 2 70B costs in practice

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

Use Llama 2 70B with LiteLLM

Call Llama 2 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="replicate/meta/llama-2-70b",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: llama-2-70b
    litellm_params:
      model: replicate/meta/llama-2-70b
      # 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-2-70b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Llama 2 70B FAQ

More Meta models

• Llama 2 7B Chat HF LoraFree
• Llama 2 13B$0.10 / $0.50 per 1M tokens
• Llama 2 7B$0.05 / $0.25 per 1M tokens
• Llama 2 7B Chat$1.923 / $1.923 per 1M tokens
• Llama 2 13B Chat HF$0.25 / $0.25 per 1M tokens
• Llama 2 70B Chat HF$1 / $1 per 1M tokens
• Llama 2 7B Chat HF$0.15 / $0.15 per 1M tokens
• Llama 2 13B Chat$0.10 / $0.50 per 1M tokens