Llama 3.3 70B Versatile API Pricing
- Input / output
- $0.20 / $0.50 per 1M tokens
- Context
- 128K tokens
As of October 21, 2026, Llama 3.3 70B Versatile costs $0.20 per 1M input tokens and $0.50 per 1M output tokens on Inference APIs. It has a 131,072-token context window.
Llama 3.3 70B Versatile 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.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Inference APIs | inferenceapis/llama-3.3-70b-versatile | $0.20 | $0.50 | 128K |
What Llama 3.3 70B Versatile costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Inference APIs | $0.65 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Inference APIs | $2.10 |
Llama 3.3 70B Versatile cost calculator
At Inference APIs's price ($0.20 input, $0.50 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $4.50 a day, about $135 a month. Change the numbers for your workload, or compare it with other models.
- Per request
- $0.00045
- Per day
- $4.50
- Per month (30 days)
- $135
Llama 3.3 70B Versatile features
- Function calling
- Image input
- Reasoning
Use Llama 3.3 70B Versatile with LiteLLM
Call Llama 3.3 70B Versatile 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="inferenceapis/llama-3.3-70b-versatile",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: llama-3.3-70b-versatile
litellm_params:
model: inferenceapis/llama-3.3-70b-versatile
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "llama-3.3-70b-versatile",
"messages": [{"role": "user", "content": "Hello!"}]
}'Llama 3.3 70B Versatile FAQ
How much does Llama 3.3 70B Versatile cost?
Llama 3.3 70B Versatile costs $0.20 per 1M input tokens and $0.50 per 1M output tokens on Inference APIs.
What is the context window of Llama 3.3 70B Versatile?
Llama 3.3 70B Versatile has a 131,072-token context window.
Which providers offer Llama 3.3 70B Versatile?
Llama 3.3 70B Versatile is available from Inference APIs through LiteLLM, using the model name inferenceapis/llama-3.3-70b-versatile.
How do I call Llama 3.3 70B Versatile with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="inferenceapis/llama-3.3-70b-versatile", 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.
What features does Llama 3.3 70B Versatile support?
Llama 3.3 70B Versatile supports function calling. It does not support image input and reasoning.
When did LiteLLM add Llama 3.3 70B Versatile?
Llama 3.3 70B Versatile was added to LiteLLM's model price file in December 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. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:
LiteLLM docs: Inference APIs.
Provider pages: Inference APIs.
