Llama 3.3 70B pricing, context window and limits
Llama 3.3 70B costs $0.59 per million input tokens and $0.79 per million output tokens at Groq list price. It accepts up to 131,072 tokens of context and returns up to 32,768 tokens.
- Model id
groq/llama-3.3-70b-versatile - Snapshot
What does Llama 3.3 70B cost?
| Input | $0.59 |
|---|---|
| Output | $0.79 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Llama 3.3 70B read and write?
| Context window | 131,072 |
|---|---|
| Max output | 32,768 |
What can Llama 3.3 70B do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | No |
| Input | text |
| Output | text |
What does a request to Llama 3.3 70B cost?
| A typical request: 1,000 tokens in, 500 out | $0.00098 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0067 |
| 1,000 typical requests | $0.98 |
| 1 million tokens in and 1 million out | $1.38 |
Among 10 Groq models with a published price, Llama 3.3 70B is the 8th cheapest by input price. Its context window is the largest of 14. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Llama 3.3 70B through DVARA?
Configure the groq provider in the DVARA LLM Gateway and send the model id groq/llama-3.3-70b-versatile. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Groq models are there?
- Llama 3.1 8B$0.05 in · $0.08 out · 131K context
- Llama Prompt Guard 2 22M$0.03 in · $0.03 out · 512 context
- Compound Mini— in · — out · 131K context
- Prompt Guard 2 86M$0.04 in · $0.04 out · 512 context
- Compound— in · — out · 131K context
- GPT OSS 120B$0.15 in · $0.6 out · 131K context
- Canopy Labs Orpheus V1 English— in · — out · 4K context
- GPT OSS 20B$0.075 in · $0.3 out · 131K context
- Canopy Labs Orpheus Arabic Saudi— in · — out · 4K context
- Safety GPT OSS 20B$0.075 in · $0.3 out · 131K context
- ALLaM-2-7b$0 in · $0 out · 4K context
- Qwen3.6 27B$0.6 in · $3 out · 131K context
Which models from other providers are similar to Llama 3.3 70B?
These are the closest in context window and input price, one per provider.
- GLM-4.5Zhipu GLM · $0.6 in · $2.2 out · 131K context
- Qwen2.5 72B InstructAlibaba Qwen · $0.574 in · $1.721 out · 131K context
- Nano Banana 2Google Gemini · $0.5 in · $60 out · 131K context
- Magistral Small 1.2Amazon Bedrock · $0.5 in · $1.5 out · 128K context
- Mistral Medium 3Mistral AI · $0.4 in · $2 out · 131K context