Llama 3.3 70B Instruct
Pricing updated daily · Last refreshed Oct 30, 2026Meta model with a 131K-token context window, priced at $0.10 per million input tokens and $0.32 per million output tokens.
At a glance
- Provider
- Meta
- Context window
- 131,072 tokens
- Max output
- 16,384 tokens
- Input price
- $0.10 / 1M tokens
- Output price
- $0.32 / 1M tokens
- Input types
- text
- Function calling
- Yes
- Released
- December 6, 2024
What it costs
Illustrative request sizes, not measurements of any real product. For your own volumes, use the cost estimator.
| Workload | Tokens in / out | Per request | Per 1,000 requests |
|---|---|---|---|
| Short chat reply | 1,000 / 500 | $0.000260 | $0.2600 |
| Question over retrieved documents | 8,000 / 500 | $0.000960 | $0.9600 |
| Summarise a long document | 50,000 / 1,500 | $0.0055 | $5.48 |
How it compares
- Input price ($0.10 per 1M tokens) is the 3rd lowest of 30 models in the catalogue.
- Output price ($0.32 per 1M tokens) is the 6th lowest of 30.
- Context window (131K tokens) is the 25th largest of 30.
- Maximum output (16K tokens) is the 23rd largest of 30.
- On blended price it is about the same price as the median Meta model in the catalogue.
These are rankings by listed price and size within this catalogue (blended price weights input 3:1 against output), not a measure of output quality.
Cheaper models with the same capabilities
Lower blended price, at least the same context window, and the same input types and function calling.
| Model | Provider | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|
| Llama 4 Scout | Meta | 1.31M | $0.10 | $0.30 |
More from Meta
| Model | Provider | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|
| Llama Guard 4 12B | Meta | 164K | $0.18 | $0.18 |
| Llama 4 Maverick | Meta | 524K | $0.188 | $0.652 |
| Llama 4 Scout | Meta | 1.31M | $0.10 | $0.30 |
| Llama 3.2 1B Instruct | Meta | 60K | $0.027 | $0.201 |
Try it with your own text
- Token counter: see how many tokens a prompt uses (exact for OpenAI models, labelled estimates for others).
- Context window visualizer: see how much of this model’s 131K window a prompt fills.
- Model comparison: sort and filter every model, and export to CSV.
Source: OpenRouter’s public model catalogue (meta-llama/llama-3.3-70b-instruct), read once a day. These are the prices OpenRouter charges; a provider’s own list price can differ, so check the provider before committing to a budget.