llama-3.3-70b-instruct API pricing
Blended at 3:1 input to output: $0.155 per million tokens.
OpenRouter charges $0.100 per million input tokens and $0.320 per million output tokens. 2 of the models nearest it in price are cheaper on a blended basis.
Against the models nearest in price
Blended at a 3:1 input to output ratio.
| Source | ||||||
|---|---|---|---|---|---|---|
| llama-3.3-70b-instruct This model | OpenRouter | $0.100 | $0.320 | 131,072 | $0.155 | ↗ |
| llama-4-scout | OpenRouter | $0.100 | $0.300 | 1,310,720 | $0.150 | ↗ |
| llama-4-scout-17b-16e-instruct | Groq | $0.110 | $0.340 | 131,072 | $0.168 | ↗ |
| gpt-5-nano | OpenAI | $0.050 | $0.400 | 272,000 | $0.138 | ↗ |
| gemini-2.0-flash | Google AI | $0.100 | $0.400 | 1,048,576 | $0.175 | ↗ |
| gemini-2.0-flash-001 | OpenRouter | $0.100 | $0.400 | 1,048,576 | $0.175 | ↗ |
| gemini-2.5-flash-lite | Google AI | $0.100 | $0.400 | 1,048,576 | $0.175 | ↗ |
| gemini-2.5-flash-lite-preview-06-17 | Google AI | $0.100 | $0.400 | 1,048,576 | $0.175 | ↗ |
| gemini-2.5-flash-lite-preview-09-2025 | Google AI | $0.100 | $0.400 | 1,048,576 | $0.175 | ↗ |
Last checked . Methodology
Questions
How much does llama-3.3-70b-instruct cost per million tokens?
$0.100 per million input tokens and $0.320 per million output tokens. At a 3:1 input to output mix that blends to $0.155. Checked 12 Sept 2026.
What would llama-3.3-70b-instruct cost for a real workload?
A thousand requests a day at 2,000 input and 600 output tokens each comes to $11.76 a month.
What is the context window for llama-3.3-70b-instruct?
131,072 tokens of input, with up to 16,384 tokens of output.
llama-4-scout · llama-4-scout-17b-16e-instruct · gpt-5-nano · gemini-2.0-flash · gemini-2.0-flash-001 · All OpenRouter models · Cost calculator