llama-3.3-70b-versatile API pricing
Blended at 3:1 input to output: $0.640 per million tokens.
Groq charges $0.590 per million input tokens and $0.790 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-versatile This model | Groq | $0.590 | $0.790 | 131,072 | $0.640 | ↗ |
| llama-3-70b-instruct | OpenRouter | $0.590 | $0.790 | 8,192 | $0.640 | ↗ |
| gpt-5-mini | OpenAI | $0.250 | $2.00 | 272,000 | $0.688 | ↗ |
| gpt-5.1-codex-mini | OpenRouter | $0.250 | $2.00 | 400,000 | $0.688 | ↗ |
| gpt-4.1-mini | OpenAI | $0.400 | $1.60 | 1,047,576 | $0.700 | ↗ |
| mistral-large-2512 | Mistral AI | $0.500 | $1.50 | 262,144 | $0.750 | ↗ |
| mistral-large-3 | Mistral AI | $0.500 | $1.50 | 262,144 | $0.750 | ↗ |
| deepseek-v3 | DeepSeek | $0.270 | $1.10 | 65,536 | $0.477 | ↗ |
| gpt-5.4-nano | OpenAI | $0.200 | $1.25 | 272,000 | $0.463 | ↗ |
Last checked . Methodology
Questions
How much does llama-3.3-70b-versatile cost per million tokens?
$0.590 per million input tokens and $0.790 per million output tokens. At a 3:1 input to output mix that blends to $0.640. Checked 12 Sept 2026.
What would llama-3.3-70b-versatile cost for a real workload?
A thousand requests a day at 2,000 input and 600 output tokens each comes to $49.62 a month.
What is the context window for llama-3.3-70b-versatile?
131,072 tokens of input, with up to 32,768 tokens of output.
llama-3-70b-instruct · gpt-5-mini · gpt-5.1-codex-mini · gpt-4.1-mini · mistral-large-2512 · All Groq models · Cost calculator