Llama 3.3 70B API pricing
Meta (Together.ai) model · Meta (Together.ai) on AIWiseRank
Short answer
Llama 3.3 70B by Meta (Together.ai) costs $1.04 per 1M input tokens and $1.04 per 1M output tokens, with a 128K token context window.
Prices updated Oct 23, 2026 (APIpulse, CC BY 4.0) · Benchmarks: ARC Prize, Vals.ai · all models
Input$1.04 / 1M
Output$1.04 / 1M
Context128K
Blended (3:1)$1.04 / 1M
API cost calculator
Enter your monthly usage in millions of tokens (1M tokens ≈ 750,000 words).
Llama 3.3 70B$12.48 / month$150 / year
Standard rates; batch processing and prompt caching can lower the bill.
Benchmarks
ARC-AGI-2 (reasoning)—
SWE-bench Verified (coding)—
Other Meta (Together.ai) models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Llama 4 Maverick | $0.27 | $0.85 |
| Llama 4 Scout | $0.18 | $0.59 |
Frequently asked questions
How much does the Llama 3.3 70B API cost?
Llama 3.3 70B costs $1.04 per 1M input tokens and $1.04 per 1M output tokens. A workload of 10M input and 2M output tokens a month costs $12.48.
What is the context window of Llama 3.3 70B?
Llama 3.3 70B supports a 128K token context window.