Context Window
131,072
Input tokens
Full-context input ≈ $0.01
Model Cost Profile
Developer: meta-llama· Tokenizer: Llama3 · Instruct: llama3 · Quantization: fp8
Canonical ID: meta-llama/llama-3.3-70b-instruct
Pricing updated Apr 23, 2026
Live Pricing
Input: $0.1000
Output: $0.3200
Last synced Apr 23, 2026 · MMLU score via public benchmark data
Meta's Llama 3.3 70B Instruct model, developed by meta-llama, offers a substantial context window of 131,072 tokens, making it ideal for applications requiring extensive text comprehension and generation, such as legal document analysis and long-form content creation. With an input price of $0.10 per 1 million tokens and an output price of $0.32 per 1 million tokens, teams can effectively manage their budgets while leveraging the model's capabilities for complex tasks. This pricing structure allows organizations to scale their usage according to project demands, optimizing costs while enhancing productivity in data-intensive environments.
Context Window
131,072
Input tokens
Full-context input ≈ $0.01
Max Output
16,384
Completion tokens
Input Price / 1M
$0.1000
Prompt tokens
Output Price / 1M
$0.3200
Completion tokens
Top Benchmark
71.3
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Meta: Llama 3.3 70B Instruct. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.1000
Current Output / 1M
$0.3200
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
99.2%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.1000 |
| Output (Completion) | $0.3200 |
Estimate monthly spend for Meta: Llama 3.3 70B Instruct based on your workload.
Estimated Monthly Cost
$6.34
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.