Meta: Llama 3.3 70B Instruct
Meta
Meta: Llama 3.3 70B Instruct by Meta costs $0.10 per 1M input tokens and $0.32 per 1M output tokens, with a 131K-token context window.
Pricing
Input (per 1M tokens)
$0.10
Output (per 1M tokens)
$0.32
Cached input (per 1M)
—
Specifications
- Provider
- Meta
- Context window
- 131K tokens
- Parameters
- —
- Released
- —
- Open weights
- —
- Frontier model
- No
- Hugging Face
- meta-llama/Llama-3.3-70B-Instruct
Benchmarks
- GPQA Diamond
- 47.4
Speed & latency
Time to first token
0.33s
Output speed
90 tok/s
Fastest host: scaleway (via hf-router).
Compare Meta: Llama 3.3 70B Instruct with…
Meta: Llama 3.3 70B Instruct vs Llama 3.2 3B Instruct$0.33/1MMeta: Llama 3.3 70B Instruct vs Gemini 1.5 Flash$0.31/1MMeta: Llama 3.3 70B Instruct vs Mistral Small 3.1$0.30/1MMeta: Llama 3.3 70B Instruct vs Qwen3 30B A3B Instruct 2507$0.30/1MMeta: Llama 3.3 70B Instruct vs Step 3.5 Flash$0.30/1MMeta: Llama 3.3 70B Instruct vs Gemma 4 26B A4B$0.30/1M
FAQ
How much does Meta: Llama 3.3 70B Instruct cost?
Meta: Llama 3.3 70B Instruct is priced at $0.10 per 1M input tokens and $0.32 per 1M output tokens. Output tokens cost more than input.
What is Meta: Llama 3.3 70B Instruct's context window?
Meta: Llama 3.3 70B Instruct supports a context window of 131K tokens — the maximum prompt plus response length it can handle in a single request.
Is Meta: Llama 3.3 70B Instruct open weight?
Open-weight status for Meta: Llama 3.3 70B Instruct is not recorded in our dataset.
Data as of 2026-10-29. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.