Llama 3 70B
ActiveOpen-weights 70B model for high-quality general use.
Overview
Llama 3 70B is Meta's 70-billion-parameter open-weights model, available under the Llama community license. Widely deployed through self-hosting and third-party inference providers.
History
Llama 3 70B was released on 2024-04-18.
Training & availability
Weights are publicly available under the Llama 3 Community License license, making this an open-weight model suitable for on-prem deployment and fine-tuning.
Capabilities
-
Context window: 128K tokens.
-
Max output: 8K tokens.
-
Input modalities: text.
Recommended for: math, agentic, open-source.
Limitations
- Text-only — cannot process images, audio, or video inputs.
Quick start
Minimal example using the OpenRouter API. Copy, paste, replace the key.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="sk-or-...",
)
resp = client.chat.completions.create(
model="meta/llama-3-70b",
messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)Benchmarks
Integrations & tooling support
- Tool calling
- Supported
- Structured outputs
- Not supported
Price vs quality
Performance trails frontier models. Pricing not publicly available — check the provider.
- Quality percentile
- 8.3%
- Effective price
- —
- Pricing breakdown
- — in
— out
Community ratings
Rate Llama 3 70B
Sign in to rate and review.
Comments
Sign in to leave a comment.