Submit
MetaOpen-weight·131K context·70B params·Llama 3 Community License

Llama 3.3 70B Instructmeta/llama-3-3-70b-instruct

Meta's Llama 3.3 70B Instruct matches or exceeds Llama 3.1 405B on several benchmarks at 6x smaller size. Most widely hosted open-weight model; available on every major inference platform at competitive per-token prices.

Cheapest blended:$0.88 / 1M tokenson Together.ai · 1 provider listed

Pricing across providers

Sort by:
ProviderInput /1MOutput /1MBlended /1MLatency p50FormatFreshnessAction

1 hosting hidden — prices older than 60 days are pending re-verification.

Affiliate disclosure: We may earn a commission from qualified signups. Pricing independence is enforced at the data layer — see our Editorial Independence Policy.

Works with

Point any of these clients at a hosting's base URL — they all speak at least one of this model's endpoint protocols (OPENAI_COMPATIBLE).

Capabilities

  • chat
  • coding
  • reasoning
  • multilingual
  • long_context

Languages: en, de, fr, it, pt, hi, es, th

Benchmarks

  • HumanEval0-shot pass@1 · official · source
    88.4%
  • MMLU5-shot · official · source
    86.8%

Code samples

Example using Together.ai — the cheapest hosting for this model as of last verification. Swap base_url and model to use a different provider from the matrix above.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.together.xyz/v1",
)

response = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct-Turbo",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Technical specs

Context
131K
Max output
4K
Parameters
70B
Release
2024-12-06
Training cutoff
2023-12-01
License
Llama 3 Community License
Hugging Face →Official blog →

Similar models

Compare with

  • Llama 3.3 70B Instruct vs Qwen3 72B Instruct
    Comparison planned — not yet published

Frequently asked

How much does Llama 3.3 70B Instruct cost?+
The cheapest public hosting is $0.88 per 1M blended tokens on Together.ai. 1 total providers are listed above with per-input / per-output / cached pricing.
Is Llama 3.3 70B Instruct open-source? Can I fine-tune it?+
Yes. Llama 3.3 70B Instruct is open-weight under the Llama 3 Community License license. Weights are available on Hugging Face for local inference, fine-tuning, and commercial use (see license for specific terms).
Is Llama 3.3 70B Instruct OpenAI-compatible?+
Most listed hostings expose an OpenAI-compatible API, so you can point an existing openai SDK client at the Provider's base_url and use the Provider's model name. See the Code Samples above for a copy-pasteable example.
What's the maximum context window for Llama 3.3 70B Instruct?+
The model supports up to 131,072 tokens of context (input + output). Some hosted versions may impose a smaller limit — check the "Context" column in the pricing matrix for each provider.