Llama 3.3 70B Instruct
Llama 3.3 70B Instruct is Meta's dense 70B model from December 2024 under the Llama 3.3 Community License: multilingual assistant-style chat and general text generation, officially in English, German, French, Italian, Portuguese, Hindi, Spanish and Thai, without a thinking mode. An older generation, but a well-understood one — many evaluation sets and prompts were tuned on it, which makes it a stable reference point. It is fulfilled through global providers under our European contract, and requests go only to backends that do not retain prompts or completions.
model id: llama-3.3-70b-instruct
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="llama-3.3-70b-instruct", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "llama-3.3-70b-instruct", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "llama-3.3-70b-instruct", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Price list, updated 12 September 2026. No minimum spend, no subscription.
About the model
- Developer
- Meta
- Released
- December 2024
- Licence
- Llama 3.3 Community License
- Architecture
- dense · 70B parameters
- Input
- text
- Reasoning
- no reasoning mode
- Knowledge cutoff
- December 2023
- Languages named by the developer
- English, German, French, Italian, Portuguese, Hindi, Spanish, Thai
Source: the developer's model card, as of 17 September 2026.
Licence: what it means for your company
Llama 3.3 Community License. Meta's own community licence, not an open-source licence: commercial use is allowed under its terms together with Meta's Acceptable Use Policy, and downloading the weights requires accepting both. Per the card, use in languages Meta does not list is the responsibility of whoever deploys the model.
A summary of the licence, not legal advice.
Benchmarks reported by the developer
- MMLU (CoT)
- 86
- IFEval
- 92.1
- HumanEval
- 88.4
- MGSM
- 91.1
Figures from the developer's model card, not our measurement. Source: huggingface.co/meta-llama/Llama-3.3-70B-Instruct
Technical details
- Context window
- 128K tokens
- Max output
- 65,536 tokens
- Throughput limit
- 200K tok/min
- Tokenizer
- Other
- Streaming
- yes
- Open weights
- meta-llama/llama-3.3-70b-instruct
- max_tokens
- 1 … 65536
- temperature
- 0 … 2
- top_p
- 0 … 1
- frequency_penalty
- -2 … 2
- presence_penalty
- -2 … 2
- stop
- array
- seed
- integer
This model is fulfilled through global providers under our European contract: one DPA with an EU company, one invoice for every model in the catalog, no US counterparty on your paperwork. Compute may run outside the EEA — if you need strict EEA-only processing, use our own-hardware model.
Questions about this model
›Where is Llama 3.3 70B Instruct computed?
Outside the EEA, through a global provider under our European contract. You get one DPA with an EU company and one invoice, but the compute itself does not run in the EEA — we state that instead of hiding it.
›Does Llama 3.3 70B Instruct store prompts and completions?
No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.
›How large is the Llama 3.3 70B Instruct context window?
128K tokens, with up to 65,536 tokens of output.
›What does Llama 3.3 70B Instruct cost?
$0.15 per million input tokens and $0.49 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on Llama 3.3 70B Instruct?
Yes, 200K tokens per minute. Higher limits are a question of volume, not of principle.
›Which languages does Llama 3.3 70B Instruct support?
The developer names English, German, French, Italian, Portuguese, Hindi, Spanish, Thai. Languages not on that list may still work, but they are not claimed — test on your own material first.
›Under which licence is Llama 3.3 70B Instruct released?
Llama 3.3 Community License. Meta's own community licence, not an open-source licence: commercial use is allowed under its terms together with Meta's Acceptable Use Policy, and downloading the weights requires accepting both. Per the card, use in languages Meta does not list is the responsibility of whoever deploys the model.
›Can reasoning be switched off in Llama 3.3 70B Instruct?
Llama 3.3 70B Instruct has no reasoning mode — it answers directly, which keeps latency and output tokens low.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| Llama 3.3 70B Instruct | Meta | 70B | 128K | Llama 3.3 Community License | $0.15 |
| Llama 3.1 8B Instruct | Meta | 8B | 128K | Llama 3.1 Community License | $0.08 |
| Qwen3 Next 80B A3B Instruct | Qwen (Alibaba) | 80B / 3B | 256K | Apache-2.0 | $0.14 |
| Qwen3 Coder Next | Qwen (Alibaba) | 80B / 3B | 256K | Apache-2.0 | $0.18 |
30 more models behind the same key and the same invoice.
Browse the catalog