The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
- Modalities
- text → text
- In / out per 1M
- Free / Free
- Context
- 131K tokens
- Added
- Dec 6, 2024
- Tokenizer
- Llama3
- Knowledge cutoff
- Dec 31, 2023
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | Free | — | Free |
| Output | Free | — | Free |
Providers
No provider breakdown is published for Llama 3.3 70B Instruct (free) in the current catalog snapshot (Jul 28, 2026). Browse all providers
Supported parameters
- frequency_penalty
- max_tokens
- presence_penalty
- stop
- temperature
- tool_choice
- tools
- top_k
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use
model meta-llama/llama-3.3-70b-instruct:free.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama/llama-3.3-70b-instruct:free",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="meta-llama/llama-3.3-70b-instruct:free",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "meta-llama/llama-3.3-70b-instruct:free",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);About Llama 3.3 70B Instruct (free)
Llama 3.3 70B Instruct (free) is Meta's 70B-parameter text-only model, tuned for instruction-following and multilingual tasks, with a 131,072-token context window and a knowledge cutoff of December 31, 2023. It supports tool calling and tool choice via the API, plus standard sampling controls like temperature, top_k, and top_p. There's no reasoning or benchmark data published for this variant, so treat it as a general-purpose chat and instruction model rather than a specialized reasoning one. At zero cost per token, it's suited to high-volume text tasks where you don't want per-token billing risk.
This is one of 25 free models on OpenKey, and its context window (131,072 tokens) is larger than 23% of the catalog — enough to fit a long report or codebase in one call. Compare that to its non-free sibling, Llama 3.3 70B Instruct, priced at $0.10/M input and $0.32/M output: same architecture, but you pay when you need guaranteed throughput or priority access instead of the free tier's typical rate limits. It also sits well above older siblings like Llama 3 8B Instruct ($0.14/M both ways) in parameter count, at no listed price difference since this variant is free.
Questions
- How much does Llama 3.3 70B Instruct (free) cost via API?
- It's free: $0 per 1M input tokens and $0 per 1M output tokens from the provider, and OpenKey's 3% fee on $0 is still $0. That makes it one of 25 free models available on OpenKey. If you need higher throughput or SLAs later, the paid Llama 3.3 70B Instruct is priced at $0.10/M input and $0.32/M output ($0.103/M and $0.3296/M after OpenKey's 3% fee).
- What is Llama 3.3 70B Instruct (free)'s context window?
- The context window is 131,072 tokens, large enough to hold a long technical document or a mid-size codebase in a single request. That's bigger than 23% of models in the OpenKey catalog. There's no separate max_completion_tokens limit specified, so output length is governed by the overall context budget.
- Is Llama 3.3 70B Instruct (free) free to use?
- Yes — both input and output tokens are priced at $0 through the provider, and OpenKey adds its flat 3% fee to provider pricing, which on $0 remains $0. It's one of 25 free models currently listed on OpenKey out of 329 total models. Free tiers typically come with lower rate limits than the paid version of the same model.
- Does Llama 3.3 70B Instruct (free) support tool calling?
- Yes, it supports tool calling — the model's supported parameters list includes both 'tools' and 'tool_choice'. It also accepts standard generation controls: temperature, top_p, top_k, frequency_penalty, presence_penalty, stop, and max_tokens. It's text-only, with text input and text output modalities — no image or audio support.
- What is Llama 3.3 70B Instruct (free)'s knowledge cutoff?
- Its knowledge cutoff is December 31, 2023, so it won't know about events, releases, or data after that date. This matches the base training cutoff for the Llama 3.3 70B family. For anything more recent, you'd need to supply context via retrieval or tool calls rather than relying on the model's built-in knowledge.
More from Meta AI
All Meta AI models →
Meta AILlama Guard 4 12B
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
ctx 164K in $0.185 out $0.185
Meta AILlama 4 Maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
ctx 1.0M in $0.154 out $0.618
Meta AILlama 4 Scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
ctx 10M in $0.103 out $0.309
Meta AILlama 3.3 70B Instruct
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
ctx 131K in $0.103 out $0.330