Llama 3.3 70B Instruct
meta/llama-3.3-70b-instructLlama 3.3 70B Instruct is Meta's instruction-tuned, text-only multilingual model released on December 6, 2024, built on an optimized transformer with grouped-query attention and a 128K-token context. It is optimized for assistant-style multilingual dialogue in eight officially supported languages, including English, German, French, Spanish, Hindi and Thai. It is a static open-weight model with a December 2023 knowledge cutoff, and its license also permits synthetic data generation and distillation.
- Input price
- $0.10USD / 1M tokens
- Output price
- $0.32USD / 1M tokens
- Context window
- 131.1K
- Max output
- 16.4K
Try the model
Playground
Try a prompt
Your response will appear here
Choose an example or write a prompt, then click Run.
Model card
Specifications
Pricing
- Input
- $0.10 / 1M tokens
- Output
- $0.32 / 1M tokens
Context & modalities
- Context window
- 131,072 tokens
- Max output
- 16,384 tokens
- Input
- Text
- Output
- Text
Capabilities
- Chat
- Supported
- Vision
- Not supported
- Reasoning
- Not supported
- Structured output
- Supported
- Function calling
- Supported
- Audio input
- Not supported
Access
- Provider
- Meta
- Model ID
- meta/llama-3.3-70b-instruct
- Execution
- sync
- Base URL
- https://api.sandbase.ai
- API
- Chat Completions API
- Endpoint
- /v1/chat/completions
Independent evaluations
Benchmarks
Scores on standardized evaluations, compared with other models on SandBase.
Metrics sourced from Artificial Analysis · Intelligence Index v4.3
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/chat/completions" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "meta/llama-3.3-70b-instruct",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"Choose your model
Compare models
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
Llama 3.3 70B InstructThis model Meta | 128K | $0.10 | $0.32 | Dec 6, 2024 |
Meta | — | — | — | Dec 2, 2025 |
Meta | — | — | — | Nov 20, 2025 |
Questions
FAQ
How do I call Meta Llama 3.3 70B Instruct through SandBase?
Create a SandBase API key, then send requests with the model ID "meta/llama-3.3-70b-instruct" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.
How much does Meta Llama 3.3 70B Instruct cost?
$0.10 per 1M input tokens and $0.32 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.
What is the context window of Meta Llama 3.3 70B Instruct?
131.1K tokens of context, with up to 16.4K output tokens per response.
How does Meta Llama 3.3 70B Instruct score on benchmarks?
Meta Llama 3.3 70B Instruct scores 7.7 on the Artificial Analysis Intelligence Index (v4.3), ranking #80 of 84 models on SandBase; Coding Index 11.9. Source: Artificial Analysis, measured as Llama 3.3 Instruct 70B.
Which features does Meta Llama 3.3 70B Instruct support?
Meta Llama 3.3 70B Instruct supports function calling, structured output. See Specifications above for the full list.
Do I need a separate Meta account?
No. One SandBase API key and balance gives you access to Meta Llama 3.3 70B Instruct and the other models in the catalog; you do not need to sign up with Meta separately.