Llama 3.3 70B API

Llama 3.3 70B is a large language model by Meta, available on the Venice API as llama-3.3-70b. It runs privately, with zero data retention.

Llama 3.3 70B API pricing

Model ID	Variant	Privacy	Price
`llama-3.3-70b`	Standard	Private	$0.70 input /$ 2.80 output per 1M tokens

Llama 3.3 70B specifications

Spec	Value
Provider	Meta
Released	Apr 6, 2025
Privacy	Private
Open weights	Yes
Context window	125K tokens
Max output	4K tokens
Served precision	FP8

How to use the Llama 3.3 70B API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "llama-3.3-70b" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'

Llama 3.3 70B API FAQ

How much does the Llama 3.3 70B API cost?

0.70 per 1M input tokens and

2.80 per 1M output tokens. Prices are in USD and can be paid in DIEM at parity.

What is the Llama 3.3 70B model ID?

Use llama-3.3-70b as the model parameter.

Is the Llama 3.3 70B API private?

Llama 3.3 70B is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

What is the context window of Llama 3.3 70B?

125K tokens of context, with up to 4K output tokens per response.

What does Llama 3.3 70B support?

Llama 3.3 70B supports function calling and web search.

Which endpoint does the Llama 3.3 70B API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

Llama 3.2 3B API: $0.15 input /$ 0.60 output per 1M tokens
Qwen 3 235B A22B Thinking 2507 API: $0.45 input /$ 3.50 output per 1M tokens
Kimi K2.5 API: $0.56 input /$ 3.50 output per 1M tokens
Hermes 3 Llama 3.1 405b API: $1.10 input /$ 3.00 output per 1M tokens
GLM 4.7 API: $0.55 input /$ 2.65 output per 1M tokens

Explore

By modality