Saltar al contenido principal

MetaAdded Apr 6, 2025PrivateOpen weights

Llama 3.3 70B

Llama 3.3 70B is Meta’s instruction-tuned 70-billion-parameter Llama model, which Meta reports performs close to its much larger Llama 3.1 405B on many tasks. It supports text input and output with a 128K-token context window, for chat, writing and code.

llama-3.3-70bPOST https://api.venice.ai/api/v1/chat/completions
Input / output
$0.70 / $2.80
per 1M tokens
Context
128K
4K max output
Reasoning
None
answers directly
Cached input
—
no prompt caching
Modalities
Text
out: text

Pricing

USD per 1M tokens
Input
$0.70
Output
$2.80
Similar modelsInputOutputOutput price, relative
Llama 3.3 70B$0.70$2.80
Qwen 3 235B A22B Thinking 2507$0.45$3.50
GLM 4.7$0.55$2.65
Gemini 3 Flash Preview$0.70$3.75
Qwen 3 Next 80b$0.35$1.90

Specs

Model ID
llama-3.3-70b
Endpoint
POST /api/v1/chat/completions
Context window
128,000 tokens
Max output
4,096 tokens
Reasoning effort
No separate reasoning phase
Served precision
FP8
Added
Apr 6, 2025
Weights
Open

Capabilities

Modalities
Text
Input and output
Image
Not supported
Audio
Not supported
Video
Not supported
Features
Streaming (SSE)
Supported
Function calling
Supported
Structured output (json_schema)
Not supported
Reasoning effort
Not supported
Prompt caching
Not supported
Web search
venice_parameters
X search
Not supported
Log probabilities
Not supported
Fine-tuning
Not supported
Image generation
Not supported
POST/api/v1/chat/completionsRecommended
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." }]
}'

Privacy

Tier 1
Anonymized

Included

Tier 2 · this model
Private

Zero data retention, enforced by contract. Prompts and outputs aren’t stored.

Tier 3
TEE

Not available

Tier 4
End-to-end encrypted

Not available