ParetoOct 14, 2026Beta
Pareto
Pareto is a blended model that runs several frontier models in parallel on every request and returns one answer. It accepts text and image inputs.
$1.00/$4.00
per 1M in / out
1M
context window
32K
max output
Time to first token—
Output speed—
Uptime—
Last 24 hours of Venice traffic.How it’s measured
Capabilities
What the model takes in, returns and supports through the API.
InTextImage
OutText
Streaming
Function callingstream: truetoolsVisionUp to 1 imagesWeb search
Prompt cachingReads at $0.0375enable_web_searchNot supportedstructured outputs, reasoning, video input, audio input, X search and log probabilities
Benchmarks
Specs
- Model ID
pareto- Endpoint
POST /api/v1/chat/completions- Context window
- 1,000,000 tokens
- Max output
- 32,768 tokens
- Reasoning
- None
- Precision
- Set by the provider
- Privacy
- Anonymized
- Weights
- Closed
- Added
- Oct 14, 2026
Compare
| Model | Input | Output |
|---|---|---|
| Pareto | $1.00 | $4.00 |
| Kimi K2.6 E2EE | $0.87 | $4.12 |
| Abliterated Large Flash | $1.25 | $2.50 |
| Gemini 3.8 Flash | $0.9375 | $4.69 |
| GPT-6.1 Terra | $1.00 | $5.00 |
Pricing
Billed per token in USD. Reasoning tokens bill as output.
Input$1.00per 1M tokens
Cached input$0.037596% off input
Output$4.00per 1M tokens
Estimate a workload
$0.004per request
$40.00for 10,000 requests
Blended price against similar models
Quickstart
OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "pareto",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'Base URL
https://api.venice.ai/api/v1Parameters
| Parameter | Values |
|---|---|
model | pareto |
messages | text · image_url |
max_completion_tokens | Up to 32,768 |
tools | Function definitions |
stream | true | false |
venice_parameters.enable_web_search | auto | on | off |