OpenAINov 17, 2026New
GPT-6.2 Astra Pro
GPT-6.2 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra.
$8.00/$40.00
per 1M in / out
1.05M
context window
128K
max output
Capabilities
What the model takes in, returns and supports through the API.
InTextImage
OutText
Streaming
Function callingstream: truetoolsStructured outputsresponse_formatReasoningreasoning_effort low · medium · high · xhigh · maxVisionUp to 10 imagesWeb search
Prompt cachingReads at $0.40enable_web_searchNot supportedvideo input, audio input, X search and log probabilities
Performance
Measured on Venice API traffic over the last 24 hours.
Time to first token—
Output speed—
Uptime—
Pricing
Billed per token in USD. Reasoning tokens bill as output.
Input$8.00per 1M tokens
Cached input$0.4095% off input
Output$40.00per 1M tokens
Estimate a workload
$0.036per request
$360for 10,000 requests
Blended price against similar models
Specs
- Model ID
openai-gpt-62-astra-pro- Endpoint
POST /api/v1/responses- Context window
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Reasoning
low · medium · high · xhigh · max· default high- Precision
- Set by the provider
- Privacy
- Anonymized
- Weights
- Closed
- Added
- Nov 17, 2026
Compare
| Model | Input | Output |
|---|---|---|
| GPT-6.2 Astra Pro | $8.00 | $40.00 |
| Claude Fable 5.2 | $8.00 | $40.00 |
| Claude Fable 5.1 | $10.00 | $50.00 |
| GPT-6.2 Astra | $8.00 | $40.00 |
| Claude Fable 5 | $10.00 | $50.00 |
Other versions
- GPT-6 Astra ProSep 2026
- GPT-6.2 Astra ProNov 2026
Quickstart
OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.
curl https://api.venice.ai/api/v1/responses \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai-gpt-62-astra-pro",
"input": "Explain TEE attestation in two sentences.",
"reasoning": { "effort": "high" }
}'Base URL
https://api.venice.ai/api/v1Parameters
| Parameter | Values |
|---|---|
model | openai-gpt-62-astra-pro |
messages | text · image_url |
max_completion_tokens | Up to 128,000 |
reasoning_effort | low | medium | high | xhigh | max |
tools | Function definitions |
response_format | { type: |
stream | true | false |
venice_parameters.enable_web_search | auto | on | off |