GPT-6 Astra Pro
GPT-6 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.
Input / output
$10.00 / $50.00
per 1M tokens
Context
1.05M
128K max output
Reasoning
low, medium, high, xhigh, max
default high
Cached input
$1.00
90% off input
Modalities
Text, image
out: text
Pricing
USD per 1M tokensInput
$10.00
$20.00 above 272K
Cached input
$1.00
$2.00 above 272K
Cache write
$12.50
$25.00 above 272K
Output incl. reasoning
$50.00
$75.00 above 272K
| Similar models | Input | Output |
|---|---|---|
| GPT-6 Astra Pro | $10.00 | $50.00 |
| Claude Fable 5.1 | $10.00 | $50.00 |
| Claude Fable 5 | $10.00 | $50.00 |
| Claude Fable 5.2 | $8.00 | $40.00 |
| GPT-6 Astra | $10.00 | $50.00 |
Prompt caching is automatic; see Prompt caching.
Specs
- Model ID
openai-gpt-6-astra-pro- Endpoint
POST /api/v1/responses- Context window
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Reasoning effort
reasoning_effort: low | medium | high | xhigh | max· default high · guide- Served precision
- Set by the upstream provider
- Added
- Sep 5, 2026
Capabilities
Modalities
- Text
- Input and output
- Image
- Input only · up to 10
- Audio
- Not supported
- Video
- Not supported
Features
- Streaming (SSE)
- Supported
- Function calling
- Supported
- Structured output (json_schema)
- Supported
- Reasoning effort
- low, medium, high, xhigh, max
- Prompt caching
- Supported
- Web search
- venice_parameters
- X search
- Not supported
- Log probabilities
- Not supported
- Fine-tuning
- Not supported
- Image generation
- Not supported
POST
/api/v1/responsesRecommendedPro and Codex models are Responses-native upstream. Use /responses for typed reasoning, tool-call and message items; /chat/completions stays fully supported.
curl https://api.venice.ai/api/v1/responses \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai-gpt-6-astra-pro",
"input": "Explain TEE attestation in two sentences.",
"reasoning": { "effort": "high" }
}'Privacy
Tier 1 · this model
Anonymized
Venice hides your identity and stores no prompts. OpenAI still sees the content.
Tier 2
Private
Not available
Tier 3
TEE
Not available
Tier 4
End-to-end encrypted
Not available