Zum Hauptinhalt springen

OpenAIAdded Sep 5, 2026Anonymized

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.

openai-gpt-6-astra-proPOST https://api.venice.ai/api/v1/responses
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 tokens
Input
$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 modelsInputOutputOutput price, relative
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/responsesRecommended

Pro 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