skip to content

GPT-6 Astra

model idgpt-6-astra

Get an API keyAll models

01·price

Price per 1M tokens

What Conifer charges, in US dollars, as the gateway's public catalog lists it. A struck figure is the list price.

billedusdper
Input$10 $91M tokens
Output$50 $451M tokens
Cache read$1 $0.91M tokens
Cache write$12.5 $11.251M tokens

Above 272,000 input tokens

Once a request’s input, fresh plus cached tokens, is above 272,000, the whole request bills at these rates.

billedusdper
Input$20 $181M tokens
Output$75 $67.51M tokens
Cache read$2 $1.81M tokens
Cache write$25 $22.51M tokens

02·the model

From the catalog

Model id
gpt-6-astra
Provider
openai
Context window
1,050,000 tokens
Max output
128,000 tokens
Capabilities
toolsvisionreasoning

03·a request

Call it

POST /v1/chat/completions, with your key in $CONIFER_API_KEY. To point an existing client at the gateway, see Replace your provider key.

terminal
curl https://api.conifer.build/v1/chat/completions \
  -H "Authorization: Bearer $CONIFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-astra",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "three names for a build cache"}]
  }'

04·more

Elsewhere on Conifer

  • All modelsEvery model Conifer serves, with its prices.
  • GatewayOne API key and endpoint, with the model and cost stated on every response.
  • RouterA model picked for each request from a pool you approve.