TokenSpend
All models

OpenAI

GPT-6 Astra

images

Model id

openai/gpt-6-astra
Try in playgroundGet API key
Input
$10
per M · $20 past 272K context
Output
$50
per M · $75 past 272K context
Cache read
$1
per M tokens
Context
1,050K
tokens

Registry contract

Capabilities

Protocols
3
Chat · Responses · Messages · streaming
Tools
2
Chat · Messages
JSON Schema
None
Not supported
Vision
Yes
Chat · Responses · Messages
Reasoning
1
Chat
Output limit
128,000
tokens
Input limit
922,000
tokens

canonical openai/gpt-6-astra · revision openai/gpt-6-astra · aliases gpt-6-astra

Provider list price

Pricing

Input$10 / M tokens
Output$50 / M tokens
Cache read$1 / M tokens
Cache write$12.5 / M tokens
Past 272K prompt tokens$20 in / $75 out per M$2 cache read$25 cache write
RoutingFree

Provider list price. BYOK bills your provider; managed credits draw down at these rates. No markup or request fee. Every request is metered per engineer and joined to shipped work.

Registry 2026-09-15.1 · effective 9/15/2026 · OpenAI API pricing

First request

Run it

Python · TokenSpend SDK

from tokenspend import TokenSpend

client = TokenSpend()
resp = client.chat.completions.create(
    model="openai/gpt-6-astra",
    messages=[{"role": "user", "content": "hello"}],
)

TypeScript · TokenSpend SDK

import { TokenSpend } from "@tokenspend/sdk";

const client = new TokenSpend();
const resp = await client.chat.completions.create({
  model: "openai/gpt-6-astra",
  messages: [{ role: "user", content: "hello" }]
});

curl

curl https://api.tokenspend.dev/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $TOKENSPEND_API_KEY" \
  -d '{"model":"openai/gpt-6-astra","messages":[{"role":"user","content":"hello"}]}'

Claude Code integration

export ANTHROPIC_BASE_URL=https://api.tokenspend.dev
export ANTHROPIC_API_KEY=$TOKENSPEND_API_KEY
export ANTHROPIC_MODEL=openai/gpt-6-astra

One request shape reaches every model. Claude Code connects as an integration with two environment variables. Prompts are not stored unless you enable request logging.