Claude models and GPT-5.6 Luna are now available to accounts that have topped up at least once. Top up any amount to unlock them — bonus credits can pay for them too. All other models are unaffected.Top up
OpenAI

GPT-6 Astra

Save 90%Official

openai/gpt-6-astra

Also callable as gpt-6

OpenAI's newest flagship — the top of the GPT-6 line.

Context window
1.1M
Max output
128K
Input modalities
text · image
Output modalities
text
Capabilities
Vision · Reasoning · Tool calling · Coding · Prompt cache · Paid cache writes · Strip Responses Summary Input
Upstream release
2026-09-03
RouteMux name
openai/gpt-6-astra
Live model playground

Try GPT-6 Astra here

Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.

streamchat
1Configure input
0 / 20,000
Add images

Sign in first to upload images to this vision model.

Maximum estimated cost
2Live result

Your result will appear here

Enter an input on the left. The same RouteMux Playground execution and billing path powers this embedded test.

conversation

What is GPT-6 Astra

GPT-6 Astra is OpenAI's newest flagship, released in September 2026 and sitting a full generation above the GPT-5.6 line. It is the model you reach for when the task is hard enough that a cheaper model burns more tokens failing than Astra costs succeeding — deep multi-step reasoning, large refactors, and agent loops that have to stay coherent over long horizons.

It carries a 1.05M-token context window with 128K of output headroom, accepts text and image input, and exposes reasoning effort as a request parameter from low all the way up to max. Explicit prompt caching is supported, and cache reads are billed at a tenth of the input rate.

Through RouteMux it is $1 per 1M input tokens against OpenAI's $10, and $5 against $50 on output — a launch rate at a tenth of list price. The same model is reachable over three protocols: OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages, so an Anthropic-shaped client can call it without rewriting its request layer.

GPT-6 Astra API pricing

Source: openai_x0.10 · Verified 2026-09-05

InputOfficial $10 / M tokens
$1/ M tokensSave 90%
OutputOfficial $50 / M tokens
$5/ M tokensSave 90%

Fast $2 / $10 /M

Cache read $0.1/M · Cache write $1.25/M

TierInputCache readCache writeOutput
Standard ≤272K$1$10−90%$0.1$1−90%$1.25$12.5−90%$5$50−90%
Standard >272K$2$20−90%$0.2$2−90%$2.5$25−90%$7.5$75−90%
Priority ≤272K$2$20−90%$0.2$2−90%$2.5$25−90%$10$100−90%

Estimate cost

Estimated cost$0.015

Limited time20% extra Credits on your first top-up — up to 200 bonus Credits

Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.

Sign up and claimNo subscription. Pay for what you use.

Key capabilities

1.05M-token context

Large enough to hold a repository or a long document set in one request, with 128K of output headroom.

Reasoning effort up to max

Effort is a request parameter spanning low, medium, high, xhigh and max — the same deployment can run cheap on easy turns and deep on hard ones.

Explicit prompt caching

Cache breakpoints are supported, and cache reads bill at a tenth of the input rate.

Three protocols

OpenAI Chat, OpenAI Responses, and Anthropic Messages all route to this model.

Interface and protocols

OpenAI Chat CompletionsStreamingOpenAI ResponsesStreamingAnthropic MessagesStreaming

Use any of these IDs to call this model via the API.

RouteMux nameopenai/gpt-6-astra
Common namegpt-6

Replace the ROUTEMUX_KEY placeholder with your API key. Create one →

from openai import OpenAI

client = OpenAI(
    base_url="https://api.routemux.com/v1",
    api_key="<ROUTEMUX_KEY>",
)

completion = client.chat.completions.create(
    model="openai/gpt-6-astra",
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)
base_url: https://api.routemux.com/v1

Performance (last 30 days)

GPT-6 Astra FAQ

What is GPT-6 Astra?

OpenAI's newest flagship — the top of the GPT-6 line.

How large is the context window of GPT-6 Astra?

GPT-6 Astra supports a context window of up to 1.1M tokens, with up to 128K output tokens per request.

How much does the GPT-6 Astra API cost?

Through RouteMux, GPT-6 Astra costs $1 for input and $5 for output (USD per 1M tokens), below the official list price.

How do I call GPT-6 Astra via API?

GPT-6 Astra is OpenAI-compatible: point your base URL at RouteMux and set the model field to openai/gpt-6-astra — no code changes needed.

Which input and output modalities does GPT-6 Astra support?

GPT-6 Astra accepts text, image as input and produces text as output.

When was GPT-6 Astra released?

GPT-6 Astra was released on September 3, 2026.

How is it different from GPT-5.6 Sol?

Astra is a generation newer and sits above the whole GPT-5.6 line. The context window is the same 1.05M, but Astra costs more per token, so Sol remains the better default for work that does not need the extra capability.

Which reasoning effort levels are supported?

low, medium, high, xhigh and max. Unlike the GPT-5.6 line, Astra does not accept an effort of none — reasoning cannot be switched off entirely.

Does the price change above 272K input tokens?

Yes. Requests whose input exceeds 272K tokens bill the whole request at the long-context rate, which OpenAI sets at roughly double for input. The pricing section above lists both tiers.

Sources