Kyma APIKyma API
OpenAI

OpenAI

GPT-6 Astra

GPT-6 Astra is OpenAI's GPT-6 flagship for the hardest reasoning and long-horizon agentic work. Reach for it when a task needs the strongest OpenAI model available and a 1.05M-token window.

Modalities

Text+Image → Text

Below release

Not established

Weights

Not published

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#67/69

$13.50

output $67.50 · cached $1.35

median $1.009 · best $0.0494

Price · output#67/69

$67.50

per 1M tokens generated

median $3.528 · best $0.2164

Availability · 30d—

Not measured yet

median 93.5% · best 100.0%

Throughput—

Not measured

probe median, one fixed prompt

median 39.4 tok/s · best 322.4 tok/s

Response time—

Not measured

probe median, to a complete answer

median 2.54 s · best 0.85 s

Context

1.05M

max output 128,000

published by OpenAI, not measured here

Tick above each rail is this model, below it the other 68. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#96

of 98 active models

Tokens served

0

all-time

Platform share

0.0%

of all tokens

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$13.50 /1M input$67.50 /1M output
Hobby10 req/day · 2K in / 500 out
~$18.23/mo
Production1,000 req/day · 2K in / 500 out
~$1,823/mo
Scale20,000 req/day · 2K in / 500 out
~$36,450/mo
+ Estimate your workload
1,000
2,000
500
30%

Estimated monthly cost

$1,604

$53.46 / day on GPT-6 Astra

Same workload on:

GPT-5.6 Sol Pro$365-77%
GPT-5.6 Sol$365-77%

Estimates use list pricing with cached input at this model's own cached rate. Actual bills depend on real token counts, and every response includes its exact cost.

When to use GPT-6 Astra

Updated 2026-09-12

Where this model earns its cost — and where it doesn't.

GPT-6 Astra went GA on 2026-09-04. OpenAI's model page lists a 1,050,000-token context window, 128,000 max output tokens, an April 30, 2026 knowledge cutoff and reasoning token support. Text is input and output; images are input only; audio and video are not supported.

On Kyma it is served through the OpenAI-compatible endpoint with exact cost reporting in the usage.cost field. Prompt caching is supported at this model's cached input rate. The rate doubles above 272K prompt tokens, exactly as OpenAI prices it.

It is a closed model available by API only. It is the successor to GPT-5.6 Sol in OpenAI's line-up and is priced above it.

Hardest reasoning

Multi-step analysis, proofs and planning where the strongest OpenAI model is the point.

Long-horizon agents

A 1.05M-token window and 128K output cap keep long agent sessions in one context.

Document and image understanding

Image input plus the long window for contracts, decks and screenshots.

Not ideal for: Cost-sensitive or high-volume traffic — this is a flagship rate, and prompts above 272K tokens bill at twice it.

How it compares

Against the peers people actually weigh it against.

SpecGPT-6 AstraGPT-5.6 Sol ProGPT-5.6 Sol
Input /1M$13.50$2.70$2.70
Output /1M$67.50$13.50$13.50
Context1M1M1M
ToolsYesYesYes
ReasoningYesYesYes
ThroughputNot measured54.7 tok/s28.8 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard. GPT-6 Astra needs a top-up — the signup credit covers the free tier.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-astra",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-astra",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of GPT-6 Astra?

GPT-6 Astra has a 1M-token context window — roughly 1544 pages of text in a single request.

How much does the GPT-6 Astra API cost?

$13.50 per 1M input tokens and $67.50 per 1M output tokens, with cached input at $1.35/1M — 90% off the input rate on repeated prompt prefixes. No subscription; you pay only for what you use.

Does GPT-6 Astra support function calling?

Yes — GPT-6 Astra supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

Are the weights for GPT-6 Astra publicly available?

No. OpenAI does not publish GPT-6 Astra's weights — it is reachable through an API rather than as a file you can download and run (https://developers.openai.com/api/docs/models/gpt-6-astra, read 2026-09-12). That is OpenAI's decision about their own product, not a limitation of Kyma.

Is GPT-6 Astra ever served below the precision its creator released it at?

Kyma cannot say, and for this model nobody can. OpenAI does not publish GPT-6 Astra's weights, so there is no released checkpoint whose precision a route could be measured against. We publish "not established" rather than reading a low format as a downgrade: on several models in this catalogue a low format is exactly how the creator ships it.

How do I use GPT-6 Astra?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to gpt-6-astra. Signing up is free, but this model needs a top-up: the $0.50 signup credit covers the free tier only.

How does GPT-6 Astra compare with GPT-5.6 Sol?

It is OpenAI's next flagship after Sol: the same 1.05M context and 128K output cap, a newer knowledge cutoff (April 30, 2026), and a higher rate. The Pricing table on this page has the current numbers.

Why does the price double above 272K prompt tokens?

OpenAI bills prompts above 272K tokens at its long-context rate, and Kyma passes that band through. The Pricing table on this page shows both rates.

Why use GPT-6 Astra through Kyma?

One API key and one OpenAI-compatible endpoint cover this and every other model on the platform, with prompt caching at the cached input rate and the exact cost of every request in usage.cost.

Needs a top-up — the signup credit covers the free tier.Create account →

More models by OpenAI

See all 12 →
ModelContextInputOutput
OpenAIGPT Transcribe—$0.006075 / min
OpenAIGPT-5.6 Terra1M$2.70$16.20
OpenAIGPT-5.6 Luna1M$0.27$1.62
OpenAIGPT-5.6 Luna Pro1M$0.27$1.62
OpenAIGPT-5.6 Terra Pro1M$2.70$16.20
OpenAIGPT-5.6 Sol1M$2.70$13.50
OpenAIGPT-5.6 Sol Pro1M$2.70$13.50
OpenAIGPT Image 2—$0.072 / image