GPT-6 Astra - Kyma API

Overview

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.

Specs

Field	Value
Model ID	`gpt-6-astra`
Best for	Hardest reasoning and long-horizon agentic work
Context window	1.05M
Max output tokens	128K
Input modalities	Text, Image
Output modalities	Text
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Medium
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$13.50
Output	$67.50

Above a long prompt this model costs more per token, because the infrastructure serving it charges more there. The threshold is on the prompt, so you know which rate applies before you send.

Prompt length	Input	Output
Standard	$13.50	$67.50
Above 272,000 tokens	$27.00	$101.25

Use this when

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.

Pick something else when

You want the previous OpenAI flagship at a lower rate: use gpt-5.6-sol.
You want the best general default overall: use qwen-3.6-plus.

Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")

response = client.chat.completions.create(
    model="gpt-6-astra",
    messages=[{"role": "user", "content": "..."}],
    tools=[...],  # function calling supported
)

Agent query example

Ask the API which models fit, instead of hardcoding an id:

curl "https://kymaapi.com/v1/models?recommended_for=chat&tools=true&quality_tier=frontier-open"

FAQ

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.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ