GPT-6 Astra
OpenAI's largest model for demanding tasks.
GPT-6 Astra is an OpenAI model with a 1M-token context window. It reads images and lets you choose how hard it thinks.
OpenAI
8 models
GPT-6 Astra in the OpenAI constellation, with GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.6 Terra and GPT-5.6 Luna.
A star's size and colour follow its API output price. OpenAI in the model list
Facts
- Context window
- 1M tokens
- Input
- Text and images
- Thinking effort
- Adjustable, up to Max
- Speed
- Deliberate
- Available on
- Plus and above
- Intelligence rank at Vani
- #2
Based on data from Artificial Analysis (artificialanalysis.ai). The ranking is Vani's ordering of the models it offers and is not endorsed by Artificial Analysis. Source (opens in a new tab)
Guide
Best for
- Hard problems
- Analysis
Good to know
- Heavy on your allowance
GPT-6 Astra API price
Use this model on the Vani API with the OpenAI- or Anthropic-compatible endpoints. Prepaid API prices per 1M tokens.
| Per 1M tokens | Official | On Vani |
|---|---|---|
| Input | $10.00 | $7.00 |
| Output | $50.00 | $35.00 |
| Cached input | $1.00 | $0.70 |
Official prices checked 30 Sept 2026. Source of the official prices (opens in a new tab)
In Vani Chat it uses your plan's allowance: tokens per plan.
GPT-6 Astra API quickstart
OpenAI-compatible: point any OpenAI SDK at https://api.vani.ai/v1 and send openai/gpt-6-astra as the model. The Anthropic-compatible /v1/messages endpoint works too.
curl https://api.vani.ai/v1/chat/completions \
-H "Authorization: Bearer $VANI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-6-astra","messages":[{"role":"user","content":"Hello"}]}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.vani.ai/v1",
api_key=os.environ["VANI_API_KEY"], # a vani_ key
)
reply = client.chat.completions.create(
model="openai/gpt-6-astra",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)import os
from anthropic import Anthropic
client = Anthropic(
base_url="https://api.vani.ai",
api_key=os.environ["VANI_API_KEY"], # a vani_ key
)
message = client.messages.create(
model="openai/gpt-6-astra",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello"}],
)
print(message.content)Compare with
OpenAI
GPT-6 Sol
GPT-6 Sol is an OpenAI model with a 1M-token context window. It reads images and lets you choose how hard it thinks.
1M context$7.00 output per 1M
Compare side by side with GPT-6 SolAnthropic
Claude Fable 5
Claude Fable 5 is an Anthropic model with a 1M-token context window. It reads images and lets you choose how hard it thinks.
1M context$35.00 output per 1M
Compare side by side with Claude Fable 5Moonshot AI
Kimi K3
Kimi K3 is a Moonshot AI model with a 1M-token context window. It lets you choose how hard it thinks.
1M context$10.50 output per 1M
Compare side by side with Kimi K3
GPT-6 Astra: questions
- What is GPT-6 Astra?
- GPT-6 Astra is an OpenAI model with a 1M-token context window. It reads images and lets you choose how hard it thinks.
- How large is GPT-6 Astra's context window?
- GPT-6 Astra has a context window of 1M tokens: that is how much it can read at once. It reads images as well as text.
- How much does the GPT-6 Astra API cost?
- On the prepaid Vani API, GPT-6 Astra costs $7.00 per 1M input tokens and $35.00 per 1M output tokens ($0.70 per 1M cached input tokens). In Vani Chat it uses your plan's allowance.
- Which Vani plan includes GPT-6 Astra?
- GPT-6 Astra is on Vani Chat's Plus plan and above.
Put a question to GPT-6 Astra.
GPT-6 Astra is on Vani Chat's Plus plan and above.