GPT-6.2 Astra is the flagship model of the GPT-6.2 series from OpenAI, built for the hardest projects - real-world engineering, professional knowledge work, and scientific research. It is a reasoning model with thinking always on and selectable effort (max / xhigh / high / medium / low, default medium), a ~1.05M-token context window, text / image / file (document) input and text output, and up to 128K output tokens. It supports native tool calling, structured outputs, a verbosity control, seeded sampling, and the Responses and Anthropic Messages APIs. Input above 272K tokens is billed at a higher long-context tier.
OpenAI-compatible — keep the SDK you already use
https://api.orcarouter.ai/v1https://api.orcarouter.aiimport os
from openai import OpenAI
client = OpenAI(
base_url="https://api.orcarouter.ai/v1",
api_key=os.environ["ORCAROUTER_API_KEY"],
)
response = client.chat.completions.create(
model="openai/gpt-6.2-astra",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosity| Tier | Input / 1M tokens | Output / 1M tokens | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| ≤ 272K | $8.00 | $40.00 | $0.400 | $10.00 |
| ≤ ∞ | $16.00 | $60.00 | $0.800 | $20.00 |
| Tier selected by input token count of each request | ||||
Estimate based on list price
Tiered pricing — this estimate uses base-tier rates.
Estimate only — actual token counts depend on the provider's tokenizer.
GET /api/public/models/openai/gpt-6.2-astraOpen @misc{orcarouter_gpt_6_2_astra,
title = {GPT-6.2 Astra API},
author = {OpenAI},
year = {2026},
howpublished = {OrcaRouter},
url = {https://www.orcarouter.ai/models/openai/gpt-6.2-astra}
}OpenAI. (2026). GPT-6.2 Astra API. OrcaRouter. https://www.orcarouter.ai/models/openai/gpt-6.2-astra