Blog

Switching to GPT-6.2: Codex, the OpenAI SDK and Claude Code From GPT-6 Astra (2026)

Short answer

GPT-6.2 is live on TeamoRouter. gpt-6.2-astra and gpt-6.2-sol both answer to the key you already have — the base URL and key don't change. Switching Codex, the OpenAI SDK or Claude Code over is a model-name change, and it takes minutes.

Model OpenAI price (input / output per 1M) When to use it
gpt-6.2-astra $8 / $40 Hardest reasoning, long-context agent work
gpt-6.2-sol $2 / $10 Everyday coding and most other work, at a quarter of the price

Both have a 1,000,000-token context window. Prompts over 272K input tokens are billed at 2x input and 1.5x output. TeamoRouter's current price is on the pricing page.

New accounts start with a $0 balance — top up before your first request. Top up from $5. If a request returns 402 (400 on the OpenAI format) with "wallet balance is insufficient", your balance is empty — your base URL and key are fine. Top up and retry.

Call GPT-6.2 Astra and Sol with your existing key

Step 1: Check that your ID resolves

TeamoRouter's models page lists every model you can call with your key, and both gpt-6.2-astra and gpt-6.2-sol are on it.

If a request fails with an error instead of reaching a model, there are only two usual causes:

  • A typo in the ID, such as gpt-6.2-astra-2026 or any other name that doesn't exist.
  • A real ID we haven't enabled, which returns a model-not-found error. Fall back to gpt-6-astra for now, retry later, or contact support.

Step 2: Codex

Codex keeps the endpoint in ~/.codex/config.toml; it doesn't read OPENAI_BASE_URL. Here is the setup for GPT-6.2 Astra, with your TeamoRouter key in OPENAI_API_KEY:

toml
model_provider = "teamorouter"
model = "gpt-6.2-astra"

[model_providers.teamorouter]
name = "TeamoRouter"
base_url = "https://api.teamorouter.com/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"

There are two ways to switch:

  • Try it in one session without touching the file: codex -m gpt-6.2-astra. Your default model stays whatever you had.
  • Make it the default: change only the model = "..." line. The [model_providers.teamorouter] block stays as it is.

For the cheaper everyday tier, use gpt-6.2-sol in the same two places.

Full Codex, Cursor and Claude Code setup: GPT-6 Astra in Codex, Cursor and Claude Code.

Step 3: The OpenAI SDK

Read the model name from an environment variable instead of writing it into the code, so the next model change is one variable. Python:

python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.teamorouter.com/v1",
    api_key=os.environ["TEAMOROUTER_API_KEY"],
)
MODEL = os.environ.get("GPT_MODEL", "gpt-6.2-astra")

resp = client.responses.create(model=MODEL, input="Review this diff and list the risky changes: ...")
print(resp.output_text)

JavaScript:

js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.teamorouter.com/v1",
  apiKey: process.env.TEAMOROUTER_API_KEY,
});
const model = process.env.GPT_MODEL ?? "gpt-6.2-astra";

const resp = await client.responses.create({ model, input: "Review this diff and list the risky changes: ..." });
console.log(resp.output_text);

If you want the new model when it resolves and GPT-6 Astra when it doesn't, catch the error and retry once with the fallback:

python
import openai

def ask(prompt, model="gpt-6.2-astra", fallback="gpt-6-astra"):
    try:
        return client.responses.create(model=model, input=prompt)
    except openai.APIStatusError as err:
        if err.status_code in (400, 404) and model != fallback:
            return client.responses.create(model=fallback, input=prompt)
        raise

Chat Completions works the same way: client.chat.completions.create(model=MODEL, messages=[...]), with only the model name changing.

Step 4: Claude Code

Claude Code reaches GPT models through TeamoRouter's Anthropic-format endpoint. Point it at TeamoRouter once:

bash
export ANTHROPIC_BASE_URL="https://api.teamorouter.com"
export ANTHROPIC_AUTH_TOKEN="sk-teamo-your-key"

Then pick the model:

  • One session: claude --model gpt-6.2-astra.
  • Every session: export ANTHROPIC_MODEL="gpt-6.2-astra" and change the value later.

Claude Code shows a notice that a GPT model isn't in its built-in catalog and keeps the session within 200K tokens of context. That's expected; requests still go to the model you named.

Step 5: Try one real task before moving everything

  • One task first: run the same refactor or bug fix you ran on GPT-6 Astra, and compare the result and the cost in your usage records. Astra went from $10 / $50 to $8 / $40, so the same task bills noticeably less.
  • Try Sol for the everyday tier: for everything except the hardest work, gpt-6.2-sol is usually enough at a quarter of Astra's price. Run a week of real tasks on Sol and step back up only where quality falls short.
  • Keep the fallback: leave your configs on the model you had until the new one has handled a few real tasks.

What's known and what isn't

Settled: the two IDs are gpt-6.2-astra and gpt-6.2-sol, both are live on TeamoRouter, OpenAI's prices are $8 / $40 and $2 / $10, and both have a 1,000,000-token context window.

Not published yet: benchmarks for the 6.2 generation and the full detail of its reasoning levels. The rumored "Cyber" variant is not in the public API and isn't covered here.

Paying for usage

No subscription: you top up a balance from $5 and pay only for the tokens you use, by card or with USDT, USDC or ETH from any exchange app or wallet (how to pay with USDT). The same key also works for Claude, Gemini and DeepSeek.

FAQ

What's the GPT-6.2 model ID?

gpt-6.2-astra and gpt-6.2-sol, and both work on TeamoRouter today. The gpt-6.2-betelgeuse name from the leaked screenshot never shipped — ignore it.

Do I need a new key for GPT-6.2?

No. The same key and base URL work. Only the model name changes.

Will my Codex config break when I switch to GPT-6.2?

No. Your provider block doesn't change, and Codex keeps using whatever you put in model =.

Can I use GPT-6.2 on TeamoRouter today?

Yes. gpt-6.2-astra and gpt-6.2-sol are both live and work with your existing key. GPT-6 Astra, GPT-6.1 Sol and GPT-6.1 Terra are still there if you want to switch back.

Related

Ready to connect?Log in · top up · create an API key — three steps to start.
Switching to GPT-6.2: Codex, the OpenAI SDK and Claude Code From GPT-6 Astra (2026) · TeamoRouter