Short answer
GPT-6.1 Sol (gpt-6.1-sol) is the mid-tier GPT-6 model OpenAI released on September 29, 2026. OpenAI positions it as "near-Astra performance for complex work at a lower cost": it is the model to pick when GPT-6 Astra is too expensive for everyday coding and GPT-6 Luna is not strong enough. The official price is $2 per million input tokens and $10 per million output tokens, with a 1.05M-token context window. On TeamoRouter it is available under the same model ID at roughly 20–30% of the official price (the live price is on the model page), and works in Codex CLI by changing two lines in config.toml.
No card at all? You can also top up with USDT, USDC or ETH: click Pay with crypto in the top-up dialog and send it from Binance, OKX or any wallet. The minimum is $5 and no browser extension is needed. Step by step: Pay for Claude and GPT APIs with crypto (USDT).
Specs at a glance
From OpenAI's model page:
| GPT-6.1 Sol | |
|---|---|
| Model ID | gpt-6.1-sol |
| Released | September 29, 2026 |
| Context window | 1,050,000 tokens (max input 922,000) |
| Max output | 128,000 tokens |
| Knowledge cutoff | April 30, 2026 |
| Input / output | Text and images in, text out |
| Reasoning effort | low, medium (default), high, xhigh, max |
| Tool calling | Responses API; Chat Completions works without tools |
Since October 8 it also has an Ultrafast mode in the Responses API (service_tier: "ultrafast"), priced at 6x the standard rate.
Sol, Astra, or Luna
OpenAI's own guidance: start with GPT-6 Astra for the hardest reasoning and coding, choose GPT-6.1 Sol to balance intelligence and cost, and use GPT-6 Luna for cost-sensitive, high-volume work.
| Model | Official price (input / output per 1M) | Use it for |
|---|---|---|
| GPT-6 Astra | $10 / $50 | The hardest tasks, when quality matters more than cost |
| GPT-6.1 Sol | $2 / $10 | Everyday coding, refactors, reviews, agent work |
| GPT-6 Luna | $0.10 / $0.50 | Bulk and simple tasks: tests, docstrings, small edits |
GPT-6.1 Sol vs GPT-6 Sol. The official input and output prices are the same, so for new work there is little reason to stay on gpt-6-sol. Cached input costs a twentieth of fresh input ($0.10 vs $2 per million at list), which matters in Codex, where most of each request is repeated context. Codex does not switch models by itself: if your config.toml says gpt-6-sol, change it by hand.
Pricing
| Per 1M tokens | OpenAI list price |
|---|---|
| Input | $2.00 |
| Cached input | $0.10 |
| Output | $10.00 |
Prompts above 272K input tokens are billed at 2x input and 1.5x output for the whole request. TeamoRouter bills the same tokens at roughly 20–30% of these list prices; prices change with supply, and the current numbers are on the GPT-6.1 Sol model page.
Use it in Codex CLI
Put this in ~/.codex/config.toml and set your TeamoRouter key in OPENAI_API_KEY:
model_provider = "teamorouter"
model = "gpt-6.1-sol"
model_reasoning_effort = "medium"
[model_providers.teamorouter]
name = "TeamoRouter"
base_url = "https://api.teamorouter.com/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"
medium is OpenAI's default effort and is enough for routine edits; raise it to high or xhigh for a hard refactor. Inside a session, /model switches between gpt-6.1-sol, gpt-6-astra and gpt-6-luna. Step-by-step setup: Codex CLI guide.
Call the API directly
Responses API (use this one if you need tool calling):
curl https://api.teamorouter.com/v1/responses \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6.1-sol",
"reasoning": {"effort": "medium"},
"input": "Write a migration that adds an email column to the users table"
}'
OpenAI Python SDK:
from openai import OpenAI
client = OpenAI(base_url="https://api.teamorouter.com/v1", api_key="YOUR_KEY")
resp = client.responses.create(model="gpt-6.1-sol", input="Find the bug in this function: ...")
print(resp.output_text)
Chat Completions also accepts gpt-6.1-sol, but OpenAI does not support tool calling on that endpoint for this model. Full reference: API integration.
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, no browser extension needed (how to pay with crypto). The same key also works for Claude and Gemini.
FAQ
Is GPT-6.1 Sol better than GPT-6 Sol? OpenAI lists GPT-6.1 Sol as the current Sol model and describes it as near-Astra performance at a lower cost; at the same official price there is no reason to start new work on gpt-6-sol.
Which reasoning effort should I use? medium is the default. none and minimal are not supported on this model; xhigh and max cost more tokens and time and are worth it only for hard problems.
Does it accept images? Yes, text and image input; output is text only.
Codex says the model was not found. Check that config.toml has model_provider = "teamorouter" at the top and that OPENAI_API_KEY is set in the terminal that launched Codex.
Related
- GPT-6 Sol API: the previous Sol model and the Sol / Astra / Luna lineup
- GPT-6 Luna API: the cheapest GPT-6 model
- GPT-6 Astra pricing