GPT-6.1 Sol
Use GPT-6.1 Sol at 30% of OpenAI's price: $0.60/1M input, $3.00/1M output. Compare with GPT-6 Sol and Astra, plus curl, Python, and Codex setup.
A codebase you don't know is a risk, not a hurdle. The plan should burn down that risk in order: understand, run, trace, spike, then make the change small enough that "production-ready" is a property you can demonstrate, not a hope.
Here are the first five steps, with the evidence you collect at each.
Step 1 — Get it building and the baseline green (half day)
Read the README, the manifest(s), the CI config, and any architecture docs. Boot the app locally, run the full test suite, run the linter/typechecker.
Evidence: The exact commands that reproduce a clean build and a passing test suite from a fresh checkout (recorded output, not memory of it). A one-page map you wrote yourself: where the entry points are, the layers, the build/test toolchain, and the main risks to your feature (e.g. "this touches cron jobs and payments").
Step 2 — Trace the smallest end-to-end slice that resembles your feature (half day)
Don't start with your feature. Pick a neighboring one that already works and follow it from entry to persistence. Note the conventions along the way: how errors surface, how config is injected, how logging is done, how tests are written.
Evidence: An annotated trace — file → function → what it does — for that slice. A written list of "conventions I must follow" (not intuitions; things you observed in real code). A named shortlist of the 3–5 files you will actually touch. If you can't produce this trace, you're not ready to write code.
Step 3 — Spike the core path (day 2)
Build the ugly version: hardcoded values, no error handling, no tests. The purpose is to confirm the path you traced in step 2 is real and to surface what you didn't know you didn't know.
Evidence: A working spike demonstrating the feature's central data path, alongside a list of every assumption the spike broke and what you corrected. That correction list is the most valuable document in this whole plan.
Step 4 — Write the contract before the code (half of day 2 / day 3)
Once the spike proves the path, pin down what production needs: the inputs/outputs, the error cases, where it sits in the conventions from step 2. Then write the tests — they'll be red, but they're the specification.
Evidence: A one-to-two-page design doc, an agreed interface/API shape (with the team if there is one), and a red test suite that encodes intended behavior. If you can't write the contract without consulting the code, you haven't finished step 2.
Step 5 — Implement in small, verified increments (days 3–4)
Replace the spike with the real thing in small commits, each one keeping the suite green, leaning on the existing patterns. Run lint/tests/typecheck per commit — CI, not just locally — and exercise the actual path against a real instance (staging or a local environment that isn't stubbed).
Evidence: A branch with progressive commits, each green in CI; coverage on the new code; something that proves it works against reality (a test result, a log trace, a screenshot); and a review by at least one person who knows the codebase. The review counts as evidence — an unfamiliar codebase has tribal knowledge you cannot extract from the files alone.
Steps 6+ would be the things that actually make it "shipped": a migration plan and its rollback, feature flagging, observability, the release and post-release verification. But the first five get you to a reviewed, green, working slice in staging — which is the point at which you can say "this will work in production" with evidence behind it, instead of a guess.
Run opens AI Chat with this prompt. Sign-in and credits are required.
Model details
Use the same model key in Playground, API requests, and internal workflows.
- Model ID
- gpt-6.1-sol
- Provider
- OpenAI
- Protocol
- OpenAI Chat Completions
- Context window
- 1,050,000 tokens
- Max output
- 128,000 tokens
What GPT-6.1 Sol is
GPT-6.1 Sol code samples
Try GPT-6.1 Sol in 3 steps
- 01
Set reasoning effort
Start at medium. Raise it to high, xhigh, or max for problems that need planning before answering, and lower it to low when latency matters more than depth.
- 02
Send a prompt
Paste your real task rather than a toy one. Token usage and credits consumed are reported under every response, so you can price the workload before committing.
- 03
Copy the API call
Move the same request into your code with model ID gpt-6.1-sol. Tool calling works on both Chat Completions and the Responses API.
FAQ
01How much does GPT-6.1 Sol cost on AIReiter?
GPT-6.1 Sol costs $0.60 per 1M input tokens and $3.00 per 1M output tokens on AIReiter, which is 30% of OpenAI's official $2.00 and $10.00. Cached input reads are $0.03 per 1M against the official $0.10, and cache writes are $0.75 per 1M. Requests above 272K input tokens are billed at 2x input and 1.5x output.
02What changed from GPT-6 Sol?
Base input and output prices are the same as GPT-6 Sol, but cached input is half the price, at 5% of the uncached rate instead of 10%. Reasoning effort gains a max setting, while the none and minimal settings are no longer supported. The context window, output limit, and long-context surcharge are unchanged.
03Is GPT-6.1 Sol better than GPT-6 Astra?
No. Astra remains OpenAI's most capable GPT-6 model, and GPT-6.1 Sol sits one tier below it. The case for Sol is cost: its short-context input and output prices are one fifth of Astra's, at $2 versus $10 input and $10 versus $50 output per 1M tokens. Route to Astra only where Sol measurably falls short.
04What is the context window?
GPT-6.1 Sol has a 1,050,000-token context window with up to 128,000 output tokens, and input and output share that budget. In practice the cheap part of the window is the first 272K input tokens: above that, the whole request is billed at 2x input and cache rates and 1.5x output.
05Which reasoning effort settings are supported?
GPT-6.1 Sol accepts low, medium, high, xhigh, and max, with medium as the default. The none and minimal settings that some earlier GPT models accepted are not supported. Higher settings produce more reasoning tokens, which are billed as output, so start at medium and raise it only for problems that need planning.
06Does GPT-6.1 Sol support tool calling?
Yes. On OpenAI's own API, GPT-6.1 Sol supports tool calling only through the Responses API, not Chat Completions. On AIReiter, tool calling works on both https://aireiter.com/api/v1/chat/completions and https://aireiter.com/api/v1/responses with model gpt-6.1-sol, so existing Chat Completions tool loops keep working unchanged.
07How do I use GPT-6.1 Sol in Codex CLI?
Add an aireiter provider to ~/.codex/config.toml with base_url https://aireiter.com/api/v1, wire_api set to responses, and env_key set to AIREITER_API_KEY, then set model to gpt-6.1-sol. Export your AIReiter key in that environment variable and start Codex. The full config is in the code section above.
08When was GPT-6.1 Sol released?
OpenAI released GPT-6.1 Sol on 29 September 2026 as an upgrade to GPT-6 Sol. It is available in the OpenAI API and in ChatGPT Work and Codex for paid plans. On AIReiter it is available in the playground and the API from launch, at 30% of the official per-token price.