GPT-6.1 Sol pricing,
with your Codex usage in context.

What does GPT-6.1 Sol cost?

At Standard short-context rates, GPT-6.1 Sol costs $2 for uncached input, $0.10 for cached input, $2.50 for cache writes, and $10 for output per million tokens. GPT-6 Sol costs $0.20 for cached input, with the same other short-context rates. OpenAI model reference; GPT-6 Sol reference.

Cache reads are 50% cheaper than GPT-6 Sol. That does not mean every session is 50% cheaper: the total depends on uncached input, cache writes, output, and the fraction of input served from cache.

A worked cost estimate

Consider illustrative usage accumulated across Standard short-context requests: 100,000 uncached input tokens, 900,000 cached input tokens, and 20,000 output tokens, with no cache writes. These are example counts, not a benchmark.

Uncached input: 0.1M × $2

$0.20

Cached input: 0.9M × $0.10

$0.09

Output: 0.02M × $10

$0.20

GPT-6.1 Sol estimate

$0.49

The same token counts at GPT-6 Sol rates produce $0.58. The $0.09 difference comes entirely from cached input: about 15.5% lower total API-equivalent cost for this particular token mix. A single request above 272K input tokens would use the long-context rates instead.

Thinking tokens count toward billed output. RepoSpend separates visible output and reasoning when the local source exposes that split, then prices each once. Read the token accounting methodology.

Track GPT-6.1 Sol usage by repository

RepoSpend 0.1.6 adds an explicit GPT-6.1 Sol card so supported local usage no longer inherits GPT-6 Sol’s older cache-read rate. It reads existing local Codex files and groups usage by Git repository.

1. Run npx repospend with Node.js 20 or later. The dashboard usually opens at localhost:2005.
2. Choose your date range and Codex source, then inspect the Models view for gpt-6.1-sol.
3. Open Repos or Sessions to find where the usage came from. Compare token mix and cache reuse alongside the cost estimate.
4. Use Data Doctor or repospend doctor to check missing token detail, unpriced models, and source warnings. Review local pricing overrides in Settings if your rates differ.

Your local prompts, transcripts, and repository usage stay on your machine. This public website receives none of that data; website traffic uses Vercel Analytics.

API-equivalent cost is an estimate

A ChatGPT or Codex subscription follows its own limits and credit rules. Multiplying local tokens by API rates does not reconstruct your subscription bill, remaining allowance, or invoice.

RepoSpend uses Standard short-context rates by default. OpenAI charges higher rates above 272K input tokens per request, twice Standard for Fast, and half Standard for Batch and Flex; regional processing can add 10%. Tool fees and account-specific terms can also change the bill. Check the current pricing reference.

Local session totals cannot reliably reveal every request’s pricing tier. Compare models on the same task, count retries, and verify success with your own tests and review.