GPT-6.1 Sol: API Pricing, Context Window and Specs
GPT-6.1 Sol is the middle model of OpenAI’s GPT-6 lineup, between GPT-6 Astra and GPT-6 Luna. OpenAI released it on September 29, 2026 as the successor to GPT-6 Sol, one week after that model launched.
The list price is the same as GPT-6 Sol: $2 per million input tokens and $10 per million output tokens. What changed is caching: cached input on GPT-6.1 Sol costs 5% of the input rate, half of what other GPT-6 models charge.
- Input
- $2
- Output
- $10
- Cached input
- $0.10
- Cache write
- $2.50
- Batch
- 50% off
- Over 272K input
- $4 / $15
USD per 1M tokens, standard tier. Source: OpenAI pricing, checked Oct 1, 2026.
Quick estimate
GPT-6.1 Sol pricing details
- Cache writes are billed at 1.25× the input rate ($2.50 per 1M tokens). Cache reads cost $0.10 per 1M tokens.
- Requests with more than 272K input tokens are billed at long-context rates for the whole request: $4 input, $0.20 cached input and $15 output per 1M tokens.
- Batch and Flex processing cost 50% of the standard rates: $1 input and $5 output per 1M tokens.
- Fast mode costs 2× the standard rates. Regional processing (data residency) adds 10%.
What GPT-6.1 Sol costs in practice
Standard-tier cost with no caching, for a few common request shapes.
| Workload | Tokens in / out | Per request | Per 10,000 requests |
|---|---|---|---|
| Chatbot | 500 / 300 | $0.004 | $40.00 |
| RAG Q&A | 4,000 / 500 | $0.013 | $130 |
| Coding agent | 30,000 / 2,000 | $0.08 | $800 |
| Summarization | 8,000 / 600 | $0.022 | $220 |
GPT-6.1 Sol specs
- Context window
- 1.05M
- Max output tokens
- 128K
- Released
- Sep 29, 2026
- API model ID
- gpt-6.1-sol
- Max input tokens
- 922K
- Knowledge cutoff
- Apr 30, 2026
- Input / output
- Text and image in, text out
- Reasoning effort
- low, medium (default), high, xhigh, max
- Tool calling
- Responses API only; Chat Completions without tools
From the official model page.
GPT-6.1 Sol vs similar models
| Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|
| GPT-6.1 Sol OpenAI | OpenAI | $2 | $10 | $0.10 | 1.05M |
| GPT-6 Sol OpenAI | OpenAI | $2 | $10 | $0.20 | 1.05M |
| GPT-6 Astra OpenAI | OpenAI | $10 | $50 | $1 | 1.05M |
| GPT-6 Luna OpenAI | OpenAI | $0.10 | $0.50 | $0.01 | 1.05M |
| Claude Sonnet 5.5 Anthropic | Anthropic | $2 | $10 | $0.20 | 1M |
| Gemini 3.1 Pro Preview Google | $2 | $12 | $0.20 | 1.05M | |
| Grok 4.7 xAI | xAI | $2 | $6 | $0.50 | 500K |
GPT-6.1 Sol FAQ
GPT-6.1 Sol costs $2 per million input tokens and $10 per million output tokens on the standard tier. Cached input costs $0.10 per million tokens, and requests over 272K input tokens are billed at $4 input and $15 output.
The list prices are identical at $2 input and $10 output per million tokens. GPT-6.1 Sol is cheaper when you use prompt caching: cached input costs $0.10 per million tokens versus $0.20 on GPT-6 Sol.
No. GPT-6.1 Sol is billed per token through the OpenAI API. Batch and Flex processing halve the price if you can wait for results.
The context window is about 1.05 million tokens, with up to 922K input tokens and 128K output tokens per request. Input beyond 272K tokens switches the whole request to long-context pricing.
Related tools
- LLM API pricing tableEvery model's input, output and cached rates in one sortable table.
- LLM Price ComparisonPut two to four models side by side: per-token rates, context window, discounts and what the same job costs on each.
- Cheapest LLM APIsRanked lists of the lowest-priced models overall, among flagships, with 1M-token context, with image input and with open weights.
- Token Cost CalculatorEnter a token count and see what that many input and output tokens cost on every model.
- LLM Cost CalculatorPick a workload and request volume, and compare the bill across models with caching and batch discounts.