openai · CODEX
GPT-6.2 Sol API Pricing
Check the model ID and provider reference rates for GPT-6.2 Sol, along with current pricing availability on CODEX.
How to use GPT-6.2 Sol for coding
GPT-6.2 Sol fits developers turning a well-defined task into a patch and running targeted tests. For an API pagination change in Codex CLI, include the current handler, cursor format, and expected behavior when a result page is empty.
Use Codex CLI with an AI in IDE CODEX key. View setup guide
In the Codex CLI config.toml, set model to gpt-6.2-sol and wire_api to responses under the AI in IDE provider. Store the dashboard API key as OPENAI_API_KEY in auth.json. Start Codex in the project directory and use a short test prompt to verify your configuration.
Example API cost at the provider’s standard rate is $0.10 for 35,000 uncached input tokens and 3,000 output tokens. This example assumes no cache usage or paid tools.
Effective CODEX API rates
USD per 1M tokens. Quota rates use the current AI in IDE base price × 1. Provider prices as of 2026-11-18.
| AI in IDE quota rate | Reference provider rate | |
|---|---|---|
| Input | $2.00 | $2.00 |
| Cache read | $0.10 | $0.10 |
| Output | $10.00 | $10.00 |
Use GPT-6.2 Sol in your client
Create a CODEX API key in your dashboard, replace YOUR_DASHBOARD_API_KEY, and run this request in a Bash-compatible terminal. The key and its funding source need a positive balance; this request consumes quota.
This example includes all the text needed for the task. It does not read your local project.
curl --globoff --fail-with-body 'https://api.aiinide.com/responses' \
-H "Authorization: Bearer YOUR_DASHBOARD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-6.2-sol","reasoning":{"effort":"low"},"input":"Rewrite this sentence in plain English: The application facilitates the modification of account settings.","max_output_tokens":4096}'Check for status: "completed" and an output_text item in output[].content[], such as “The app lets you change your account settings.” Wording may vary. If the status is incomplete, check incomplete_details.reason. The output limit includes reasoning tokens; increase it if they exhaust the limit. Then check your usage records.
View setup guideExample: usage versus a top-up purchase
Each row uses a 3:1 input-to-output mix and no cache reads. Quota consumed is the cost of that mix. The top-up column is a separate purchase.
| Monthly tokens | Reference API cost | Quota this example consumes | Smallest top-up that covers it |
|---|---|---|---|
| 1M | $4.00 | $4.00 | 62.5 dollars of quota, priced at $7.99 |
| 10M | $40.00 | $40.00 | 62.5 dollars of quota, priced at $7.99 |
| 100M | $400.00 | $400.00 | 406.25 dollars of quota, priced at $49.18 |
The quota column is what this token mix consumes. The top-up column is the smallest purchase the slider accepts: $62.5, then steps of $31.25. A small task does not cost that purchase. Examples round top-up quota up to the next $31.25 with a $62.5 minimum. Actual charges vary by usage, plan, context, speed, and promotions.
Protocol, channels, and tools
- Protocol
- OpenAI Responses
- Path
- /responses
- API key header
- Authorization: Bearer
Channels and this model ID
- AWSQ is not compatible with this model ID.
- CCMAX is not compatible with this model ID.
- CODEX is compatible with this model ID and uses 1× the configured model price when the model is in the catalog.
- GEMINI is not compatible with this model ID.
Tool limits on this channel
File search is unavailable. code_interpreter, image_generation, and a shell that is not local are rejected because their usage fee cannot be calculated. Remote MCP is rejected. Web search is priced per call. Server-stored context and remote file or image URLs are rejected; images must be data URLs and files need inline file_data.
GPT-6.2 Sol API FAQ
How much does GPT-6.2 Sol API cost?
Reference rates for GPT-6.2 Sol are USD 2 input, USD 0.1 cache read, and USD 10 output per 1M tokens. AI in IDE applies 1× its configured model price when charging quota.
What is the GPT-6.2 Sol model ID?
The model ID is gpt-6.2-sol.
How do I use GPT-6.2 Sol in my IDE?
Create a CODEX API key, run the setup example on this page, and follow the linked IDE guide.