GPT-5.5
GPT-5.5 is OpenAI's most intelligent model in Cursor. It keeps momentum on long-running work and stays on task for significantly longer before stopping early, which matters most in complex, multi-step coding sessions.
Strengths
- Highest overall intelligence in the GPT-5 family for challenging coding and reasoning tasks.
- More persistent on long-running work; it keeps digging instead of ending early when tasks are still incomplete.
- Strong at maintaining context and execution quality across larger, multi-step workflows.
- More token-efficient than GPT-5.4 on complex, long-running tasks, which helps reduce total token usage for the same outcomes.
Limitations
- Higher per-token pricing than GPT-5.3 Codex.
- Throughput can be lower on straightforward tasks where smaller models are already enough.
Tools
GPT-5.5 has access to all agent tools when used with Cursor including:
Find files by name, read directory structures, and grep for patterns.
Generate search queries and fetch results from the web.
Read file contents, including images for vision-capable models.
Suggest edits and apply them automatically.
Execute terminal commands and monitor output.
Control a browser to take screenshots, test applications, and verify visual changes. See the Browser documentation.
Generate images from text descriptions or reference images.
Ask clarifying questions while continuing to work in the background.
Retrieve rules based on type and description.
Learn more about how tools work and tool calling fundamentals.
Pricing
GPT-5.5 is a third-party model, so it isn't part of the usage included with Cursor plans. On The X Subscription it's billed at the rates below from your prepaid credit. On legacy Cursor plans it draws from the Other Models pool. All prices are per million tokens.
| Name | ||||
|---|---|---|---|---|
| $5 | - | $0.5 | $30 | |
| $12.5 | - | $1.25 | $75 | |
| $10 | - | $1 | $45 |
A Fast mode tier (gpt-5.5-fast) is available for priority processing. It has higher per-token pricing than standard mode.
GPT-5.5 uses the same cache discount, regional endpoint pricing, and long-context pricing behavior as GPT-5.4. When input exceeds 272k tokens (long context), input pricing doubles and output pricing is 1.5x the standard rate.