ModelRegistry
Explore text, image, video and speech models
Find the right AI by model, modality and provider.
Browse modelsChoose with facts
Turn the model directory into an actionable evaluation workflow.
Clear capabilities
Review modalities, protocols, limits and status.
Transparent coverage
See which providers expose each model.
Easy comparison
Compare candidates using consistent dimensions.
Start exploring the directory
Begin with a model, provider or organization.
Model spotlight
GPT-5.5
Default frontier GPT for coding, computer use, research, and knowledge work
Compare modelsCore capabilities
A compact view of the model contract before integration.
Input and output
See supported modalities and generation directions.
Limits and context
Check context, output limits and release details.
Provider coverage
Compare the providers and protocols that expose this version.
GPT-5.5 FAQ
Start building with GPT-5.5
Move from model evaluation to a production-ready workflow.
Model family
GPT
-
Focus areas
ReasoningGenerative AI
Core specifications
Released
2026-04-23
Context window
1.1M
Max output
128K
Weights
Closed
Modalities
Input
ImageText
Output
Text
Identity
- Version
- gpt-5.5
- Knowledge cutoff
- 2025-12-01
- Aliases
- GPT-5.5
Capabilities
AttachmentsReasoningStructuredTool call
Pricing
IN $5/M
OUT $30/M
Read $0.5/M
Capabilities and fit
Model summary
Default frontier GPT for coding, computer use, research, and knowledge work
Text
AttachmentsReasoningStructuredTool call
- Output
- Text
- Capabilities
- 4
- Catalog updated
- 2026-08-06T01:26:38.048Z
- Status
Benchmark results
| Benchmark | Type | Score / rank | Evaluated |
|---|---|---|---|
| SWE-Bench Pro | Coding | 58.6 | 2026-05-28T00:00:00.000Z |
| Terminal-Bench | Coding | 78.2 | 2026-05-28T00:00:00.000Z |
| SWE-Atlas Codebase QnA | Coding | 45.43 | 2026-08-05T03:37:00.044Z |
| SWE-Atlas Refactoring | Coding | 44.79 | 2026-08-05T03:37:00.044Z |
| SWE-Atlas Test Writing | Coding | 42.59 | 2026-08-05T03:37:00.044Z |
| Artificial Analysis Coding Agent Index | General | 65.3 | 2026-08-05T03:37:00.044Z |
| SWE-Atlas Codebase QnA | Coding | 80.8 | 2026-08-05T03:37:00.044Z |
| SWE-Bench Pro | Coding | 30.9 | 2026-08-05T03:37:00.044Z |
| Terminal-Bench | Coding | 84.1 | 2026-08-05T03:37:00.044Z |
| Artificial Analysis Coding Agent Index | General | 60.4 | 2026-08-05T03:37:00.044Z |
| SWE-Atlas Codebase QnA | Coding | 79.1 | 2026-08-05T03:37:00.044Z |
| SWE-Bench Pro | Coding | 26.2 | 2026-08-05T03:37:00.044Z |
| Terminal-Bench | Coding | 75.8 | 2026-08-05T03:37:00.044Z |
| Artificial Analysis Coding Agent Index | General | 57.8 | 2026-08-05T03:37:00.044Z |
| SWE-Atlas Codebase QnA | Coding | 75 | 2026-08-05T03:37:00.044Z |
| SWE-Bench Pro | Coding | 24.9 | 2026-08-05T03:37:00.044Z |
| Terminal-Bench | Coding | 73.4 | 2026-08-05T03:37:00.044Z |
| Terminal-Bench | Coding | 82.7 | 2026-04-23T00:00:00.000Z |
| GPQA Diamond | Reasoning | 93.6 | 2026-04-23T00:00:00.000Z |
| Humanity's Last Exam | General | 41.4 | 2026-04-23T00:00:00.000Z |
| Humanity's Last Exam | General | 52.2 | 2026-04-23T00:00:00.000Z |
| OSWorld-Verified | General | 78.7 | 2026-04-23T00:00:00.000Z |
| BrowseComp | General | 84.4 | 2026-04-23T00:00:00.000Z |
| MMMU Pro | Vision | 81.2 | 2026-04-23T00:00:00.000Z |
| ARC-AGI-2 | Reasoning | 85 | 2026-04-23T00:00:00.000Z |
| FrontierMath | Math | 51.7 | 2026-04-23T00:00:00.000Z |
| FrontierMath | Math | 35.4 | 2026-04-23T00:00:00.000Z |
| GDPval | General | 84.9 | 2026-04-23T00:00:00.000Z |
| MCP Atlas | General | 75.3 | 2026-04-23T00:00:00.000Z |
| Toolathlon | General | 55.6 | 2026-04-23T00:00:00.000Z |
| τ²-Bench Telecom | General | 98 | 2026-04-23T00:00:00.000Z |
Provider coverage
| Provider | Input | Output | Pricing |
|---|---|---|---|
| CrossModel | IN $5/M OUT $30/M Read $0.5/M | ||
| Poe | IN $5/M OUT $30/M Read $0.5/M | ||
| Vivgrid | IN $5/M OUT $30/M Read $0.5/M | ||
| NanoGPT | IN $5/M OUT $30/M Read $0.5/M | ||
| FastRouter | IN $5/M OUT $30/M Read $0.5/M | ||
| NEAR AI Cloud | IN $5/M OUT $30/M Read $0.5/M | ||
| DaoXE | IN $5/M OUT $30/M Read $0.5/M | ||
| LLM Gateway | IN $5/M OUT $30/M Read $0.5/M | ||
| Kenari | IN $5/M OUT $30/M Read $0.5/M | ||
| OpenCode Zen | IN $5/M OUT $30/M Read $0.5/M | ||
| GitHub Copilot | IN $5/M OUT $30/M Read $0.5/M | ||
| UnoRouter | IN $5/M OUT $30/M Read $0.5/M | ||
| UnoRouter | IN $5/M OUT $30/M Read $0.5/M | ||
| FrogBot | IN $5/M OUT $30/M Read $0.5/M | ||
| SAP AI Core | IN $5/M OUT $30/M Read $0.5/M | ||
| Pioneer | IN $5/M OUT $30/M Read $0.5/M | ||
| AI-ROUTER | IN $5/M OUT $30/M Read $0.5/M | ||
| ZenMux | IN $5/M OUT $30/M Read $0.5/M | ||
| Abacus | IN $5/M OUT $30/M Read $0.5/M | ||
| Azure Cognitive Services | IN $5/M OUT $30/M Read $0.5/M | ||
| Model Oracle AI | IN $5/M OUT $30/M Read $0.5/M | ||
| Azure | IN $5/M OUT $30/M Read $0.5/M | ||
| AIHubMix | IN $5/M OUT $30/M Read $0.5/M | ||
| Ofox | IN $5/M OUT $30/M Read $0.5/M | ||
| OrcaRouter | IN $5/M OUT $30/M Read $0.5/M | ||
| GMI Cloud | IN $5/M OUT $30/M Read $0.5/M | ||
| FreeModel | IN $5/M OUT $30/M Read $0.5/M | ||
| Kilo Gateway | IN $5/M OUT $30/M Read $0.5/M | ||
| Merge Gateway | IN $5/M OUT $30/M Read $0.5/M | ||
| Vercel AI Gateway | IN $5/M OUT $30/M Read $0.5/M | ||
| OpenRouter | IN $5/M OUT $30/M Read $0.5/M | ||
| Cloudflare AI Gateway | IN $5/M OUT $30/M Read $0.5/M | ||
| Perplexity Agent | IN $5/M OUT $30/M Read $0.5/M | ||
| OpenAI | IN $5/M OUT $30/M Read $0.5/M | ||
| Xpersona | IN $5/M OUT $30/M Read $0.5/M | ||
| HPC-AI | IN $5/M OUT $30/M Read $0.5/M |