GPT-5.5 Pro
GPT-5.5 Pro is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 1.05m context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- GPT-5.5
- Released
- 2026-04-23
- Context
- 1.05m
- Max output
- 128,000
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-12
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
Cheapest of 3 routes · OpenAI API
About
GPT-5.5 Pro is OpenAI's premium extra-compute deployment of GPT-5.5, released April 23, 2026. It uses the same underlying weights as GPT-5.5 standard with additional parallel test-time compute for harder tasks. Supports text and image inputs, reasoning effort control, tool use, structured outputs, code execution, a 1,050,000-token context window, and 128K max output. Key datapack rows: Terminal-Bench 2.1 78.2%, SWE-bench Pro 58.6%, GPQA Diamond 93.6%, ARC-AGI-2 high effort 83.3%, BrowseComp Pro compute 90.1%, and FrontierMath Tier 4 39.6%. Official pricing is $30/M input, $180/M output, $10/M batch input, and $45/M batch output; native cached input discount is not listed.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ D3 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ D1 relevant benchmark in the decision map.
Provider price ladder
Compare all 3Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Route |
|---|---|---|---|---|
| OpenAI API | $30.00 | $180.00 | $10.00 / $45.00 | Serverless |
| OpenRouter | $30.00 | $180.00 | - | Serverless |
| Vercel AI Gateway | - | - | - | ServerlessPartial |
Available via routers & gateways(15)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
AIRouter
RouterCommercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(18)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| SWE-bench Verified | 82.6 | Vals.ai independent SWE-bench Verified; standard GPT-5.5 weightsObserved 2026-04-24 | — | Source |
| SWE-bench Pro | 58.6 | SWE-bench Pro; standard GPT-5.5 weightsObserved 2026-04-24 | — | Source |
| Terminal-Bench 2.0 | 82.7 | Terminal-Bench 2.0; standard GPT-5.5 weightsObserved 2026-04-23 | — | Source |
| Terminal-Bench 2.1 | 78.2 | Terminal-Bench 2.1; standard GPT-5.5 weightsObserved 2026-05-28 | — | Source |
| Google-Proof Q&A | 93.6 | GPQA DiamondObserved 2026-04-24 | — | Source |
| Humanity's Last Exam — No Tools | 41.4 | HLE no tools; standard GPT-5.5 weightsObserved 2026-04-24 | — | Source |
| Humanity's Last Exam — With Tools | 52.2 | HLE with tools; standard GPT-5.5 weightsObserved 2026-04-24 | — | Source |
| Humanity's Last Exam — With Tools Pro Compute | 57.2 | HLE with tools; GPT-5.5 Pro computeObserved 2026-04-24 | — | Source |
| BrowseComp — Single Agent | 84.4 | BrowseComp single-agent; standard GPT-5.5 weightsObserved 2026-04-24 | — | Source |
| BrowseComp — Pro Compute | 90.1 | BrowseComp; GPT-5.5 Pro computeObserved 2026-04-24 | — | Source |
| OSWorld-Verified | 78.7 | OSWorld-VerifiedObserved 2026-04-24 | — | Source |
| GDPval-AA | 1785.0 | GDPval-AA ELO; Artificial Analysis independentObserved 2026-06-26 | — | Source |
| Artificial Analysis Intelligence Index | 55.0 | Artificial Analysis Intelligence Index; GPT-5.5 xhigh computeObserved 2026-06-26 | — | Source |
| MCP-Atlas | 75.3 | MCP-AtlasObserved 2026-04-24 | — | Source |
| FrontierMath Tier 4 | 39.6 | FrontierMath Tier 4; GPT-5.5 Pro computeObserved 2026-04-24 | — | Source |
| ARC-AGI-2 — High Effort | 83.3 | ARC-AGI-2 high effortObserved 2026-04-24 | — | Source |
| LiveCodeBench | 91.0 | LiveCodeBench; approximate standard GPT-5.5 scoreObserved 2026-04-24 | — | Source |
| GeneBench-Pro | 20.5 | GPT Pro (Extended)Observed 2026-06-30 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(6)
Compare GPT-5.5 Pro with other models
Comparison and alternatives
Browse all comparisons →Show all 10 popular comparisonssorted by 7-day search impressions
Cheapest of 3 routes · OpenAI API