GPT-5.5 vs GPT-5.4
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by OpenAI
|
by OpenAI
|
|---|---|---|
| Overview | ||
| Status | Current flagship | Current flagship |
| Released | Nov 15, 2025 | Aug 15, 2025 |
| Pricing per million tokens | ||
| Input | $5.00/Mtok | $2.50/Mtok |
| Output | $30.00/Mtok | $15.00/Mtok |
| Blended avg | $11.25/Mtok | $5.63/Mtok |
| Cached input | $0.500/Mtok | $0.250/Mtok |
| Specifications | ||
| Context window | 1M tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimageaudio
|
textimage
|
| Benchmarks sources: Vellum LLM Leaderboard / OpenAI model card, Artificial Analysis | ||
| Avg benchmark score | 75 | 78.7 |
| Perf / dollar | 6.7 | 14 |
| GPQA Diamond | 93.6 | 88 |
| Humanity's Last Exam | 41.4 | 40.2 |
| ARC-AGI 2 | 85 | 50 |
| HumanEval | 58.6 | 94.5 |
| SWE-Bench Verified | — | 75 |
| Terminal-Bench 2.1 | 82.7 | — |
| MCP Atlas | 75.3 | — |
| BrowseComp | 84.4 | — |
| OSWorld-Verified | 78.7 | — |
| AIME 2025 | — | 95.5 |
| MMMLU | — | 88 |
| BFCL | — | 85 |
| MATH 500 | — | 92 |
| AutoBench | 12.9 | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 56.3 | 53.1 |
| AA Agentic Index | 47.4 | 44.2 |
| AA-Omniscience Index (−100–100) | 20.5 | 5.8 |
| LMSYS Chatbot Arena | 1476.7 ELO | 1465.5 ELO |
| GDPval-AA v2 | 1491.1 ELO | — |
| Providers | ||
| Available from |
OpenAI — $5.00/$30.00/Mtok
|
OpenAI — $2.50/$15.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | GPT-5.5 | GPT-5.4 | Savings |
|---|---|---|---|
| 1M tokens | $11.25 | $5.63 | $5.63 (50%) |
| 10M tokens | $112.5 | $56.25 | $56.25 (50%) |
| 100M tokens | $1125 | $562.5 | $562.5 (50%) |
| 1000M tokens | $11250 | $5625 | $5625 (50%) |
When to pick which
distilled from the pricing and spec data above- this pairing gives GPT-5.5 no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
- cost dominates: $5.63/Mtok blended vs $11.25 — 50% less on the same 50/50 token mix
- raw capability matters more than price: 78.7 vs 75 average benchmark score
The cheaper option here — GPT-5.4 costs $5.63/Mtok blended on OpenAI.
Summary
GPT-5.5 by OpenAI costs $5.00/Mtok input and $30.00/Mtok output, with a 1M-token context window. It supports text, image, audio input.
GPT-5.4 by OpenAI costs $2.50/Mtok input and $15.00/Mtok output, with a 1M-token context window. It supports text, image input.
On a blended cost basis, GPT-5.4 is 50% cheaper than GPT-5.5.
On benchmarks, GPT-5.4 scores higher (78.7 vs 75) on average. In terms of value, GPT-5.4 has better performance per dollar (14 vs 6.7).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.