Model comparison
GPT-5.4 Mini vs GPT-5.5
Two OpenAI tiers compared on the figures that decide which one a workload actually needs.
Catalog record checked September 3, 2026Individual provider fields may changeEvidence confidence: High — see receipts below
OpenAI
GPT-5.4 Mini
Balanced
OpenAI
GPT-5.5
Frontier
| Specification | GPT-5.4 Mini | GPT-5.5 |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Tier | Balanced | Frontier |
| Context window | 400K | Winner: 1.05M |
| Max output | 128K | 128K |
| Input / 1M tokens | Winner: $0.75 | $5 |
| Output / 1M tokens | Winner: $4.50 | $30 |
| Weights | Closed | Closed |
| Parameters | Not disclosedUnverified | Not disclosedUnverified |
| Reasoning levels | none, low, medium, high | none, low, medium, high, xhigh, max |
| Modalities | text, image | text, image |
| API model id | gpt-5.4-mini | gpt-5.5 |
| Released | March 17, 2026 | April 23, 2026 |
| Artificial Analysis Intelligence Index [high] (2026-08-14) | 46 | Not verifiedUnverified |
| Artificial Analysis Intelligence Index [xhigh] (2026-08-14) | Not verifiedUnverified | 58 |
| SWE-bench Verified (2026-09-01) | Not verifiedUnverified | 82.6 |
| Terminal-Bench 2.1 (2026-07-27) | Not verifiedUnverified | 83.4 |
| GPQA Diamond (2026-07-27) | Not verifiedUnverified | 93.5 |
| Humanity's Last Exam (2026-04-23) | Not verifiedUnverified | 52.2 |
Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.
Benchmark receipts
- 2026-09-01: vals.ai SWE-bench Verified leaderboard (independent, mini-swe-agent bash-only); official SWE-bench not publishedReal GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
- 2026-08-14: Artificial AnalysisComposite index blending reasoning, knowledge, and coding evals into one 0–100 score. Comparability: directly comparable — AA occasionally rebaselines the index scale between snapshots — a score captured on one date is only comparable to same-snapshot scores (check measuredAt).
- 2026-07-27: Kimi K3 model card (vendor-reported, xhigh); announcement charts show 93.6 — minor conflict preservedAgentic terminal work: multi-step tasks executed in a sandboxed shell environment. Comparability: comparable with caveat — Scores across Terminal-Bench major versions (v1 vs v2) are NOT comparable; harness configuration (container, time limits) also shifts results.
- 2026-04-23: OpenAI — Introducing GPT-5.5 (vendor, with tools; 41.4 no tools)Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise. Comparability: comparable with caveat — Subset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
Pricing tiers: GPT-5.4 Mini: Standard $0.75/$4.50 per MTok; cached input $0.075/MTok; batch $0.375/$2.25. · GPT-5.5: Standard $5/$30 per MTok; >272K input billed 2x in / 1.5x out. Cached input $0.50/MTok; batch $2.50/$15.
GPT-5.4 Mini
GPT-5.4 Mini is OpenAI's efficient mid-tier for high-volume, well-scoped tasks at $0.75/$4.50.
Best for
- High-volume calls
- Mixed workloads
- Cost-sensitive production
Watch out
400K context (vs 1.05M on GPT-5.4/5.5/5.6); verify long-context needs.
GPT-5.5
GPT-5.5 is OpenAI's previous flagship — strong on Terminal-Bench 2.0 (82.7%) and 1M-token context.
Best for
- Reasoning
- Agentic coding
- Long-context work
Watch out
Superseded by GPT-5.6 Sol on quality; still a capable, widely integrated model.
When the cheaper one wins
GPT-5.4 Mini is cheaper on output at $4.50 per million tokens against $30 for GPT-5.5 — about 6.7×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.
Run the model pickerEvidence confidence: High
How strong and complete the evidence behind this comparison is — not a prediction of which model is better.
- Pricing verified on both sides — Input and output rates are verified for both models.
- 4/5 core specs verified on both sides — Not published for at least one side: parameter count.
- 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
- Verified within the last 90 days — Newest catalog check was 8 days ago.
- Both models carry source citations — Each side has at least two catalog sources on record.
Source receipts
Each catalog figure was checked against the provider or an independent second source on the date shown.
- GPT-5.4 Mini: OpenAI — GPT-5.4 Mini & Nano (accessed 2026-08-29)
- GPT-5.4 Mini: OpenAI API pricing (gpt-5.4-mini $0.75/$4.50) (accessed 2026-08-29)
- GPT-5.5: OpenAI — Introducing GPT-5.5 (accessed 2026-08-29)
- GPT-5.5: OpenAI API pricing (gpt-5.5 $5/$30) (accessed 2026-08-29)
Related comparisons
- Amazon Nova 2 Pro vs GPT-5.4 Mini
- Claude Fable 5.1 vs GPT-5.5
- Claude Fable 5 vs GPT-5.5
- Claude Mythos 5.1 vs GPT-5.5
- Claude Opus 5 vs GPT-5.5
- Claude Sonnet 5 vs GPT-5.4 Mini
Diving deeper on one model? GPT-5.4 Mini · GPT-5.5
Common questions
GPT-5.4 Mini vs GPT-5.5
Answered from the verified figures on this page rather than general guidance.
Is GPT-5.4 Mini or GPT-5.5 cheaper for input?
GPT-5.4 Mini is cheaper at $0.75 per million input tokens, against $5 for GPT-5.5 — roughly 6.7× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-5.4 Mini has tiered pricing: Standard $0.75/$4.50 per MTok; cached input $0.075/MTok; batch $0.375/$2.25. GPT-5.5 has tiered pricing: Standard $5/$30 per MTok; >272K input billed 2x in / 1.5x out. Cached input $0.50/MTok; batch $2.50/$15.
Is GPT-5.4 Mini or GPT-5.5 cheaper for output?
GPT-5.4 Mini is cheaper at $4.50 per million output tokens, against $30 for GPT-5.5 — roughly 6.7× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-5.4 Mini has tiered pricing: Standard $0.75/$4.50 per MTok; cached input $0.075/MTok; batch $0.375/$2.25. GPT-5.5 has tiered pricing: Standard $5/$30 per MTok; >272K input billed 2x in / 1.5x out. Cached input $0.50/MTok; batch $2.50/$15.
Which has the larger context window, GPT-5.4 Mini or GPT-5.5?
GPT-5.5 accepts 1.05M tokens against 400K for GPT-5.4 Mini. This only matters if you routinely send very long documents or large codebases.
Do GPT-5.4 Mini and GPT-5.5 support the same reasoning levels?
GPT-5.4 Mini exposes none, low, medium, high, while GPT-5.5 exposes none, low, medium, high, xhigh, max.
Should I use GPT-5.4 Mini or GPT-5.5?
GPT-5.4 Mini is the balanced tier and GPT-5.5 the frontier tier. The useful question is whether your hardest task actually fails on the cheaper one — most production volume such as classification, extraction and summarisation does not.
Next step
Choosing between them
The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.
- Input price: GPT-5.4 Mini costs $0.75 per 1M tokens versus $5 for GPT-5.5 — a 6.7x difference at the headline tier.
- Context: GPT-5.5 takes 1.05M against 400K for GPT-5.4 Mini — only decisive if your prompts approach the smaller window.
- Measured capability: GPT-5.5 leads Artificial Analysis Intelligence Index 58 to 46 (measured 2026-08-14).
- Positioning: GPT-5.4 Mini sits in the balanced tier, GPT-5.5 in the frontier tier — most production volume (classification, extraction, summarisation) does not need the pricier tier.
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.