← Model list

GPT-5.5

openai·openai/gpt-5.5·BETA·Closed·gpt series

Default frontier GPT for coding, computer use, research, and knowledge work

At a glance
Official price$5.00 / $30.00 per 1M
Cache read $0.50 · OpenAI
Lowest paid$0.188 / $1.13
UnoRouter Gateway · 33.3× spread
2 more $0 channels
Context1,050,000
⚠ Providers report 272,000–1,050,000; the table below is authoritative
Output limit128,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2025-12-01
Released / updated2026-04-23 / 2026-04-23

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier xhigh

Intelligence56.3
Value133
Coding74.9
Agentic47.4
Output speed85 tok/s
TTFT68.86 s
Cost per task$1.1747
Value formulaIQ 56.3 ÷ min blended $0.422 = 133
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 35.8 · 68 tok/s
lowIQ 44.5 · 74 tok/s
mediumIQ 51.4 · 79 tok/s
highIQ 54.7 · 74 tok/s
xhighIQ 56.3 · 85 tok/s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 45 providers41 with public prices · 2 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kenari
gpt-5-5
GatewayFree1,050,000128,000
UnoRouter
gpt-5.5:free
GatewayFree1,050,000128,000
UnoRouterGateway$0.188$1.131,050,000128,000
XpersonaGateway$1.50$12.00$0.151,050,000128,000
FrogBot
gpt-5-5
Gateway$2.50$15.00$0.25272,000128,000
Xpersona
xpersona-gpt-5.5
Gateway$3.00$18.00$0.301,000,000128,000
PoeGateway$4.55$27.27$0.455400,000128,000
RequestyGateway$4.95$29.70$0.4951,050,000128,000
HPC-AICloud$5.00
tiered >272K: $10.00
$30.00$0.501,050,000128,000
AI-ROUTERGateway$5.00$30.00$0.501,050,000128,000
OpenAIOfficialFirst-party$5.00
tiered >272K: $10.00
$30.00$0.501,050,000128,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1UnoRouter$93.75
2Xpersona$738.00
3FrogBot$980.00
4Xpersona$1,176.00
5Poe$1,781.82
6Requesty$1,940.40
16OpenAI · Official$1,960.00

2 more channels offer $0 (Kenari, UnoRouter); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to UnoRouter to save $1,866.25/mo (95%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark31 items

NameConditionsScoreMetricSource
SWE-Bench Pro58.6resolve rateSource ↗
Terminal-Benchharness: Terminus-2 · v2.178.2success rateSource ↗
SWE-Atlas Codebase QnAharness: Codex45.43scoreSource ↗
SWE-Atlas Refactoringharness: Codex44.79scoreSource ↗
SWE-Atlas Test Writingharness: Codex42.59scoreSource ↗
Artificial Analysis Coding Agent Indexharness: Codex · variant: xhigh65.3average pass@1Source ↗
SWE-Atlas Codebase QnAharness: Codex · variant: xhigh80.8pass@1Source ↗
SWE-Bench Proharness: Codex · variant: xhigh · dataset: hard-aa30.9pass@1Source ↗
Terminal-Benchharness: Codex · variant: xhigh · v2.184.1pass@1Source ↗
Artificial Analysis Coding Agent Indexharness: Codex · variant: medium60.4average pass@1Source ↗
SWE-Atlas Codebase QnAharness: Codex · variant: medium79.1pass@1Source ↗
SWE-Bench Proharness: Codex · variant: medium · dataset: hard-aa26.2pass@1Source ↗
Terminal-Benchharness: Codex · variant: medium · v2.175.8pass@1Source ↗
Artificial Analysis Coding Agent Indexharness: Cursor CLI · variant: medium57.8average pass@1Source ↗
SWE-Atlas Codebase QnAharness: Cursor CLI · variant: medium75pass@1Source ↗
SWE-Bench Proharness: Cursor CLI · variant: medium · dataset: hard-aa24.9pass@1Source ↗
Terminal-Benchharness: Cursor CLI · variant: medium · v2.173.4pass@1Source ↗
Terminal-Benchv2.082.7success rateSource ↗
GPQA Diamond93.6accuracySource ↗
Humanity's Last Examvariant: no tools41.4accuracySource ↗
Humanity's Last Examvariant: with tools52.2accuracySource ↗
OSWorld-Verified78.7success rateSource ↗
BrowseComp84.4accuracySource ↗
MMMU Provariant: no tools81.2accuracySource ↗
ARC-AGI-2variant: Verified85accuracySource ↗
FrontierMathdataset: Tier 1-351.7accuracySource ↗
FrontierMathdataset: Tier 435.4accuracySource ↗
GDPval84.9wins or tiesSource ↗
MCP Atlas75.3success rateSource ↗
Toolathlon55.6success rateSource ↗
τ²-Bench Telecomvariant: original prompts98success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = xhigheffort = maxbudget_tokenseffort = minimal

4 / 45 providers expose no reasoning control (reasoning_options: []).

Experimental modes6 items

ModeProviderInputOutputCache readCache write
fastOrcaRouter$12.50$75.00$1.25
fastDatabricks$12.50$75.00$1.25
fastOpenAI$12.50$75.00$1.25
fastMerge Gateway$12.50$75.00$1.25
fastZenMux$12.50$75.00$1.25
fastAIHubMix$12.50$75.00$1.25

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$30.00$02026-08-052026-08-132026-08-05 · Input list $5.002026-08-06 · Input list $5.002026-08-07 · Input list $5.002026-08-08 · Input list $5.002026-08-09 · Input list $5.002026-08-10 · Input list $5.002026-08-11 · Input list $5.002026-08-12 · Input list $5.002026-08-13 · Input list $5.002026-08-05 · Output list $30.002026-08-06 · Output list $30.002026-08-07 · Output list $30.002026-08-08 · Output list $30.002026-08-09 · Output list $30.002026-08-10 · Output list $30.002026-08-11 · Output list $30.002026-08-12 · Output list $30.002026-08-13 · Output list $30.002026-08-05 · Min blended $0.4222026-08-06 · Min blended $0.4222026-08-07 · Min blended $0.4222026-08-08 · Min blended $0.4222026-08-09 · Min blended $0.4222026-08-10 · Min blended $0.4222026-08-11 · Min blended $0.4222026-08-12 · Min blended $0.4222026-08-13 · Min blended $0.422