Models & Pricing

GPT-5.2 vs GPT-5

Choose two or three models. Copy the URL to share your selection.

ComparisonGPT-5.2
gpt-5.2
GPT-5
gpt-5
TypeChatChat
Best forChat, writing, coding and reasoning tasksChat, writing, coding and reasoning tasks
TokenRex price$1.75 in / $14.00 out per 1M tokens$1.25 in / $10.00 out per 1M tokens
Cached input / 1M tokens$0.175 per 1M tokens$0.125 per 1M tokens
Cache write / 1M tokensNo extra feeNo extra fee
Cached outputNot offered · standard output rate appliesNot offered · standard output rate applies
Market price$1.75 in / $14.00 out per 1M tokens$1.25 in / $10.00 out per 1M tokens
Context window (provider)400,000 tokens400,000 tokens
Input token limit (provider)Within the context windowWithin the context window
Maximum output128,000 tokens128,000 tokens
Knowledge cutoffAug 31, 2025Sep 30, 2024
Vendor input modalitiesNot verifiedText, Image
Vendor output modalitiesNot verifiedText
TokenRex endpointsPOST /v1/chat/completionsPOST /v1/chat/completions
TokenRex inputText, Image/PDF content through the chat bridgeText, Image/PDF content through the chat bridge
TokenRex outputTextText
Benchmarks
Benchmark evidence8 source-linked results—
GDPval wins/ties
70.9%

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenRex default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: GDPval (wins or ties) Knowledge work tasks 70.9% vs 38.8% (GPT-5)

OpenAI - Introducing GPT-5.2
—
SWE-Bench Pro (public)
55.6%

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenRex default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: SWE-Bench Pro (public) Software engineering 55.6% vs 50.8%

OpenAI - Introducing GPT-5.2
—
GPQA Diamond (no tools)
92.4%

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenRex default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: GPQA Diamond (no tools) Science questions 92.4% vs 88.1%

OpenAI - Introducing GPT-5.2
—
CharXiv Reasoning (w/ Python)
88.7%

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenRex default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: CharXiv Reasoning (w/ Python) Scientific figure questions 88.7% vs 80.3%

OpenAI - Introducing GPT-5.2
—
AIME 2025 (no tools)
100%

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenRex default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: AIME 2025 (no tools) Competition math 100.0% vs 94.0%

OpenAI - Introducing GPT-5.2
—
FrontierMath (Tier 1-3)
40.3%

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenRex default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: FrontierMath (Tier 1–3) Advanced mathematics 40.3% vs 31.0%

OpenAI - Introducing GPT-5.2
—
ARC-AGI-1 (Verified)
86.2%

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenRex default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: ARC-AGI-1 (Verified) Abstract reasoning 86.2% vs 72.8%

OpenAI - Introducing GPT-5.2
—
ARC-AGI-2 (Verified)
52.9%

OpenAI launch-reported GPT-5.2 Thinking result, not a TokenRex default-effort test. Professional tasks use heavy effort; most other evaluations use xhigh; see source footnotes for harness details. Published excerpt: ARC-AGI-2 (Verified) Abstract reasoning 52.9% vs 17.6%

OpenAI - Introducing GPT-5.2
—

No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenRex API support.

— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenRex media controls and response formats are listed separately.

GPT-5.2

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (1)
  • Published provider limits; maximum-capacity requests have not been independently exercised through TokenRex. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.

GPT-5

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (1)
  • Published provider limits; maximum-capacity requests have not been independently exercised through TokenRex. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.

Popular comparisons

Open the cost calculator →