openai / Chat

GPT-5.2

openai/gpt-5.2

Complex reasoning & problem solving

Best for: Chat, writing, coding and reasoning tasks

ShareLinkedIn X

Catalog status

Enabled

Research checked

2026-10-06

Price / performance

What it costs to get this result

Benchmark

GDPval wins/ties · Source-reported results, not a composite ranking. Prices use the average of TokenRex input and output rates per million tokens; actual spend depends on usage. Test configurations differ.

GPT-5.270.9% · 1 sourced models

Blended price / 1M tokens · log scale

● Current model● Other modelsDashed line: price/score frontier among plotted models

Compare sourced models on this benchmark

Benchmark results

8 reported results

Results are source-attributed, not TokenRex measurements. Different tests and thinking variants are not interchangeable.

8 of 8 results

GDPval wins/ties

Knowledge-Work · Vendor-reported

Test conditions and source

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)

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

70.9%

SWE-Bench Pro (public)

Coding · Vendor-reported

Test conditions and source

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%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

55.6%

GPQA Diamond (no tools)

Science · Vendor-reported

Test conditions and source

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%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

92.4%

CharXiv Reasoning (w/ Python)

Multimodal · Vendor-reported

Test conditions and source

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%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

88.7%

AIME 2025 (no tools)

Math · Vendor-reported

Test conditions and source

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%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

100%

FrontierMath (Tier 1-3)

Math · Vendor-reported

Test conditions and source

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%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

40.3%

ARC-AGI-1 (Verified)

Reasoning · Vendor-reported

Test conditions and source

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%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

86.2%

ARC-AGI-2 (Verified)

Reasoning · Vendor-reported

Test conditions and source

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%

Tested model: openai/gpt-5.2

OpenAI - Introducing GPT-5.2 · Checked 2026-10-06

52.9%

Model specifications

Context window

400K

Published provider limit

Maximum output

128K

Published provider limit

Knowledge cutoff

Aug 31, 2025

Upstream model

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Not verified

Output

Not verified

Exact model ID: openai/gpt-5.2
Model type: Chat
Context window: 400,000 tokens
Maximum output: 128,000 tokens
Knowledge cutoff: Aug 31, 2025

A context window is the total conversation budget, not a separate maximum input allowance; generated output and reasoning can use that budget. Published provider limits are not independently tested TokenRex request limits.

Versions and thinking levels

Choose from 4 enabled versions. The exact ID determines the version and its price; benchmark scores do not carry over between variants.

GPT-5.2Selected$1.75 in / $14.00 out per 1M tokens

GPT-5.2 Deep$1.75 in / $14.00 out per 1M tokens

GPT-5.2 Fast$1.75 in / $14.00 out per 1M tokens

GPT-5.2 Max$1.75 in / $14.00 out per 1M tokens

Features and tool support

TokenRex’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Reasoning configuration

The catalog version determines the requested reasoning effort.

Selected effort: medium (default catalog version). Reasoning level is not a measured intelligence or speed score.

Coding and agent workflows

Text/code generation and customer-managed tool loops.

Coding benchmark results do not establish a hosted terminal, sandbox, autonomous browser or guaranteed task success.

Streaming answers

Available

Incremental text through TokenRex’s chat endpoint; Claude also has native Messages access.

Customer-defined function tools

Limited

Only customer-defined function tools are forwarded. Model/protocol compatibility applies; your application authorizes and executes every tool.

Forced or named tool selection

Limited

The chat route accepts auto, none and required. A named-tool choice is not forwarded; exact model compatibility is not independently tested.

Images and PDFs

Available

Images and PDFs can be sent in chat messages to every chat model. File size and model limits apply.

Hosted web search / browsing

Not exposed

No provider-hosted web search or web-fetch tool is exposed. Customer-owned search can be implemented as an authorized function tool.

Hosted code execution / computer use

Not exposed

No built-in execution environment or computer-control tool is provided. Code generation is not code execution.

Hosted file search / persistent assistants

Not exposed

No hosted file-search index, Assistants endpoint or persistent provider agent is exposed.

Prompt caching

Available

Gateway-reported cache reads and writes are included in billing. See this model’s cached input and cache-write rates; a cache hit is not guaranteed. Output is billed at the standard output rate.

Batch / fine-tuning

Not exposed

No public batch or fine-tuning endpoint is offered here.

Prompt caching

Cached input:: $0.175 per 1M tokens
Cache write:: No extra fee
Cached output:: Not offered · standard output rate applies

Eligible repeated prompt prefixes can use the cached-input rate when the gateway reports a cache hit. Cache hits are not guaranteed.

Caching guide and usage fields

TokenRex pricing

Input / 1M tokens

$1.75

Output / 1M tokens

$14.00

Cached input / 1M

$0.175

Cache write / 1M

No extra fee

Test in Playground Get API key

Usage-based billing. Repeated prompt prefixes are cached automatically and billed at the cached input rate.

Billing calculator

Total input tokensprompt_tokens, including cached tokensCached input tokenscached_tokens reported in usageOutput tokensIncludes thinking tokensNumber of requestsSame usage per request

Per request: $0.105
Total: $0.105
Without cache: $0.231

Cached tokens are billed at the cached-input rate; output is always billed at the standard rate. This is an estimate; your actual charge follows the usage the API reports.

API access

https://tokenrex.ai/api/public

POST /v1/chat/completions

TokenRex input: Text, Image/PDF content through the chat bridge
TokenRex output: Text

Requests require a TokenRex API key and sufficient wallet balance.

Integration documentation

Streaming and customer-defined function tools are routed through the chat API; compatibility varies by model. Image/PDF input is accepted by the bridge, but model vision support needs provider confirmation. Hosted search and computer-use tools are not enabled; public Responses, Assistants, Batch and fine-tuning endpoints are not exposed.

Explore similar models

GPT-5.4 GPT-5.6 Terra GPT-6 Sol

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.

Provider model specifications
Vendor-reported
Last checked 2026-10-06
OpenAI - Introducing GPT-5.2
Vendor-reported
Last checked 2026-10-06

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.