ModelBench
OpenAI logo
Models/OpenAI

OpenAI: GPT-5.2 Codex

Code-specialist GPT for repository edits, reviews, and long-running software agents

Source-linked gpt-codex Closed weights Released 2025-12-11
API record Report
InputT
OutputT
Input price$0.14/M
Output price$1.14/M
Context400K
Max output128K
Providers23
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering GPT-5.2 Codex
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
QiHang gpt-5.2-codex 400K 128K $0.14 $1.14 — ReasoningToolsJSON Docs ↗
Poe openai/gpt-5.2-codex 400K 128K $1.6 $13 $0.16 ReasoningTools Docs ↗
Abacus gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Cloudflare AI Gateway openai/gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Azure Cognitive Services gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
OpenAI gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Neon gpt-5-2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Kilo Gateway openai/gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Vivgrid gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningTools Docs ↗
NanoGPT openai/gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
GitHub Copilot gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Azure gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
AIHubMix gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Ofox openai/gpt-5.2-codex 400K 128K $1.75 $14 $0.18 ReasoningToolsJSON Docs ↗
OrcaRouter openai/gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Impossibl openai/gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Requesty openai/gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
DevPass (LLM Gateway) gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Vercel AI Gateway openai/gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
OpenRouter openai/gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
Eden AI azure/gpt-5.2-codex 272K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
OpenCode Zen gpt-5.2-codex 400K 128K $1.75 $14 $0.175 ReasoningToolsJSON Docs ↗
ZenMux openai/gpt-5.2-codex 400K 64K $1.75 $14 $0.17 ReasoningTools Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.14/M

Across 23 priced providers

Median input $1.75/M

Midpoint of listed rates

Highest input $1.75/M

12.5× the lowest listed rate

Output range $1.14 – $14

Per million output tokens

QiHang $0.14/MLowest
Poe $1.6/M
Abacus $1.75/M
Cloudflare AI Gateway $1.75/M
Azure Cognitive Services $1.75/M
OpenAI $1.75/M
Neon $1.75/M
Kilo Gateway $1.75/M
Vivgrid $1.75/M
NanoGPT $1.75/M
GitHub Copilot $1.75/M
Azure $1.75/M
AIHubMix $1.75/M
Ofox $1.75/M
OrcaRouter $1.75/M
Impossibl $1.75/M
Requesty $1.75/M
DevPass (LLM Gateway) $1.75/M
Vercel AI Gateway $1.75/M
OpenRouter $1.75/M
Eden AI $1.75/M
OpenCode Zen $1.75/M
ZenMux $1.75/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 272K to 400K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes
✓ Tool calling Yes
✓ Structured output Yes
✓ Attachments Yes
✓ Vision input Yes
× Open weights No
Creator
OpenAI
Model family
gpt-codex
Knowledge cutoff
2025-08-31
License
Not documented
Release date
2025-12-11
Model ID
openai/gpt-5.2-codex
Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
Benchmark profile
Design Arena: f…Design Arena: fullstack Design Arena: w…Design Arena: webapps Design Arena: m…Design Arena: mobileapps Design Arena: a…Design Arena: androidnative Design Arena: g…Design Arena: godotgamedev SWE-Bench ProSWE-Bench Pro This model — Design Arena: fullstack: 1002 elo (3.7th percentile) This model — Design Arena: webapps: 1072 elo (8.2th percentile) This model — Design Arena: mobileapps: 1119 elo (13.6th percentile) This model — Design Arena: androidnative: 1176 elo (38.1th percentile) This model — Design Arena: godotgamedev: 1142 elo (35.6th percentile) This model — SWE-Bench Pro: 41.04 resolve rate (22.4th percentile)

Each axis is this model's percentile among the 6 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

Design Arena: fullstack elo Source ↗
Design Arena: fullstack #65 of 67
Design Arena: webapps elo Source ↗
Design Arena: webapps #62 of 67
Design Arena: mobileapps elo Source ↗
Design Arena: mobileapps #56 of 66
Design Arena: androidnative elo Source ↗
Design Arena: androidnative #37 of 59
Design Arena: godotgamedev elo Source ↗
Design Arena: godotgamedev #27 of 45
SWE-Bench Pro resolve rate Source ↗
SWE-Bench Pro #30 of 38

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against Design Arena: fullstack, the benchmark with the widest published coverage that this model appears in.

0 797 1593 $1 $10 Claude Fable 5 — $10/M, score 1281.0 Anthropic: Claude Fable 5.1 — $10/M, score 1346.0 Anthropic: Claude Fable 5.1 (batch) — $5/M, score 1346.0 Anthropic: Claude Fable 5 (batch) — $5/M, score 1281.0 Anthropic: Claude Opus 4.5 — $5/M, score 1166.0 Anthropic: Claude Opus 4.5 (batch) — $2.5/M, score 1166.0 Anthropic: Claude Opus 4.6 — $5/M, score 1228.0 Anthropic: Claude Opus 4.6 (batch) — $2.5/M, score 1228.0 Anthropic: Claude Opus 4.7 — $5/M, score 1503.0 Anthropic: Claude Opus 4.7 (batch) — $2.5/M, score 1503.0 Anthropic: Claude Opus 4.8 — $5/M, score 1258.0 Anthropic: Claude Opus 4.8 (batch) — $2.5/M, score 1258.0 Claude Opus 5 — $5/M, score 1331.0 Claude Opus 5 (batch) — $2.5/M, score 1331.0 Anthropic: Claude Sonnet 4.5 — $3/M, score 1059.0 Anthropic: Claude Sonnet 4.5 (batch) — $1.5/M, score 1059.0 Anthropic: Claude Sonnet 4.6 — $3/M, score 1222.0 Anthropic: Claude Sonnet 4.6 (batch) — $1.5/M, score 1222.0 Claude Sonnet 5 — $2/M, score 1261.0 Anthropic: Claude Sonnet 5 (batch) — $1/M, score 1261.0 DeepSeek V4 Pro — $0.435/M, score 948.0 Gemini 3 Flash Preview — $0.5/M, score 1072.0 Google: Gemini 3 Flash Preview (batch) — $0.25/M, score 1072.0 Gemini 3.1 Pro Preview — $2/M, score 1078.0 Google: Gemini 3.1 Pro Preview (batch) — $1/M, score 1078.0 Gemini 3.5 Flash — $1.5/M, score 1207.0 Google: Gemini 3.5 Flash (batch) — $0.75/M, score 1207.0 Gemini 3.6 Flash — $0.75/M, score 1195.0 Google: Gemini 3.6 Flash (batch) — $0.375/M, score 1195.0 Gemini 3.7 Flash — $0.75/M, score 1215.0 Google: Gemini 3.7 Flash (batch) — $0.375/M, score 1215.0 Muse Spark 1.1 — $1.25/M, score 1217.0 Muse Spark 1.2 — $1.25/M, score 1221.0 Muse Spark 1.3 — $1.25/M, score 1314.0 MiniMax: MiniMax M3 — $0.3/M, score 1207.0 MiniMax: MiniMax M3 (batch) — $0.3/M, score 1207.0 Kimi K2.5 — $0.3/M, score 1122.0 Kimi K2.6 — $0.95/M, score 1166.0 Kimi K2.7 Code — $0.95/M, score 1183.0 MoonshotAI: Kimi K2.7 Code (batch) — $0.95/M, score 1198.0 Kimi K3 — $3/M, score 1331.0 MoonshotAI: Kimi K3 (batch) — $3/M, score 1331.0 GPT-5.1 Codex — $1.07/M, score 1086.0 GPT-5.2 — $1.75/M, score 1052.0 GPT-5.2 Codex — $0.14/M, score 1002.0 OpenAI: GPT-5.2 (batch) — $0.875/M, score 1052.0 GPT-5.3 Codex — $1.75/M, score 992.0 GPT-5.4 — $2.5/M, score 1026.0 OpenAI: GPT-5.4 (batch) — $1.25/M, score 1026.0 GPT-5.5 — $5/M, score 1099.0 OpenAI: GPT-5.5 (batch) — $2.5/M, score 1099.0 Qwen: Qwen3.7 Max — $1.475/M, score 1199.0 Qwen: Qwen3.8 Max (0803) — $2/M, score 1321.0 SpaceXAI: Grok 4.20 — $1.25/M, score 1062.0 SpaceXAI: Grok 4.3 — $1.25/M, score 1014.0 SpaceXAI: Grok 4.3 (batch) — $1/M, score 1014.0 SpaceXAI: Grok 4.5 — $2/M, score 1258.0 SpaceXAI: Grok 4.6 — $2/M, score 1274.0 Z.ai: GLM 4.6 — $0.43/M, score 1038.0 Z.ai: GLM 4.7 — $0.4/M, score 1058.0 Z.ai: GLM 5 — $0.6/M, score 1131.0 Z.ai: GLM 5.1 — $0.966/M, score 1173.0 Z.ai: GLM 5.2 — $0.966/M, score 1248.0 Z.ai: GLM 5.2 (batch) — $0.7/M, score 1248.0 Z.ai: GLM 5V Turbo — $1.2/M, score 1158.0 GPT-5.2 Codex Input price per million tokens (log scale) Elo

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Price Completion14.0 → 1.14
Price Prompt1.75 → 0.14
Price Completion1.14 → 14.0
Price Prompt0.14 → 1.75
Price Completion14.0 → 1.14
Price Prompt1.75 → 0.14
Price Completion1.14 → 14.0
Price Prompt0.14 → 1.75
Price Completion14.0 → 1.14
Price Prompt1.75 → 0.14
Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology
Last verified
Sep 11, 2026
Status
Source-linked
Confidence
Medium
Catalog source
Models.dev
Models.devcatalog ↗QiHang documentationprovider documentation ↗Poe documentationprovider documentation ↗Abacus documentationprovider documentation ↗Cloudflare AI Gateway documentationprovider documentation ↗Azure documentationprovider documentation ↗OpenAI documentationprovider documentation ↗Neon documentationprovider documentation ↗Kilo Gateway documentationprovider documentation ↗Vivgrid documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗GitHub Copilot documentationprovider documentation ↗
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/openai/gpt-5.2-codex
curl
curl "https://model.kyssta.lol/api/v1/models/openai/gpt-5.2-codex"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is GPT-5.2 Codex?

Code-specialist GPT for repository edits, reviews, and long-running software agents. It is published by OpenAI and catalogued here from Models.dev.

How much does GPT-5.2 Codex cost?

Listed input pricing starts at $0.14 per million tokens from QiHang, rising to $1.75 across 23 listed providers.

What is the context length of GPT-5.2 Codex?

GPT-5.2 Codex accepts up to 400K tokens of context and returns up to 128K output tokens.

Does GPT-5.2 Codex support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, reasoning, and image input.

Which providers serve GPT-5.2 Codex?

23 providers list this model: QiHang, Poe, Abacus, Cloudflare AI Gateway, Azure Cognitive Services, OpenAI and 17 more.

Are the weights for GPT-5.2 Codex open?

No. This model is served through hosted APIs only.

When was GPT-5.2 Codex released?

The catalog records a release date of 2025-12-11, last verified Sep 11, 2026.

More models from OpenAI

View all →
GPT-Image-1.5

Image model for prompt-driven generation, editing, and visual design workflows

Not documented ctx $5/M in o3-deep-research

Research model for long-horizon investigation, synthesis, and analytical reports

200K ctx $9/M in GPT-6 Astra (Fast)

Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.

1.05M ctx $20/M in GPT-5.3 Chat (latest)

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

128K ctx $1.75/M in