LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-5.2 Codex

openai·openai/gpt-5.2-codex·GA·Closed·gpt-codex series
Code-specialist GPT for repository edits, reviews, and long-running software agents

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·QiHangGateway
$0.14 / $1.14
Blended $0.39 · 12.5× spread
1 more $0 channels
Context
400,000
Output limit
128,000
Knowledge cutoff
2025-08-31
Released / updated
2025-12-11 / 2025-12-11
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
Modalities
TextImagePDF

GPT-5.2 Codex by openai is offered by 21 providers on this page. Public prices are shown for 20 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is QiHang at $0.14 / $1.14 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 13× across the providers that host it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 151 tokens per second, with 117.54s to the first token.

The context window is 400,000 tokens at the reference host, but hosts report different limits, from 272,000 to 400,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2025-08-31.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Xhigh

Intelligence—
Value—
Output speed151 tok/s
TTFT117.54 s

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

Available at 21 providers20 with public prices · 1 free

  • ProviderInput / Output
  • GitLab DuoCloud
    duo-chat-gpt-5-2-codex
    Free
    Context 400,000Output limit 128,000deprecated
  • QiHangGateway
    $0.14 / $1.14
    Context 400,000Output limit 128,000deprecated
  • PoeGateway
    $1.60 / $13.00
    Cache read $0.16Context 400,000Output limit 128,000deprecated
  • LLM GatewayGateway
    $1.75 / $14.00
    Cache read $0.18Context 400,000Output limit 128,000
  • Jiekou.AIGateway
    $1.75 / $14.00
    Cache read $0.18Context 400,000Output limit 128,000
  • NanoGPTGateway
    $1.75 / $14.00
    Cache read $0.18Context 400,000Output limit 128,000
  • DevPass (LLM Gateway)Gateway
    $1.75 / $14.00
    Cache read $0.18Context 400,000Output limit 128,000
  • OpenRouterGateway
    $1.75 / $14.00
    Cache read $0.18Context 400,000Output limit 128,000
  • VivgridGateway
    $1.75 / $14.00
    Cache read $0.18Context 400,000Output limit 128,000deprecated
  • AIHubMixGateway
    $1.75 / $14.00
    Cache read $0.18Context 400,000Output limit 128,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GitLab Duo
duo-chat-gpt-5-2-codex
CloudFree——400,000128,000deprecated
QiHangGateway$0.14$1.14——400,000128,000deprecated
PoeGateway$1.60$13.00$0.16—400,000128,000deprecated
LLM GatewayGateway$1.75$14.00$0.18—400,000128,000
Jiekou.AIGateway$1.75$14.00$0.18—400,000128,000
NanoGPTGateway$1.75$14.00$0.18—400,000128,000
DevPass (LLM Gateway)Gateway$1.75$14.00$0.18—400,000128,000
OpenRouterGateway$1.75$14.00$0.18—400,000128,000
VivgridGateway$1.75$14.00$0.18—400,000128,000deprecated
AIHubMixGateway$1.75$14.00$0.18—400,000128,000

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.

Reasoning control

effort = loweffort = mediumeffort = higheffort = xhigh

3 / 21 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1QiHang$85.00
2Poe$797.20
3LLM Gateway$861.00
4Jiekou.AI$861.00
5NanoGPT$861.00
6DevPass (LLM Gateway)$861.00

1 more channels offer $0 (GitLab Duo); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.39

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Prodataset: public41.04resolve rateSource ↗

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

Related models

GPT-5.3 Codexsame series$1.75 / $14.00GPT-5.1 Codexsame series—GPT-5.1 Codex minisame series—GPT-5.2 Chatsame lab—GPT-5.2 Prosame lab$21.00 / $168
Data partly from models.dev (MIT)