LLM Reference

GPT-5.2 Codex vs GPT-5.5

GPT-5.2 Codex (2025) and GPT-5.5 (2026) compare a coding-specialized model against a standalone API model. GPT-5.2 Codex ships a 400k-token context window, while GPT-5.5 ships a 1.05m-token context window. On SWE-bench Verified, GPT-5.5 leads by 9.8 pts. On pricing, GPT-5.2 Codex costs $1.75/1M input tokens; GPT-5.5 ranges from $5 to $8/1M input tokens by tier. This page treats the result as workflow and deployment fit, not a universal model winner.

Treat this as a product-type comparison: GPT-5.2 Codex is coding-specialized model, while GPT-5.5 is standalone API model. Choose based on workflow fit before reading any benchmark or price row as decisive.

Decision scorecard

Local evidence first
SignalGPT-5.2 CodexGPT-5.5
Product typeCoding-specialized modelStandalone API model
Best forcustom coding agents, code generation, and tool loopsreasoning-heavy apps, multimodal apps, and tool-calling agents
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window400k1.05m
Cheapest output$14/1M tokens$30/1M tokens
Provider routes2 tracked4 tracked
Shared benchmarks3 sharedSWE-bench Verified leader

Decision tradeoffs

Choose GPT-5.2 Codex when...
  • GPT-5.2 Codex has the lower cheapest tracked output price at $14/1M tokens.
  • Local decision data tags GPT-5.2 Codex for Coding, RAG, and Agents.
Choose GPT-5.5 when...
  • GPT-5.5 holds a shared-benchmark lead on SWE-bench Verified, ahead by 9.8 points.
  • GPT-5.5 has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • GPT-5.5 has broader tracked provider coverage for fallback and route flexibility.
  • Local decision data tags GPT-5.5 for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate GPT-5.2 Codex

GPT-5.2 Codex

$4,900

Cheapest tracked route/tier: Vercel AI Gateway

GPT-5.5

$11,500

Cheapest tracked route/tier: OpenAI API 0-272K input tokens

Estimated monthly gap: $6,600. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

GPT-5.2 Codex -> GPT-5.5
  • Provider overlap exists on OpenAI API and Vercel AI Gateway; start route-level A/B tests there.
  • GPT-5.5 is $16/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
GPT-5.5 -> GPT-5.2 Codex
  • Provider overlap exists on Vercel AI Gateway and OpenAI API; start route-level A/B tests there.
  • GPT-5.2 Codex is $16/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.

Specs

Specification
Released2025-12-182026-04-23
Context window400k1.05m
Parameters
ArchitectureDecoder OnlyDecoder Only
LicenseProprietaryProprietary
OpennessProprietaryProprietary
WeightsNot releasedNot released
CodeUnknownUnknown
Commercial useCommercial use: conditionalCommercial use: conditional
Knowledge cutoff2025-082025-12

Pricing and availability

Pricing attributeGPT-5.2 CodexGPT-5.5
Input price$1.75/1M tokens
0-272K input tokens
$5/1M tokens
Standard GPT-5.5 token pricing before the long-context surcharge threshold.
272K+ input tokens
$8/1M tokens
Long-context surcharge applies above 272K input tokens for the full session.
Output price$14/1M tokens
0-272K input tokens
$30/1M tokens
Standard GPT-5.5 token pricing before the long-context surcharge threshold.
272K+ input tokens
$36/1M tokens
Long-context surcharge applies above 272K input tokens for the full session.
Providers

Capabilities

CapabilityGPT-5.2 CodexGPT-5.5
VisionYesYes
MultimodalYesYes
ReasoningYesYes
JSON / Tool useYesYes
Structured outputsYesYes
Code executionYesYes
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkGPT-5.2 CodexGPT-5.5
SWE-bench Verified72.882.6
SWE-bench Pro56.458.6
Terminal-Bench 2.064.082.7

Continue comparing

Last reviewed: 2026-06-30. Data sourced from public model cards and provider documentation.