OpenAI: GPT-5.2-Codex

openai/gpt-5.2-codex

GPT-5.2-Codex (OpenAI) ranks #33 of 235 on the TryAii Score at $1.75/$14 per million input/output tokens, though GLM 5.3 Flash matches it for $0.25 per million output tokens. It's strongest on coding (#12 on LiveCodeBench). It's reasonably quick at roughly 30-43 tokens/sec.

Prompt $/1M

$1.750

Completion $/1M

$14.000

Context

400,000 tok

Best provider

50 tok/s · OpenAI

Specs

Model id: openai/gpt-5.2-codex
Display name: OpenAI: GPT-5.2-Codex
Modality: text+image->text
Tokenizer: GPT
Instruct type: —
Context length: 400,000
Max completion: 128,000
Prompt $/1M: $1.750
Completion $/1M: $14.000
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
OpenAIfastest	50	1,774 ms	2,704 ms
Azurefastest	23	3,576 ms	5,683 ms
openaifastest	—	—	—
Artificial Analysis	0	0 ms	—

Prompt caching by provider

Provider	Min tokens to cache	Notes
OpenAI	1,024 tokens	GPT-5.x pre-5.6: 90% cached-read discount, free cache writes. 5-10 min sliding TTL; extended retention up to 24h on eligible models (non-ZDR default since May 2026).