OpenAI: GPT-5.1-Codex

openai/gpt-5.1-codex

GPT-5.1-Codex (OpenAI) ranks #99 of 261 on the TryAii Score while still priced at $1.25/$10 per million input/output tokens — models at its level now sell for about $2.08 per million output tokens. DeepSeek V4.1 Flash matches it for $0.08 per million output tokens. Its best showing is #6 on AIME-2025. It's reasonably quick at about 66 tokens/sec.

Prompt $/1M

$1.250

Completion $/1M

$10.000

Context

400,000 tok

Best provider

67 tok/s · Azure

Specs

Model id: openai/gpt-5.1-codex
Display name: OpenAI: GPT-5.1-Codex
Modality: text+image->text
Tokenizer: GPT
Instruct type: —
Context length: 400,000
Max completion: 128,000
Prompt $/1M: $1.250
Completion $/1M: $10.000
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
Azurefastest	67	3,205 ms	4,590 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).