GPT-5.3 Codex

OpenAIReleased Feb 5, 2026

GPT-5.3 Codex is not ranked on LMArena yet; output price $14.00 per 1M tokens.

Key metrics

Arena score–Not yet rated
Intelligence32.5Variant: xhigh
Coding–Artificial Analysis
List price in / out$1.75 / $14.00USD per 1M tokens
Lowest route$1.75 / $14.00Cheapest OpenRouter route
Context400Ktokens
Output speed94tok/sAA measured median
TTFT / first answer50 / 50sReasoning model: includes thinking

More from OpenAI

#ModelArenaIntel.Output $tok/s
22GPT-5.51471.538.4$30.00–
27GPT-5.41469.039.0$15.00–
35GPT-5.6 Sol1457.347.0$20.00–
44GPT-5.6 Terra1446.542.1$12.00111
45GPT-6.1 Sol1446.551.8$10.0058
48GPT-5.11442.724.7$10.00–

Pricing

  • Official API list price: $1.75 input and $14.00 output per 1M tokens (USD).
  • At a typical 3:1 input-to-output ratio, the blended cost is about $4.81 per 1M tokens.
  • Among 78 models with an output price, it is the #61 cheapest.
  • The cheapest OpenRouter route charges $1.75 input / $14.00 output.

Sources & methodology

GPT-5.3 Codex (OpenAI): Intelligence Index 32.5, $1.75 in / $14.00 out per 1M tokens, 400K context. Data updated Oct 9, 2026.

  • LMArena — Arena score, 95% confidence interval, votes and rank.
  • Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
  • OpenRouter — Route prices, context length and listing date.

Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).

FAQ

What rank is GPT-5.3 Codex right now?

GPT-5.3 Codex has not been scored by LMArena yet, so it is not ranked here.

What does GPT-5.3 Codex cost via API?

Input $1.75 / output $14.00 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $4.81 per 1M tokens.

How fast is GPT-5.3 Codex?

Artificial Analysis measures about 94 output tokens per second, 50 s to the first token and 50 s to the first answer token; it is a reasoning model, so latency includes thinking time.

Is GPT-5.3 Codex open source? Can it be self-hosted?

GPT-5.3 Codex is a closed model, available only via official APIs or hosted services.

What is the context length of GPT-5.3 Codex?

400K (400,000 tokens, as listed on OpenRouter).

Related leaderboards