Skip to content

Model Library

OpenAIReleased February 5, 2026

GPT-5.3 Codex (xhigh)

OpenAI · Released February 5, 2026

Intelligence score

44

At a glance

Intelligence
44
Speed
99.0tokens/sec
Latency
98.73stime to first token
Input price
$1.75per 1M tokens
Output price
$14.00per 1M tokens
Context window
400Ktokens
Parameters
—

Summary

Comparison summary

GPT-5.3 Codex (xhigh) scores 44 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 28). GPT-5.3 Codex (xhigh) generates output at 99.0 tokens per second (based on OpenAI's API), which is above average compared to other reasoning models in a similar price tier (median: 81.2 t/s). GPT-5.3 Codex (xhigh) costs $1.75 per 1M input tokens (somewhat higher than average, median: $1.50) and $14.00 per 1M output tokens (somewhat higher than average, median: $8.40), based on OpenAI's API.

Specifications

Technical specifications

Model nameGPT-5.3 Codex (xhigh)
ProviderOpenAI
Release dateFebruary 5, 2026
Intelligence score44
Speed99.0 tokens/sec
Latency (TTFT)98.73s
Input price$1.75 / 1M tokens
Output price$14.00 / 1M tokens
Context window400,000 tokens
Parameters—
ReasoningYes
Input modalitiestext, image
Output modalities—
Open weightsNo
License—
API availability—
SourceModel Intelligence legacy profile: gpt-5-3-codex

Pricing

Token prices

Price per 1M tokens

GPT-5.3 Codex (xhigh), as listed in the catalog record

Input $1.75 and output $14.00 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$1.75
  2. Output$14.00

Model Intelligence legacy profile: gpt-5-3-codex

FAQ · 19

Frequently asked questions

GPT-5.3 Codex (xhigh) was released on February 5, 2026.

GPT-5.3 Codex (xhigh) was created by OpenAI.

GPT-5.3 Codex (xhigh) scores 44 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 28).

GPT-5.3 Codex (xhigh) generates output at 99.0 tokens per second (based on OpenAI's API), which is above average compared to other reasoning models in a similar price tier (median: 81.2 t/s).

GPT-5.3 Codex (xhigh) has a time to first token (TTFT) of 98.73s (based on OpenAI's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 2.78s).

GPT-5.3 Codex (xhigh) costs $1.75 per 1M input tokens (somewhat higher than average, median: $1.50) and $14.00 per 1M output tokens (somewhat higher than average, median: $8.40), based on OpenAI's API.

GPT-5.3 Codex (xhigh) costs $1.75 per 1M input tokens and $14.00 per 1M output tokens (based on OpenAI's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.87 per 1M tokens. Pricing may vary by provider.

Yes, GPT-5.3 Codex (xhigh) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

GPT-5.3 Codex (xhigh) supports text and image input.

GPT-5.3 Codex (xhigh) supports text output.

Yes, GPT-5.3 Codex (xhigh) supports image input and can analyze, describe, and answer questions about images.

Yes, GPT-5.3 Codex (xhigh) is multimodal. It can process text and image input and generate text output.

GPT-5.3 Codex (xhigh) has a context window of 400k tokens. This determines how much text and conversation history the model can process in a single request.

No, GPT-5.3 Codex (xhigh) is proprietary. The model weights are not publicly available.

GPT-5.3 Codex (xhigh) is a proprietary model and OpenAI has not disclosed the model size or parameter count.

GPT-5.3 Codex (xhigh) achieves a score of 44 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

GPT-5.3 Codex (xhigh) has a knowledge cutoff of August 2025. The model's training data includes information up to this date.

Yes, GPT-5.3 Codex (xhigh) is available via API through 1 provider.

GPT-5.3 Codex (xhigh) is available through 1 API provider.