DevTk.AI

GPT-5.3-Codex

OpenAI

GPT-5.3-Codex by OpenAI costs $2/M input, $10/M output with 200K context window. Updated February 2026. Compare with GPT-5, Claude, Gemini & 40+ models.

Input Price

$2.00

per 1M tokens

Output Price

$10.00

per 1M tokens

Context Window

200K

tokens

Specifications

ProviderOpenAI
Model IDgpt-5-3-codex
Input Price$2 / 1M tokens
Output Price$10 / 1M tokens
Context Window200K tokens
Max Output33K tokens
Capabilities
textfunction_callingstructured_output
Release Date2026-02
NotesAgentic coding model. 25% faster than GPT-5.2.

Monthly Cost Estimates

Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split).

Daily TokensMonthly CostAnnual Cost
10K $1.80 $21.60
50K $9.00 $108.00
100K $18.00 $216.00
500K $90.00 $1080.00
1.0M $180.00 $2160.00

About GPT-5.3-Codex

GPT-5.3-Codex is a large language model by OpenAI. It features a 200K token context window with up to 33K tokens of output per request. The model supports 3 capabilities: text, function_calling, structured_output.

At $2 per million input tokens and $10 per million output tokens, GPT-5.3-Codex is positioned as a mid-range option in the OpenAI lineup. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.

Other OpenAI Models

Similar Price Range

Related Tools

FAQ

How much does GPT-5.3-Codex cost?

GPT-5.3-Codex costs $2 per million input tokens and $10 per million output tokens. For a typical workload of 100K tokens/day, expect approximately $21.00/month.

What is GPT-5.3-Codex's context window?

GPT-5.3-Codex supports a context window of 200K tokens. This means your combined input prompt and output response can be up to 200K tokens. The maximum output per response is 33K tokens.

Is GPT-5.3-Codex good for my use case?

GPT-5.3-Codex supports text, function_calling, structured_output. As a mid-range model, it balances capability and cost for most production use cases. Use our Pricing Calculator to compare with alternatives.