Pricingby GlyphGPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.
Ways to buy 3
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
The lab's own API · cached $0.175 | $1.75 | $14 | $1.75 / $14List price | $0.175 | List price |
Default region · cached $0.175 | $1.75 | $14 | $1.75 / $14Same as list | $0.175 | Same as list |
fast · cached $0.35 | $3.5 | $28 | $3.5 / $28+100% vs list | $0.35 | +100% vs list |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $455.00 direct.
Kong AI Gateway$455.00+0%
LiteLLM$455.00+0%
Neon AI Gateway$455.00+0%
Vercel AI Gateway$455.00+0%
Requesty$477.75+5%
Eden AI$480.02+5.5%
OpenRouter$480.02+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
OpenAI · 1.05MCheapest: $1 on OpenAI (flex) | $1 | $5 | $1 / $5 | $2 | 1.05M | $1 on OpenAI (flex) | · | GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. |
OpenAI · 1.05MCheapest: $1 on OpenAI (flex) | $1 | $5 | $1 / $5 | $2 | 1.05M | $1 on OpenAI (flex) | · | GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. |
OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · | GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. |
OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · | GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. |
Anthropic · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · | Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. |
Google · 1MCheapest: $2 on Google Gemini API (flex) | $2 | $10 | $2 / $10 | $4 | 1M | $2 on Google Gemini API (flex) | · | Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. |
Anthropic · 1M | $2 | $10 | $2 / $10 | $4 | 1M | Lab list price | · | Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. |
Anthropic · 1M | $5 | $25 | $5 / $25 | $10 | 1M | Lab list price | · | Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. |
About GPT-5.3-Codex
Takes text, image, files in and returns text. First listed Mar 3, 2026. Up to 128K output tokens. Blended price $4.81 per 1M tokens at 3 input to 1 output. Model id gpt-5-3-codex.
Price history
List price since Mar 3, 2026, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
Questions
How much does GPT-5.3-Codex cost?
$1.75 per million input tokens and $14 per million output tokens, with cached input at $0.175.
What is the context window of GPT-5.3-Codex?
400K tokens, with up to 128K tokens of output.
Where is GPT-5.3-Codex cheapest?
Of 3 routes tracked, Azure AI Foundry is cheapest at $1.75 input and $14 output per million tokens.