OpenAI · gpt-5.3-codex

GPT-5.3 Codex pricing (November 2026)

OpenAI lists GPT-5.3 Codex at $1.75 per 1M input tokens and $14.00 per 1M output tokens.

On Crazyrouter the same model is $1.40 / $11.20 — 20% below list price.

That is $0.00175 / $0.014 per 1K tokens. GPT-5.3 Codex is the #19 cheapest of the 40 chat models we track, by input price. 1.4× the price of GPT-5 Codex. Through Crazyrouter you save $0.35 on every 1M input tokens versus list.

Call GPT-5.3 Codex at $1.40 in / $11.20 out per 1M tokens. Same model, same API, no plan — pay per token.

This page lists token-based pricing for the developer API. Consumer app subscriptions are billed separately.

GPT-5.3 Codex price by provider

USD per 1M tokens. Cloud prices are the base tier in the default region; the linked source is authoritative.

per 1M tokensInputOutput
  • OpenAI$1.75$14.00
  • Azure$1.75$14.00
  • Crazyrouter$1.40$11.20
ProviderInputCached inputOutputContextSource
OpenAI$1.75$0.175$14.00272KOpenAI
Azure$1.75$0.175$14.00272KAzure OpenAI
Crazyrouter$1.40$0.14$11.20272Kcrazyrouter.com

AWS Bedrock · Google Vertex AI · OpenRouter: No verified quote

per 1M tokens · Snapshot Nov 13, 2026

What GPT-5.3 Codex costs per month

Three typical workloads, priced on each provider from the table above.

  • Prototype: 10M in / 2M out

    Input 10M · Output 2M

    $36.40

    • OpenAI$45.50
    • Azure$45.50
    • Crazyrouter$36.40
  • Product: 100M in / 20M out

    Input 100M · Output 20M

    $364.00

    • OpenAI$455.00
    • Azure$455.00
    • Crazyrouter$364.00
  • Scale: 1B in / 200M out

    Input 1,000M · Output 200M

    $3,640

    • OpenAI$4,550
    • Azure$4,550
    • Crazyrouter$3,640

Price changes

  • Sep 3, 2026 — OpenRouter started listing GPT-5.3 Codex at $1.75 / $14.00 per 1M.
  • Feb 25, 2026 — Azure started listing GPT-5.3 Codex at $1.75 / $14.00 per 1M.
  • Feb 24, 2026 — OpenAI started listing GPT-5.3 Codex at $1.75 / $14.00 per 1M.

Alternatives to GPT-5.3 Codex

Same-family models and cheaper options for similar tasks.

Guides and comparisons

Podcast

AI Dev Tools: The Crazyrouter Podcast

Short episodes for developers on AI APIs, gateways, cost control and coding tools.

Latest episodes

  • EP196 · Oct 29, 2026 · 6:53

    AI API Security Posture — Turn Controls Into Continuous Evidence

    A practical guide to AI API security posture: inventory exposure, verify controls continuously, protect keys and data, constrain tools, and turn security assumptions into evidence that operators can act on.

  • EP195 · Oct 28, 2026 · 7:21

    AI API Policy Drift — Detect When Production Rules Stop Matching Intent

    A practical guide to policy drift in AI APIs: version routing and safety rules, detect stale enforcement, compare intended and observed behavior, and restore control before small gaps become incidents.

Episodes with written show notes →

GPT-5.3 Codex pricing FAQ

How much does GPT-5.3 Codex cost?

OpenAI charges $1.75 per 1M input tokens and $14.00 per 1M output tokens. Through Crazyrouter the same model is $1.40 / $11.20.

What is cached input pricing?

Tokens that repeat an earlier prompt prefix are billed at the cached rate ($0.175 per 1M when supported) instead of the full input price.

Is there a batch discount?

No public batch tier is listed for GPT-5.3 Codex; Crazyrouter's per-token price applies to all requests.

Is GPT-5.3 Codex cheaper on Azure, Bedrock or Vertex?

Cloud providers usually match the list price and add regional or provisioned tiers; see the table above for the base rate on each. Crazyrouter applies its discount on top of list.

Sources and method

Provider reference prices use LiteLLM data and maintained entries. Provider links are references, not proof of daily official verification. Snapshot: Nov 13, 2026. Crazyrouter rates come from our billing table; confirm current prices, region and terms with the provider before purchase.

Further reading