gpt-5.3-codexGPT-5.3 Codex pricing (October 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 38 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.
Looking for the ChatGPT / Claude app subscription price? That is a separate consumer product sold by OpenAI. This page is the developer API price per token.
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.
| Provider | Input | Cached input | Output | Context | Source |
|---|---|---|---|---|---|
| OpenAI | $1.75 | $0.175 | $14.00 | 272K | OpenAI |
| Azure | $1.75 | $0.175 | $14.00 | 272K | Azure OpenAI |
| AWS Bedrock | No verified quote | ||||
| Google Vertex AI | No verified quote | ||||
| OpenRouter | No verified quote | ||||
| Crazyrouter | $1.40 | $0.14 | $11.20 | 272K | crazyrouter.com |
per 1M tokens · Snapshot Oct 24, 2026
What GPT-5.3 Codex costs per month
Three typical workloads, priced on each provider from the table above.
| Workload | OpenAI | Azure | Crazyrouter |
|---|---|---|---|
| Prototype: 10M in / 2M out | $45.50 | $45.50 | $36.40 |
| Product: 100M in / 20M out | $455.00 | $455.00 | $364.00 |
| Scale: 1B in / 200M out | $4,550 | $4,550 | $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.
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: Oct 24, 2026. Crazyrouter rates come from our billing table; confirm current prices, region and terms with the provider before purchase.
- OpenAI — openai.com/api/pricing
- Azure — azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service
- Crazyrouter — crazyrouter.com/pricing
- LiteLLM