OpenAI: GPT-5.3-Codex
by OpenAIOpenAI: GPT-5.3-Codex is a large language model from OpenAI. It costs $1.75 per million input tokens and $14.00 per million output tokens. Its context window is 400K tokens.
- Input / 1M tokens
- $1.75
- Output / 1M tokens
- $14.00
- Cached input / 1M
- $0.175
- Context window
- 400K
On repeated prefixes
tokens
This model also charges $0.01 per search request
That is $10.00 per 1,000 requests, billed on top of the token prices above. On a typical 1,000-in / 500-out exchange the tokens cost $0.0088, so the search fee is 1.1× the token cost. Per-token rankings elsewhere ignore this entirely.
Who serves it cheapest
2 hosts serve GPT-5.3-Codex. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| AzureCheapest | $1.75 | $14.00 | 400K | - | 100.0% |
| OpenAI | $1.75 | $14.00 | 400K | - | 99.9% |
The spread between Azure and OpenAI is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.
About GPT-5.3-Codex
GPT-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. It achieves state-of-the-art results...
Specifications
| Model ID | openai/gpt-5.3-codex |
|---|---|
| Provider | OpenAI |
| Context window | 400K tokens |
| Max output | 128K tokens |
| Input modalities | text, image, file |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | No |
| Released | February 24, 2026 |
Cheaper alternatives
Models that cost less than GPT-5.3-Codex while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does OpenAI: GPT-5.3-Codex cost?
$1.75 per million input tokens and $14.00 per million output tokens. Cached input reads cost $0.175 per million tokens.
What is the context window of OpenAI: GPT-5.3-Codex?
400K tokens, with up to 128K tokens of output per request.
Does OpenAI: GPT-5.3-Codex have extra fees beyond per-token pricing?
Yes. OpenAI: GPT-5.3-Codex charges $0.01 per search request - $10.00 per 1,000 requests - on top of $1.75 per million input tokens and $14.00 per million output tokens. On a typical 1,000-input / 500-output exchange the search fee alone is 1.1× the token cost.
Which provider serves OpenAI: GPT-5.3-Codex cheapest?
Azure at $1.75 per million input tokens - about the same cheaper than OpenAI, the most expensive of the 2 hosts serving it.
Confirm against the source: OpenAI official pricing.