Back to models
GPT-5.3-Codex vs Claude Sonnet 4.6
GPT-5.3-Codex and Claude Sonnet 4.6: current price, context, max output, and supported operations.
Pricing comparison
| GPT-5.3-Codex | Claude Sonnet 4.6 | |
|---|---|---|
| Model maker | OpenAI | Anthropic |
| Delivery availability | Available | Available |
| Context window | 400K | 1M |
| Max output | 128K | 128K |
| Official price | Input$1.75per 1M tokensOutput$14.00per 1M tokens | Input$3.00per 1M tokensOutput$15.00per 1M tokens |
| Verified price | Input$1.23per 1M tokensOutput$9.80per 1M tokens | Input$0.90per 1M tokensOutput$4.50per 1M tokens |
| Model performance | Collecting data |
|
| Capabilities | JSON modePrompt CacheTool useVision | JSON modePrompt CacheReasoningTool useVision |
Summary
- GPT-5.3-Codex: Input $1.23 / Output $9.80 per 1M tokens; Claude Sonnet 4.6: Input $0.90 / Output $4.50 per 1M tokens. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
- Claude Sonnet 4.6 has a 2.5x larger context window
FAQ
Which is cheaper, GPT-5.3-Codex or Claude Sonnet 4.6?
GPT-5.3-Codex: Input $1.23 / Output $9.80 per 1M tokens; Claude Sonnet 4.6: Input $0.90 / Output $4.50 per 1M tokens. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the key differences between GPT-5.3-Codex and Claude Sonnet 4.6?
Claude Sonnet 4.6: Reasoning