What gpt-5.3-codex costs for real workloads
| Workload | Estimated cost |
|---|---|
| Support chatbot: 100K messages | $560.00 |
| RAG search: 10K queries with 6K-token context | $175.00 |
| Batch summarization: 1,000 long documents | $49.00 |
| Coding agent: 100 tasks, 50K context x 20 turns | $53.38 |
Chatbot: 800 input + 300 output tokens per message. RAG: 6,000 + 500 per query. Summarization: 20,000 + 1,000 per document. Coding agent: 20 turns per task over a 50K-token context, with 95% of input served from cache where the model supports it.
gpt-5.3-codex vs similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached / 1M | Blended |
|---|---|---|---|---|---|
| Qwen3.7-Max | Together AI | $2.50 | $7.50 | $0.50 | $3.75 |
| gpt-6.1-sol | OpenAI | $2.00 | $10.00 | $0.10 | $4.00 |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | $0.10 | $4.00 |
| Gemini 3 Pro | $2.00 | $10.00 | $0.10 | $4.00 | |
| Gemini 4 Argon | $2.00 | $10.00 | $0.10 | $4.00 | |
| Kimi K3.1 Pro | Together AI | $2.00 | $10.00 | $0.20 | $4.00 |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | $0.20 | $4.50 | |
| gpt-5.3-codex | OpenAI | $1.75 | $14.00 | $0.17 | $4.81 |
| Kimi K3 | Together AI | $3.00 | $15.00 | $0.30 | $6.00 |
Other OpenAI models
gpt-5.3-codex pricing FAQ
How much does the gpt-5.3-codex API cost?
gpt-5.3-codex costs $1.75 per million input tokens and $14.00 per million output tokens on OpenAI, with cached input at $0.17 per million. Prices as of November 8, 2026.
How much does gpt-5.3-codex cost for 1,000 requests?
At 1,000 input and 500 output tokens per request, 1,000 requests cost about $8.75.
Does gpt-5.3-codex have a prompt caching discount?
Yes. Cached input is $0.17 per million tokens, 10x cheaper than fresh input. Workloads that resend the same context, like agents and chat with long system prompts, pay mostly the cached rate.
Is gpt-5.3-codex expensive compared to other LLM APIs?
It ranks #67 cheapest of 76 models we track on a blended price (3 input tokens per output token) of $4.81 per million tokens.
Picking a model for production?
Describe your workload and the Planner estimates monthly token spend across every model we track.