GPT-5.3 Codex API Pricing
As of October 10, 2026, GPT-5.3 Codex costs $1.75 per 1M input tokens and $14.00 per 1M output tokens on OpenAI, with cache reads at $0.175 per 1M tokens. Across 7 providers on LiteLLM, the input price ranges from $1.75 to $3.50. It has a 272,000-token context window and returns up to 128,000 tokens per response.
gpt-5.3-codex.- Input
- $1.75 / 1M tokens
- Output
- $14.00 / 1M tokens
- Cache read
- $0.175 / 1M tokens
- Context window
- 272,000 tokens
- Max output
- 128,000 tokens
- Providers
- 7
- Added to LiteLLM
- February 2026
GPT-5.3 Codex pricing by provider
9 listings across 7 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Cache write | Context |
|---|---|---|---|---|---|---|
| OpenAI | gpt-5.3-codex | $1.75 | $14.00 | $0.175 | – | 272K |
| AIHubMix | aihubmix/gpt-5.3-codex | $1.75 | $14.00 | $0.175 | – | 400K |
| Azure OpenAI | azure/gpt-5.3-codex | $1.75 | $14.00 | $0.175 | – | 272K |
| ChatGPT Subscription | chatgpt/gpt-5.3-codex | – | – | – | – | 128K |
| Databricks | databricks/databricks-gpt-5-3-codex | $1.75 | $14.00 | $0.175 | $1.75 | 272K |
| GitHub Copilot | github_copilot/gpt-5.3-codex | $1.75 | $14.00 | $0.175 | – | 128K |
| Perplexity | perplexity/openai/gpt-5.3-codex | $3.50 | $28.00 | $0.35 | – | – |
| Azure OpenAIeu | azure/eu/gpt-5.3-codex | $1.925 | $15.40 | $0.1925 | – | – |
| Azure OpenAIus | azure/us/gpt-5.3-codex | $1.925 | $15.40 | $0.1925 | – | – |
Other GPT-5.3 Codex prices on OpenAI
| Priority input | $3.50 per 1M tokens |
| Priority output | $28.00 per 1M tokens |
| Web search | $10.00 per 1K searches |
What GPT-5.3 Codex costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| OpenAI | $10.50 |
| AIHubMix | $10.50 |
| Azure OpenAI | $10.50 |
| Databricks | $10.50 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| OpenAI | $20.30 |
| AIHubMix | $20.30 |
| Azure OpenAI | $20.30 |
| Databricks | $20.30 |
GPT-5.3 Codex features
Input: text, image. Output: text.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- PDF input
- Reasoning
- Prompt caching
- Web search
Use GPT-5.3 Codex with LiteLLM
Call GPT-5.3 Codex through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/responses. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="gpt-5.3-codex",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-5.3-codex
litellm_params:
model: gpt-5.3-codex
api_key: os.environ/OPENAI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-5.3-codex",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT-5.3 Codex FAQ
How much does GPT-5.3 Codex cost?
GPT-5.3 Codex costs $1.75 per 1M input tokens and $14.00 per 1M output tokens on OpenAI, with cache reads at $0.175 per 1M tokens. Across 7 providers on LiteLLM, the input price ranges from $1.75 to $3.50.
What is the context window of GPT-5.3 Codex?
GPT-5.3 Codex has a 272,000-token context window and returns up to 128,000 tokens per response.
Which providers offer GPT-5.3 Codex?
GPT-5.3 Codex is available from 7 providers through LiteLLM: OpenAI, AIHubMix, Azure OpenAI, ChatGPT Subscription, Databricks, GitHub Copilot and Perplexity. The lowest price is on OpenAI.
How do I call GPT-5.3 Codex with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gpt-5.3-codex", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/responses from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does GPT-5.3 Codex support?
GPT-5.3 Codex supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search.
When did LiteLLM add GPT-5.3 Codex?
GPT-5.3 Codex was added to LiteLLM's model price file in February 2026.
Is GPT-5.3 Codex being deprecated?
OpenAI lists a deprecation date of April 1, 2027 for gpt-5.3-codex.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- developers.openai.com/api/docs/pricing
- aihubmix.com/api/v1/models
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
- www.databricks.com/product/pricing/proprietary-foundation-model-serving
LiteLLM docs: OpenAI, AIHubMix, Azure OpenAI, ChatGPT Subscription, Databricks, GitHub Copilot.
Provider pages: OpenAI, AIHubMix, Azure OpenAI, ChatGPT Subscription, Databricks, GitHub Copilot, Perplexity.
