GPT-5.3 Codex
gpt-5.3-codexGPT-5.3 Codex by OpenAI: 400K context, 128K max output, with Vision, Function Calling, Reasoning, Prompt Caching, Streaming. Via KumoAPI, Input (prompt) costs 1.75 Credits / M tokens.
Capabilities
Listed exactly as the catalog flags them, including what this model does not support.
Vision
Natively multimodal: captioning, classification, visual Q&A, chart and screenshot understanding. Images are converted to tokens at the input rate.
Function Calling
Connect the model to external tools and APIs: it decides when to call which function and with what arguments, your code runs it. Force or forbid calls with tool_choice.
Reasoning
The model thinks before answering, which markedly improves multi-step planning and reasoning for coding, math and data analysis. Thinking tokens bill at the output rate.
Prompt Caching
Repeated prefixes (system prompts, long documents) hit the cache: reads cost far less than input, writes are priced by retention time.
Streaming
Tokens arrive over SSE as they are generated; the first frame is forwarded immediately with no buffering. Claude Code, Codex and similar tools depend on this.
Response SchemaNot supported
Constrain output to a JSON Schema you provide for predictable, type-safe results without parsing free text.
AudioNot supported
Audio input or speech output.
VideoNot supported
Video input understanding or video generation.
File InputNot supported
Upload PDFs and other documents directly; the model reads the whole document with native vision.
Web SearchNot supported
Vendor-hosted live web retrieval; the model decides when to search and cites sources.
RealtimeNot supported
Bidirectional low-latency voice / text sessions over WebSocket.
SessionNot supported
Server-side multi-turn context (e.g. previous_response_id in Responses) so you need not resend history.
MediaNot supported
Image / video / music generation endpoints.
Multipart FormNot supported
multipart/form-data file-upload requests.
Binary ResponseNot supported
Endpoints that return raw audio / image bytes.
Full price list
List price → KumoAPI price per channel, every pricing dimension, nothing hidden.
| Item | Unit | OpenAI list price | KumoAPI ×1 |
|---|---|---|---|
| Input (prompt) | per 1M tokens | 1.75 Credits | |
| Output (completion) | per 1M tokens | 14 Credits | |
| Cache read | per 1M tokens | 0.175 Credits |
“Off” is computed at 1 Credit = ¥1 and today’s rate: 1 − channel multiplier × (1 Credit in the list currency).
FAQ
How much does the GPT-5.3 Codex API cost?
Via KumoAPI, Input (prompt) costs 1.75 Credits / M tokens, with 1 Credit = ¥1.
What are the context window and output limit of GPT-5.3 Codex?
Context window 400K tokens, up to 128K tokens per response.
Does GPT-5.3 Codex support function calling and structured outputs?
Function calling with tool_choice control is supported; structured outputs (JSON Schema) are not enabled — use a function-call parameter schema for type-safe results instead.
One API key for GPT-5.3 Codex and 30+ models
Free credits on sign-up, pay as you go, no monthly fee.