OpenAI model

GPT-5.3-Codex API

Call openai/gpt-5.3-codex only if you accept its 400000 token context and $14 output price; walk away if you need first-party CacheSafety, because it is unpublished for this exact model. This id has an input price of $1.75 per million tokens, a 400000 token context window, and a 1000 to 3000ms latency band. It has streaming, tool, json, vision, and long capabilities.

Read quickstartEstimate cost
OpenAIPlatform curatedCatalog
ThinkingFunction CallingVision
Input price$1.75 / 1M tokens
Output price$14 / 1M tokens
Context length400k tokens
Max output8.2k tokens

What is GPT-5.3-Codex API in NextModel?

Call openai/gpt-5.3-codex only if you accept its 400000 token context and $14 output price; walk away if you need first-party CacheSafety, because it is unpublished for this exact model. This id has an input price of $1.75 per million tokens, a 400000 token context window, and a 1000 to 3000ms latency band. It has streaming, tool, json, vision, and long capabilities.

GPT-5.3 Codex via NextModel: 400k-token context; $1.75 / 1M tokens in / $14 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Best use cases

  • Call openai/gpt-5.3-codex if you need a 400000 token context, vision input, long-context work, or agent use cases, and you accept the listed latency band of 1000 to 3000ms.
  • You need the listed capabilities on this catalog entry.
  • The listed price fits the workload better than the siblings in the same family.

When not to use

  • Do not call openai/gpt-5.3-codex if you require published first-party CacheSafety data, because this exact model has no CacheSafety row in the catalog notes.
  • A required number is unpublished in the catalog snapshot.
  • You need a first-party CacheSafety score and this model does not have one.

OpenAI-compatible code example

request.sh
curl https://api.nextmodel.app/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NEXTMODEL_API_KEY" \
  -d '{"model":"openai/gpt-5.3-codex","messages":[{"role":"user","content":"Reply with OK."}]}'

Switching models only changes the model field.

Try it in the playground

Similar alternatives

OpenAICatalog

GPT-5.4

GPT-5.4 via NextModel: 1M-token context; Starting at $2.50 / 1M tokens in / $15 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Starting at $2.50 / 1M tokensInput$15 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details
OpenAICatalog

GPT-5.4 Pro

GPT-5.4 Pro via NextModel: 1M-token context; Starting at $30 / 1M tokens in / $180 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Starting at $30 / 1M tokensInput$180 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details
OpenAICatalog

GPT-5.4 Mini

GPT-5.4 Mini via NextModel: 400k-token context; $0.75 / 1M tokens in / $4.50 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$0.75 / 1M tokensInput$4.50 / 1M tokensOutput400kContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details

Compare GPT-5.3 Codex

GPT-5.3 Codex vs GPT-5.4GPT-5.3 Codex vs GPT-5.4 ProGPT-5.3 Codex vs GPT-5.4 MiniGPT-5.3 Codex vs GPT-5.4 NanoGPT-5.3 Codex vs GPT-5.2 Codex

Reading

Articles that explain GPT-5.3 Codex

FAQ

GPT-5.3 Codex API questions

What model id do I send for GPT-5.3-Codex?

Send openai/gpt-5.3-codex to https://api.nextmodel.app/v1 with your OpenAI SDK. If that id is missing from /v1/models, the page is stale.

What does the catalog list for price and context?

GPT-5.3-Codex is listed at $1.75 / 1M tokens input and $14 / 1M tokens output. Context window: 400000 tokens.

What should I treat as unverified?

Do not call openai/gpt-5.3-codex if you require published first-party CacheSafety data, because this exact model has no CacheSafety row in the catalog notes.

Start now

Ready to start building?

Passwordless signup, pay-as-you-go billing, and one OpenAI-compatible endpoint for every model. Create your key and send your first request in minutes.

Get your API keyRead the quickstart