OpenAI model

GPT-5.1-Codex-Mini API

openai/gpt-5.1-codex-mini is an OpenAI catalog model with 400000 token context, $0.25 per 1M input tokens, and $2 per 1M output tokens. It has streaming, tool, json, vision, and long capabilities. Its use cases are vision, long-context, and agent.

Read quickstartEstimate cost
OpenAIPlatform curatedCatalog
ThinkingFunction CallingVision
Input price$0.25 / 1M tokens
Output price$2 / 1M tokens
Context length400k tokens
Max output8.2k tokens

What is GPT-5.1-Codex-Mini API in NextModel?

openai/gpt-5.1-codex-mini is an OpenAI catalog model with 400000 token context, $0.25 per 1M input tokens, and $2 per 1M output tokens. It has streaming, tool, json, vision, and long capabilities. Its use cases are vision, long-context, and agent.

GPT-5.1 Codex Mini via NextModel: 400k-token context; $0.25 / 1M tokens in / $2 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Best use cases

  • Call this id when you need vision plus a 400000 token context window, or when you are building agent and long-context tasks on the OpenAI gateway.
  • Call it if the price points match your budget and you do not require a first-party CacheSafety score.
  • You need the listed capabilities on this catalog entry.

When not to use

  • Do not call this id if your selection process depends on CacheSafety, because no first-party score is published for openai/gpt-5.1-codex-mini.
  • Do not call it if you need a cheaper output model or a larger context window than 400000 tokens.
  • A required number is unpublished in the catalog snapshot.

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-5.1-codex-mini","messages":[{"role":"user","content":"Reply with OK."}]}'

Switching models only changes the model field.

Try it in the playground

Similar alternatives

OpenAICatalog

GPT-5.1

GPT-5.1 via NextModel: 400k-token context; $1.25 / 1M tokens in / $10 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$1.25 / 1M tokensInput$10 / 1M tokensOutput400kContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details
OpenAICatalog

GPT-5.1 Codex

GPT-5.1 Codex via NextModel: 400k-token context; $1.25 / 1M tokens in / $10 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$1.25 / 1M tokensInput$10 / 1M tokensOutput400kContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details
OpenAICatalog

GPT-4.1

GPT-4.1 via NextModel: 1M-token context; $2 / 1M tokens in / $8 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$2 / 1M tokensInput$8 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details

Compare GPT-5.1 Codex Mini

GPT-5.1 Codex Mini vs GPT-5.1GPT-5.1 Codex Mini vs GPT-5.1 CodexGPT-5.1 Codex Mini vs GPT-4.1GPT-5.1 Codex Mini vs GPT-4.1 MiniGPT-5.1 Codex Mini vs GPT-4.1 Nano

Reading

Articles that explain GPT-5.1 Codex Mini

FAQ

GPT-5.1 Codex Mini API questions

What model id do I send for GPT-5.1-Codex-Mini?

Send openai/gpt-5.1-codex-mini 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-5.1-Codex-Mini is listed at $0.25 / 1M tokens input and $2 / 1M tokens output. Context window: 400000 tokens.

What should I treat as unverified?

Do not call this id if your selection process depends on CacheSafety, because no first-party score is published for openai/gpt-5.1-codex-mini. Do not call it if you need a cheaper output model or a larger context window than 400000 tokens.

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