GPT-5.4 Nano API

Model details

Context window

400K tokens

Max output

128K tokens

Input

Text, images

Output

Text

Capabilities

Reasoning, Vision, Tool calling, Streaming, JSON output

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• GPT-5.4 Nano for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call GPT-5.4 Nano

GPT-5.4 Nano answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-5.4-nano",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-5.4-nano",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-5.4-nano",
  "input": "Hello"
}'

Use GPT-5.4 Nano in your tools

Every coding agent below has a setup guide. Set the model to gpt-5.4-nano.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

More from OpenAI

Alternatives to GPT-5.4 Nano

• Llama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Meta
• DeepSeek V4.1 Flash CyberDeepSeek V4.1 Flash Cyber for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.DeepSeek
• CodestralCodestral for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Mistral

Questions about this model

How much does the GPT-5.4 Nano API cost?

GPT-5.4 Nano costs $0.2 per 1M input tokens and $1.25 per 1M output tokens on Inferray, and cached input is $0.02 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for GPT-5.4 Nano?

No. You add credit and pay GPT-5.4 Nano's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is GPT-5.4 Nano included in Token Plans?

No. GPT-5.4 Nano is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use GPT-5.4 Nano in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to gpt-5.4-nano. The same key works in Codex, opencode, Cline, and other agents.

Does GPT-5.4 Nano support tool calling and vision?

GPT-5.4 Nano supports tool calling, image input, reasoning, JSON output and streaming on Inferray.

Is it the real GPT-5.4 Nano?

Yes. A request for gpt-5.4-nano is answered by GPT-5.4 Nano from OpenAI, billed at its published list price. Inferray never substitutes a different or smaller model.