Model overview
ReasoningVisionToolsGPT-5.4 balances high reasoning quality with lower cost than GPT-5.5. It supports text and image input, text output, long context, tool use, streaming, structured outputs, and Responses API access.
Company: OpenAIProvider: OpenAI
Model capabilities
Input modalityT
Output modalityT
Model experience✓
Function calling✓
Structured output✓
Web search✓
Prefix completion-
Context cache✓
Batch inference✓
Fine-tuning×
Model pricing
Input$2.50/1M tokens
Input (cache hit)$0.25/1M tokens
Output$15/1M tokens
Input (Batch)$1.25/1M tokens
Input (Batch cache hit)$0.13/1M tokens
Output (Batch)$7.50/1M tokens
Input (over 200K context)$5/1M tokens
Input cache hit (over 200K context)$0.50/1M tokens
Output (over 200K context)$22.50/1M tokens
Tool call pricing
Web search Responses API$10/1K calls + model token charges
File search Responses APIUsage based
Rate limits and context
Maximum input length1M
Context length1M
Maximum output length128K
Knowledge cutoff2025-08-31
Supported endpointsResponses / Chat Completions / Batch
API reference
EndpointPOST /v1/chat/completions or POST /v1/responses
SDKOpenAI-compatible
API code examples
from openai import OpenAI client = OpenAI( api_key="$WLROUTER_API_KEY", base_url="https://api.wlrouter.com/v1" ) response = client.chat.completions.create( model="gpt-5.4", messages=[ {"role": "user", "content": "Reply with one short sentence."} ], max_tokens=32 ) print(response.choices[0].message.content)