Using the Chat Completions API, you can directly access the fine-tuned models and tool used by Search in ChatGPT. When using Chat Completions, the model always retrieves information from the web before responding to your query. To use web_search_preview as a tool that models like gpt-4o and gpt-4o-mini invoke only when necessary, switch to using the Responses API. Currently, you need to use one of these models to use web search in Chat Completions: gpt-4o-search-preview gpt-4o-mini-search-preview Web search parameter example import OpenAI from "openai"; const client = new OpenAI(); const completion = await client.chat.completions.create({ model: "gpt-4o-search-preview", web_search_options: {}, messages: [{ "role": "user", "content": "What was a positive news story from today?" }], }); console.log(completion.choices[0].message.content); Output and citations The API response item in the choices array will include: message.content with the text result from the model, inclusive of any inline citations annotations with a list of cited URLs By default, the model's response will include inline citations for URLs found in the web search results. In addition to this, the url_citation annotation object will contain the URL and title of the cited source, as well as the start and end index characters in the model's response where those sources were used.
GPT 4o Mini Search Preview vs Kimi K3
Output tokens cost $0.60 per million on GPT 4o Mini Search Preview and $15.00 per million on Kimi K3. Input tokens cost $0.15 per million on GPT 4o Mini Search Preview and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.08 per million on GPT 4o Mini Search Preview and $0.30 per million on Kimi K3. Context lengths are 128,000 tokens on GPT 4o Mini Search Preview and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 1.6s on GPT 4o Mini Search Preview and 0.9s on Kimi K3. Measured output throughput is 189.0 tok/s on GPT 4o Mini Search Preview and 73.1 tok/s on Kimi K3.
Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence.
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
Tokens / day
Requests / day
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Throughput (tok/s)
TTFT (s)
Uptime (%)
Cost calculator
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: GPT 4o Mini Search Preview, Kimi K3?
GPT 4o Mini Search Preview: $0.60/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
Which responds faster?
Kimi K3: 0.9s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
How large is each context window?
GPT 4o Mini Search Preview accepts 128,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 16,384 tokens on GPT 4o Mini Search Preview and 1,048,576 tokens on Kimi K3.
Which one generates tokens faster?
GPT 4o Mini Search Preview at 189.0 tok/s and Kimi K3 at 73.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
GPT 4o Mini Search Preview accepts text and image input and supports web search, function calling and structured outputs; Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs.
Can I call GPT 4o Mini Search Preview and Kimi K3 with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
