Output tokens cost $10.00 per million on GPT 4o Audio Preview and $15.00 per million on Kimi K3. Input tokens cost $2.50 per million on GPT 4o Audio Preview and $3.00 per million on Kimi K3. Cached input tokens are billed at $2.50 per million on GPT 4o Audio Preview and $0.30 per million on Kimi K3. Context lengths are 128,000 tokens on GPT 4o Audio Preview and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 2.5s on GPT 4o Audio Preview and 0.9s on Kimi K3. Measured output throughput is 10.4 tok/s on GPT 4o Audio Preview and 73.1 tok/s on Kimi K3.
GPT 4o Audio Preview
Kimi K3OpenAI voice input and output model, with prices consistent with the official ones. For now, only the text portion prices are displayed; voice prices can be found on the official OpenAI website. Backend billing is the same as the official.
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.
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.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
GPT 4o Audio Preview: $10.00/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
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.
GPT 4o Audio Preview accepts 128,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 16,384 tokens on GPT 4o Audio Preview and 1,048,576 tokens on Kimi K3.
Kimi K3 at 73.1 tok/s and GPT 4o Audio Preview at 10.4 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
GPT 4o Audio Preview accepts text and audio input; Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs.
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.
Related model match-ups readers also look at.
AIHubMix