Output tokens cost $3.80 per million on Baidu DeepSeek V4 Pro 0813 and $15.00 per million on Kimi K3. Input tokens cost $1.27 per million on Baidu DeepSeek V4 Pro 0813 and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.13 per million on Baidu DeepSeek V4 Pro 0813 and $0.30 per million on Kimi K3. Context lengths are 1,000,000 tokens on Baidu DeepSeek V4 Pro 0813 and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 1.7s on Baidu DeepSeek V4 Pro 0813 and 0.9s on Kimi K3. Measured output throughput is 39.1 tok/s on Baidu DeepSeek V4 Pro 0813 and 73.1 tok/s on Kimi K3.
Baidu DeepSeek V4 Pro 0813
Kimi K3DeepSeek-V4 features an ultra-long context of one million characters and achieves leading performance domestically and in the open-source domain in agent capabilities, world knowledge, and reasoning.
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.
Baidu DeepSeek V4 Pro 0813: $3.80/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.
Baidu DeepSeek V4 Pro 0813 accepts 1,000,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 384,000 tokens on Baidu DeepSeek V4 Pro 0813 and 1,048,576 tokens on Kimi K3.
Kimi K3 at 73.1 tok/s and Baidu DeepSeek V4 Pro 0813 at 39.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
Baidu DeepSeek V4 Pro 0813 accepts text input and supports tool calling, function calling, structured outputs and thinking; 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