Output tokens cost $0.05 per million on Jina Deepsearch V1 and $15.00 per million on Kimi K3. Input tokens cost $0.05 per million on Jina Deepsearch V1 and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.05 per million on Jina Deepsearch V1 and $0.30 per million on Kimi K3. Context lengths are 1,000,000 tokens on Jina Deepsearch V1 and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 0.8s on Jina Deepsearch V1 and 0.9s on Kimi K3. Measured output throughput is 65.5 tok/s on Jina Deepsearch V1 and 73.1 tok/s on Kimi K3.
Jina Deepsearch V1
Kimi K3DeepSearch combines search, reading, and reasoning capabilities to pursue the best possible answer. It's fully compatible with OpenAI's Chat API format—just replace api.openai.com with aihubmix.com to get started. The stream will return the thinking process.
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.
Jina Deepsearch V1: $0.05/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
Jina Deepsearch V1: 0.8s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
Jina Deepsearch V1 accepts 1,000,000 and Kimi K3 accepts 1,048,576 input tokens.
Kimi K3 at 73.1 tok/s and Jina Deepsearch V1 at 65.5 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
Jina Deepsearch V1 accepts text and image input and supports thinking, web search and deep search; 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