Output tokens cost $0.56 per million on DeepSeek V4 Flash 0731 Fast and $15.00 per million on Kimi K3. Input tokens cost $0.28 per million on DeepSeek V4 Flash 0731 Fast and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.07 per million on DeepSeek V4 Flash 0731 Fast and $0.30 per million on Kimi K3. Context lengths are 1,000,000 tokens on DeepSeek V4 Flash 0731 Fast and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 3.7s on DeepSeek V4 Flash 0731 Fast and 0.9s on Kimi K3. Measured output throughput is 129.8 tok/s on DeepSeek V4 Flash 0731 Fast and 73.1 tok/s on Kimi K3. On the LMArena coding leaderboard DeepSeek V4 Flash 0731 Fast scores 1483 and Kimi K3 scores 1531.
DeepSeek V4 Flash 0731 Fast
Kimi K3DeepSeek V4 Flash 0731 Fast is a high-speed deployment of DeepSeek’s agentic model provided by Wafer, designed for coding, tool use, and high-volume agent workloads. It preserves the capabilities of V4 Flash 0731 while delivering much faster inference. Compared with V4 Pro, it prioritizes latency and execution efficiency.
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.
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
DeepSeek V4 Flash 0731 Fast: $0.56/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
Kimi K3: 1531; DeepSeek V4 Flash 0731 Fast: 1483 (LMArena coding leaderboard).
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.
DeepSeek V4 Flash 0731 Fast accepts 1,000,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 384,000 tokens on DeepSeek V4 Flash 0731 Fast and 1,048,576 tokens on Kimi K3.
DeepSeek V4 Flash 0731 Fast at 129.8 tok/s and Kimi K3 at 73.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
DeepSeek V4 Flash 0731 Fast 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