Output tokens cost $1.68 per million on DeepSeek V3.1 Thinking and $15.00 per million on Kimi K3. Input tokens cost $0.56 per million on DeepSeek V3.1 Thinking and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.56 per million on DeepSeek V3.1 Thinking and $0.30 per million on Kimi K3. Context lengths are 128,000 tokens on DeepSeek V3.1 Thinking and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 1.3s on DeepSeek V3.1 Thinking and 0.9s on Kimi K3. Measured output throughput is 31.5 tok/s on DeepSeek V3.1 Thinking and 73.1 tok/s on Kimi K3. On the LMArena coding leaderboard DeepSeek V3.1 Thinking scores 1458 and Kimi K3 scores 1531.
DeepSeek V3.1 Thinking
Kimi K3Thinking mode of DeepSeek-V3.1; DeepSeek V3.1 is a text generation model provided by DeepSeek, featuring a hybrid reasoning architecture that achieves an effective integration of thinking and non-thinking modes.
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 V3.1 Thinking: $1.68/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
Kimi K3: 1531; DeepSeek V3.1 Thinking: 1458 (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 V3.1 Thinking accepts 128,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 32,000 tokens on DeepSeek V3.1 Thinking and 1,048,576 tokens on Kimi K3.
Kimi K3 at 73.1 tok/s and DeepSeek V3.1 Thinking at 31.5 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
DeepSeek V3.1 Thinking accepts text input and supports thinking, tool calling, function calling and structured outputs; 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