Output tokens cost $0.45 per million on DeepSeek V3.2 and $15.00 per million on Kimi K3. Input tokens cost $0.30 per million on DeepSeek V3.2 and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.03 per million on DeepSeek V3.2 and $0.30 per million on Kimi K3. Context lengths are 128,000 tokens on DeepSeek V3.2 and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 2.0s on DeepSeek V3.2 and 0.9s on Kimi K3. Measured output throughput is 30.8 tok/s on DeepSeek V3.2 and 73.1 tok/s on Kimi K3. On the LMArena coding leaderboard DeepSeek V3.2 scores 1470 and Kimi K3 scores 1531.
DeepSeek V3.2
Kimi K3DeepSeek-V3.2 is an efficient large language model equipped with DeepSeek Sparse Attention and reinforced reasoning performance, but its core strength lies in powerful agentic capabilities—enabled by large-scale task-synthesis that tightly integrates reasoning with real-world tool use, delivering robust, compliant, and generalizable agent behaviour. Users can toggle deeper reasoning through the reasoning_enabled switch.
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 V3.2: $0.45/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
Kimi K3: 1531; DeepSeek V3.2: 1470 (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 V3.2 accepts 128,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 64,000 tokens on DeepSeek V3.2 and 1,048,576 tokens on Kimi K3.
Kimi K3 at 73.1 tok/s and DeepSeek V3.2 at 30.8 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
DeepSeek V3.2 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