Output tokens cost $8.00 per million on GPT 4.1 and $15.00 per million on Kimi K3. Input tokens cost $2.00 per million on GPT 4.1 and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.50 per million on GPT 4.1 and $0.30 per million on Kimi K3. Context lengths are 1,047,576 tokens on GPT 4.1 and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 1.1s on GPT 4.1 and 0.9s on Kimi K3. Measured output throughput is 81.0 tok/s on GPT 4.1 and 73.1 tok/s on Kimi K3. On the LMArena coding leaderboard GPT 4.1 scores 1457 and Kimi K3 scores 1531.
GPT 4.1
Kimi K3The latest flagship multimodal model supports million-token context, with encoding capability (SWE-bench 54.6%) and instruction-following (Scale AI 38.3%) performance significantly surpassing GPT-4o, while reducing costs by 26%, making it suitable for complex tasks. Its automatic caching mechanism offers a 75% cost reduction on cache hits.
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.
GPT 4.1: $8.00/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
Kimi K3: 1531; GPT 4.1: 1457 (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.
GPT 4.1 accepts 1,047,576 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 32,768 tokens on GPT 4.1 and 1,048,576 tokens on Kimi K3.
GPT 4.1 at 81.0 tok/s and Kimi K3 at 73.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
GPT 4.1 accepts text and image input and supports tool calling, function calling, structured outputs and long context; 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