Output tokens cost $10.00 per million on claude-sonnet-5 and $15.00 per million on kimi-k3. Input tokens cost $2.00 per million on claude-sonnet-5 and $3.00 per million on kimi-k3. Cached input tokens are billed at $2.00 per million on claude-sonnet-5 and $0.30 per million on kimi-k3. Context windows are 1,000,000 tokens on claude-sonnet-5 and 1,048,576 tokens on kimi-k3. First-token latency measured on AIHubMix is 3.3s on claude-sonnet-5 and 6.8s on kimi-k3. Measured output throughput is 91.0 tokens/s on claude-sonnet-5 and 32.2 tokens/s on kimi-k3. On the LMArena coding leaderboard claude-sonnet-5 scores 1526 and kimi-k3 scores 1531.
claude-sonnet-5
kimi-k3Claude Sonnet 5 is the next generation of Anthropic's Sonnet model family. It is a drop-in upgrade for Claude Sonnet 4.6 with three behavior changes: adaptive thinking is on by default, manual extended thinking now returns a 400 error (it was deprecated on Claude Sonnet 4.6), and setting sampling parameters (temperature, top_p, top_k) to non-default values returns a 400 error
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. Latency 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.
claude-sonnet-5: $10.00/M output tokens; kimi-k3: $15.00/M. Use the cost calculator above to estimate your own workload.
kimi-k3: 1531; claude-sonnet-5: 1526 (LMArena coding leaderboard).
claude-sonnet-5: 3.3s first-token latency measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
claude-sonnet-5 accepts 1,000,000 and kimi-k3 accepts 1,048,576 input tokens. Maximum output per request is 128,000 tokens on claude-sonnet-5 and 1,048,576 tokens on kimi-k3.
claude-sonnet-5 at 91.0 tokens/s and kimi-k3 at 32.2 tokens/s, measured as output throughput on AIHubMix — a separate metric from first-token latency.
claude-sonnet-5 accepts text and image 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