kimi-k3
Moonshot AI · text, image, video → text
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.
Input$3.00 /M
Output$15.00 /M
← Modelskimi-k3
qwen3.8-2.4t-a95b
kimi-k3 vs qwen3.8-2.4t-a95b
Output tokens cost $15.00 per million on kimi-k3 and $6.00 per million on qwen3.8-2.4t-a95b. Input tokens cost $3.00 per million on kimi-k3 and $2.00 per million on qwen3.8-2.4t-a95b. Cached input tokens are billed at $0.30 per million on kimi-k3 and $0.50 per million on qwen3.8-2.4t-a95b. Context lengths are 1,048,576 tokens on kimi-k3 and 262,000 tokens on qwen3.8-2.4t-a95b. Time to first token (TTFT) measured on AIHubMix is 2.4s on kimi-k3 and 0.7s on qwen3.8-2.4t-a95b. Measured output throughput is 39.1 tok/s on kimi-k3 and 32.2 tok/s on qwen3.8-2.4t-a95b.
kimi-k3qwen3.8-2.4t-a95b+ Add model · 2/4
qwen3.8-2.4t-a95b
Qwen · text, image → text
Qwen3.8-2.4T-A95B is Alibaba’s most powerful Qwen model to date. It is a 2.4‑trillion‑parameter sparse Mixture-of-Experts (MoE) model with approximately 95 billion active parameters. It is built for autonomous, long‑duration tasks: multi‑day code runs, reproducing research papers, and self‑improvement.
Input$2.00 /M
Output$6.00 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
kimi-k3
qwen3.8-2.4t-a95b
Input /M
$3.00
$2.00
Output /M
$15.00
$6.00
Cache read /M
$0.30
$0.50
Context length
1,048,576
262,000
Max output
1,048,576
262,000
Time to First Token
2.4 s
0.7 s
Throughput
39.1 tok/s
32.2 tok/s
Modalities
textimagevideo
textimage
Supported Parameters
thinkingfunction callingstructured outputs
toolsfunction callingstructured outputsweblong contextthinking
API Formats
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
kimi-k3qwen3.8-2.4t-a95b
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3qwen3.8-2.4t-a95b
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
qwen3.8-2.4t-a95b
$210 /mo
kimi-k3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: kimi-k3, qwen3.8-2.4t-a95b?
qwen3.8-2.4t-a95b: $6.00/M output tokens; kimi-k3: $15.00/M. Use the cost calculator above to estimate your own workload.
Which responds faster?
qwen3.8-2.4t-a95b: 0.7s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
How large is each context window?
kimi-k3 accepts 1,048,576 and qwen3.8-2.4t-a95b accepts 262,000 input tokens. Maximum output per request is 1,048,576 tokens on kimi-k3 and 262,000 tokens on qwen3.8-2.4t-a95b.
Which one generates tokens faster?
kimi-k3 at 39.1 tok/s and qwen3.8-2.4t-a95b at 32.2 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
kimi-k3 accepts text, image and video input and supports thinking, function calling and structured outputs; qwen3.8-2.4t-a95b accepts text and image input and supports tool calling, function calling, structured outputs, web search, long context and thinking.
Can I call kimi-k3 and qwen3.8-2.4t-a95b with the same API key?
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.
Popular comparisons
Related model match-ups readers also look at.
AIHubMix