Output tokens cost $1.20 per million on ERNIE 4.5 Turbo VL and $15.00 per million on Kimi K3. Input tokens cost $0.40 per million on ERNIE 4.5 Turbo VL and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.40 per million on ERNIE 4.5 Turbo VL and $0.30 per million on Kimi K3. Context lengths are 139,000 tokens on ERNIE 4.5 Turbo VL and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 0.6s on ERNIE 4.5 Turbo VL and 0.9s on Kimi K3. Measured output throughput is 24.4 tok/s on ERNIE 4.5 Turbo VL and 73.1 tok/s on Kimi K3.
ERNIE 4.5 Turbo VL
Kimi K3The new version of the Wenxin Yiyan large model significantly improves capabilities in image understanding, creation, translation, and coding. It supports a context length of up to 32K tokens for the first time, with a notable reduction in the latency of the first token.
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.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
ERNIE 4.5 Turbo VL: $1.20/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
ERNIE 4.5 Turbo VL: 0.6s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
ERNIE 4.5 Turbo VL accepts 139,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 16,000 tokens on ERNIE 4.5 Turbo VL and 1,048,576 tokens on Kimi K3.
Kimi K3 at 73.1 tok/s and ERNIE 4.5 Turbo VL at 24.4 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
ERNIE 4.5 Turbo VL accepts text and image input and supports 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