Output tokens cost $6.00 per million on grok-4.20-beta-0309-non-reasoning and $15.00 per million on Kimi K3. Input tokens cost $2.00 per million on grok-4.20-beta-0309-non-reasoning and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.20 per million on grok-4.20-beta-0309-non-reasoning and $0.30 per million on Kimi K3. Context lengths are 2,000,000 tokens on grok-4.20-beta-0309-non-reasoning and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 0.9s on grok-4.20-beta-0309-non-reasoning and 0.9s on Kimi K3. Measured output throughput is 89.0 tok/s on grok-4.20-beta-0309-non-reasoning and 73.1 tok/s on Kimi K3.
grok-4.20-beta-0309-non-reasoning
Kimi K3Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent tool-invocation capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, enabling it to consistently deliver precise and factual responses.
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.
grok-4.20-beta-0309-non-reasoning: $6.00/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
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.
grok-4.20-beta-0309-non-reasoning accepts 2,000,000 and Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 2,000,000 tokens on grok-4.20-beta-0309-non-reasoning and 1,048,576 tokens on Kimi K3.
grok-4.20-beta-0309-non-reasoning at 89.0 tok/s and Kimi K3 at 73.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
grok-4.20-beta-0309-non-reasoning accepts text and image input and supports thinking, 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