Compare Kimi K2 0905 from Moonshot AI and DeepSeek V4 Flash from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Kimi K2 0905
DeepSeek V4 FlashKimi-K2-0905 is a large-scale Mixture of Experts (MoE) language model developed by Moonshot AI, with a total of 1 trillion parameters and 32 billion active parameters per forward pass. It supports long-context inference of up to 256k tokens, an expansion from the previous 128k.
(This model currently points to the older 0423 version; if you need to request the latest version, you can choose the model deepseek-v4-flash-0731)DeepSeek-V4 features an ultra-long context of one million characters and achieves leading performance domestically and in the open-source domain in agent capabilities, world knowledge, and reasoning.
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.
DeepSeek V4 Flash: $0.284/M output tokens; Kimi K2 0905: $2.192/M. Use the cost calculator above to estimate your own workload.
DeepSeek V4 Flash: 1483; Kimi K2 0905: 1467 (LMArena coding leaderboard).
Kimi K2 0905: 0.8s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
Kimi K2 0905 accepts 262,144 and DeepSeek V4 Flash accepts 1,000,000 input tokens. Maximum output per request is 262,144 tokens on Kimi K2 0905 and 384,000 tokens on DeepSeek V4 Flash.
DeepSeek V4 Flash at 66.5 tok/s and Kimi K2 0905 at 49.0 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
Kimi K2 0905 accepts text input and supports tool calling, function calling and structured outputs; DeepSeek V4 Flash accepts text input and supports tool calling, function calling, structured outputs and thinking.
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.