Moonshot AI's most capable Kimi model: an open-weights 2.8T-parameter mixture-of-experts with native vision and a 1M-token context. it sits above Kimi 2.6 and Kimi 2.7 Code, which have a 256K context and cost less per token.
pick it if
you want the model Moonshot calls its most capable
your prompts outgrow the 256K context of Kimi 2.6 and 2.7 Code
you resend long prompts, so cache hits bill at a tenth of input
skip it if
Kimi 2.6 or 2.7 Code covers your workload at a lower rate
DeepSeek's larger V4 model: 1.6T total parameters (49B active), text-only, with a 1M-token context and selectable thinking effort. previewed in April 2026 and generally available from 2026-08-13, it sits above V4.1 Flash, which costs less and also reads images.
pick it if
want DeepSeek's largest V4 model with MIT-licensed open weights
resend long prompts: cache hits bill $0.044 per 1M versus $1.32
need low / high / max thinking effort for agent workflows
skip it if
you need image input; V4.1 Flash accepts images
V4.1 Flash at $0.30 / $1.20 already covers your workload
faq
which is better, Kimi K3 or DeepSeek V4 Pro?
on Terminal-Bench 2.1, as each maker reports it, Kimi K3 scores 88.3 and DeepSeek V4 Pro 87.9. these are each maker's own numbers, not a controlled head-to-head; the spec table lists every benchmark both publish.
which is cheaper, Kimi K3 or DeepSeek V4 Pro?
DeepSeek V4 Pro lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) Kimi K3 costs $6.90 and DeepSeek V4 Pro $2.88.
which one accepts images?
Kimi K3 supports vision; DeepSeek V4 Pro does not.
can i switch between Kimi K3 and DeepSeek V4 Pro mid-task?
yes. in an octomind session, /model octohub:kimi-k3 and /model octohub:deepseek-v4-pro switch models without losing the conversation, so you can draft on one and review on the other.
try either model
switch between models inside the same octomind session.