Mistral's mixture-of-experts model with about 1T total parameters (52B active): a hybrid instruct-and-reasoning model with a vision encoder and a 1M-token context. it entered public preview on 2026-10-06; Mistral says the open weights ship later.
pick it if
want a Mistral model that takes text and image input
need a 1M-token context with function calling and structured outputs
resend long prompts: cache hits bill $0.136 per 1M versus $1.36
skip it if
you need downloadable weights today; Mistral says they ship later
you need a stable release rather than a public preview
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 cheaper, Mistral Large 4 or DeepSeek V4 Pro?
DeepSeek V4 Pro lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) Mistral Large 4 costs $2.97 and DeepSeek V4 Pro $2.88.
which one accepts images?
Mistral Large 4 supports vision; DeepSeek V4 Pro does not.
can i switch between Mistral Large 4 and DeepSeek V4 Pro mid-task?
yes. in an octomind session, /model octohub:mistral-large-4 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.