DeepSeek V4-Pro vs Kimi K3
DeepSeek · China | Moonshot AI · China · Updated June 2026
Quick verdict
Pick DeepSeek V4-Pro for open-weight 1.6t moe (~49b active) — deepseek's largest, self-hostable or 1m-token context with up to 384k output tokens. Pick Kimi K3 for largest open-weight model at release — 2.8t sparse moe, self-hostable or 1m-token context with native vision (text, image and video). On a tight budget at scale, DeepSeek V4-Pro is the value pick.
DeepSeek V4-Pro (DeepSeek) and Kimi K3 (Moonshot AI) are two of the models people most often weigh against each other in 2026. DeepSeek V4-Pro is deepSeek's 1.6-trillion-parameter open-weight model at $0.435/$0.87 — strong open-weight coding and a 1M context at a fraction of flagship prices. Kimi K3 is moonshot's 2.8-trillion-parameter open-weight model — the largest open AI at release, with a 1M context and strong self-reported coding scores. They diverge most on price and context window — each quantified below from the models' real specs.
Key differences at a glance
- ▸Price: DeepSeek V4-Pro is about 4.5× cheaper on input ($0.66/$1.98 per 1M tokens vs $3/$15 per 1M tokens) — meaningful once you are processing millions of tokens a month.
- ▸Context window: 1M vs 1M — within a few percent of each other, so treat this as a tie and test on your own long inputs, since usable recall varies by model.
- ▸Recency: Kimi K3 is the newer model by about 3 months (released July 27, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | DeepSeek V4-Pro | Kimi K3 |
|---|---|---|
| Provider | DeepSeek (China) | Moonshot AI (China) |
| Released | April 24, 2026 | July 27, 2026 |
| Context window | 1M (~1,500 pages) | 1M (~1,573 pages) |
| Price (in/out) | $0.66/$1.98 per 1M tokens | $3/$15 per 1M tokens |
| Open weight? | Yes — self-hostable | Yes — self-hostable |
| Modalities | text, code | text, image, video, code |
| SWE-Bench Verified | Not published | Not published |
| MRCR v2 @ 1M | Not published | Not published |
Who wins what
Open-weight 1.6T MoE (~49B active) — DeepSeek's largest, self-hostable
DeepSeek V4-Pro
Kimi K3 is comparatively weak here — 2.8T params need serious hardware to self-host — weights are free, running is not
1M-token context with up to 384K output tokens
DeepSeek V4-Pro
DeepSeek's 1.6-trillion-parameter open-weight model at $0.435/$0.87 — strong open-weight coding and a 1M context at a fraction of flagship prices — and it runs cheaper at $0.66/$1.98 per 1M tokens.
Permanent low pricing at $0.435/$0.87 per million, set May 2026
DeepSeek V4-Pro
DeepSeek V4-Pro lists permanent low pricing at $0.435/$0.87 per million, set May 2026 among its strengths; Kimi K3 does not.
Largest open-weight model at release — 2.8T sparse MoE, self-hostable
Kimi K3
Moonshot's 2.8-trillion-parameter open-weight model — the largest open AI at release, with a 1M context and strong self-reported coding scores — and it is the newer of the two.
1M-token context with native vision (text, image and video)
Kimi K3
DeepSeek V4-Pro is comparatively weak here — text and code only — no image, audio or video
Vendor reports 81.2 FrontierSWE and 88.3 Terminal-Bench 2.1 on its own harness
Kimi K3
DeepSeek V4-Pro is comparatively weak here — independent SWE-Bench Verified placement is inconsistent across sources
Lowest cost at scale
DeepSeek V4-Pro
At $0.66/$1.98 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Which should you pick?
A cost-sensitive startup shipping high volume
→ DeepSeek V4-Pro
At $0.66/$1.98 per 1M tokens it undercuts Kimi K3, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ Kimi K3
Larger 1M window fits more in one prompt.
Anyone whose priority is open-weight 1.6t moe (~49b active) — deepseek's largest, self-hostable
→ DeepSeek V4-Pro
It is specifically built for that.
Anyone whose priority is largest open-weight model at release — 2.8t sparse moe, self-hostable
→ Kimi K3
That is its strongest area.
DeepSeek V4-Pro: where it fits
DeepSeek's 1.6-trillion-parameter open-weight model at $0.435/$0.87 — strong open-weight coding and a 1M context at a fraction of flagship prices. Released April 24, 2026 by DeepSeek, it is built for open-weight 1.6T MoE (~49B active) — DeepSeek's largest, self-hostable, 1M-token context with up to 384K output tokens, permanent low pricing at $0.435/$0.87 per million, set May 2026, and sources place it near the top of open-weight coding, around 80 on SWE-Bench Verified.
Its trade-offs are real: independent SWE-Bench Verified placement is inconsistent across sources, pro and Pro-Max variants are quoted with different scores, text and code only — no image, audio or video, and overlaps DeepSeek V4 and V3.2 already in this comparison. At $0.66 in / $1.98 out per million tokens, it sits in the budget price band.
Kimi K3: where it fits
Moonshot's 2.8-trillion-parameter open-weight model — the largest open AI at release, with a 1M context and strong self-reported coding scores. Released July 27, 2026 by Moonshot AI, it is built for largest open-weight model at release — 2.8T sparse MoE, self-hostable, 1M-token context with native vision (text, image and video), vendor reports 81.2 FrontierSWE and 88.3 Terminal-Bench 2.1 on its own harness, and fresh-input pricing of $3/M (cached $0.30/M), flat across the full 1M context.
Its trade-offs: coding scores use Moonshot FrontierSWE, not standard SWE-Bench Verified, 2.8T params need serious hardware to self-host — weights are free, running is not, no independent benchmark reproduction yet at release, and image input but no audio or video. At $3 in / $15 out per million tokens, it sits in the mid price band.
The bottom line for this matchup
DeepSeek V4-Pro and Kimi K3 overlap enough that the right pick depends on your specific job. DeepSeek V4-Pro costs less per token; Kimi K3 holds the larger context; and each leads in its own area — DeepSeek V4-Pro for open-weight 1.6t moe (~49b active) — deepseek's largest, self-hostable, Kimi K3 for largest open-weight model at release — 2.8t sparse moe, self-hostable. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both DeepSeek V4-Pro and Kimi K3 without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.
See pricingFrequently asked questions
Is DeepSeek V4-Pro or Kimi K3 better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, DeepSeek V4-Pro leans toward open-weight 1.6t moe (~49b active) — deepseek's largest, self-hostable while Kimi K3 leans toward largest open-weight model at release — 2.8t sparse moe, self-hostable, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, DeepSeek V4-Pro or Kimi K3?
DeepSeek V4-Pro is cheaper — $0.66/$1.98 per 1M tokens vs $3/$15 per 1M tokens, roughly 4.5× apart on input.
Which has the bigger context window?
Effectively neither — 1M vs 1M is a difference of a few percent. Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both DeepSeek V4-Pro and Kimi K3 together?
Yes — a multi-model platform like LumiChats gives you DeepSeek V4-Pro, Kimi K3 and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, DeepSeek V4-Pro or Kimi K3?
Kimi K3 — released July 27, 2026, about 3 months after DeepSeek V4-Pro.
Related comparisons
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.