Model comparison
DeepSeek V4 Pro vs Kimi K3
DeepSeek against Moonshot AI, compared on context, price, and verified benchmark results.
Catalog record checked September 3, 2026Individual provider fields may changeEvidence confidence: High — see receipts below
DeepSeek
DeepSeek V4 Pro
Frontier · Open weights
Moonshot AI
Kimi K3
Frontier · Open weights
| Specification | DeepSeek V4 Pro | Kimi K3 |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Tier | Frontier | Frontier |
| Context window | 1M | Winner: 1.05M |
| Max output | Winner: 384K | 128K |
| Input / 1M tokens | Winner: $1.32 | $3 |
| Output / 1M tokens | Winner: $3.96 | $15 |
| Weights | Open | Open |
| Parameters | 1.6T total / 49B active (MoE) | 2.8T (open-weight MoE) |
| Reasoning levels | low, high, max | low, high, max |
| Modalities | text | text, image, video |
| License | MIT | Not disclosedUnverified |
| API model id | deepseek-v4-pro | kimi-k3 |
| Released | April 24, 2026 | July 16, 2026 |
| Artificial Analysis Intelligence Index (2026-08-14) | 53 | Not verifiedUnverified |
| Artificial Analysis Intelligence Index [max] (2026-08-14) | Not verifiedUnverified | 60 |
| SWE-bench Verified (2026-04-24) | 80.6 | Winner: 93.4 |
| GPQA Diamond (2026-04-24) | 90.1 | Winner: 93.5 |
| Humanity's Last Exam (2026-04-24) | 48.2 | Winner: 56 |
| MMLU-Pro (2026-04-24) | 87.5 | Not verifiedUnverified |
| Terminal-Bench 2.1 (2026-07-27) | Not verifiedUnverified | 88.3 |
Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.
Benchmark receipts
- 2026-09-01: vals.ai SWE-bench Verified leaderboard (independent, mini-swe-agent bash-only); not published by Moonshot; a 76.8 aggregator claim is low-reliability — both notedReal GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
- 2026-08-14: Artificial AnalysisComposite index blending reasoning, knowledge, and coding evals into one 0–100 score. Comparability: directly comparable — AA occasionally rebaselines the index scale between snapshots — a score captured on one date is only comparable to same-snapshot scores (check measuredAt).
- 2026-07-27: Kimi K3 HF model card (vendor, with tools; 43.5 no tools)Agentic terminal work: multi-step tasks executed in a sandboxed shell environment. Comparability: comparable with caveat — Scores across Terminal-Bench major versions (v1 vs v2) are NOT comparable; harness configuration (container, time limits) also shifts results.
- 2026-04-24: DeepSeek V4 Pro HF model card (vendor, Think Max, exact match)Real GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
Pricing tiers: DeepSeek V4 Pro: Official peak rates $1.32/$3.96 per MTok; off-peak $0.66/$1.98 (cache-miss). Open weights (MIT). 1.6T/49B active MoE. · Kimi K3: $3/$15 per MTok; cached input $0.30/MTok. Open-weight under the custom Kimi K3 License (not a standard open-source licence). 2.8T MoE with native vision.
DeepSeek V4 Pro
DeepSeek V4 Pro is the open-weight (MIT) flagship with a 1M-token context at a fraction of frontier API cost.
Best for
- Cost-sensitive hosted agents
- Open-weight deployments
- High-volume coding
Watch out
Self-hosting needs datacentre VRAM; hosted rates vary by provider. Price single-source — verify.
Kimi K3
Kimi K3 is Moonshot AI's open-weight frontier model — 2.8T MoE, 1M context, tied near the top of open-weight leaderboards.
Best for
- Open-weight frontier work
- Long-context
- Multimodal
Watch out
Self-hosting needs large clusters; hosted rates vary.
When the cheaper one wins
DeepSeek V4 Pro is cheaper on output at $3.96 per million tokens against $15 for Kimi K3 — about 3.8×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.
Run the model pickerEvidence confidence: High
How strong and complete the evidence behind this comparison is — not a prediction of which model is better.
- Pricing verified on both sides — Input and output rates are verified for both models.
- 5/5 core specs verified on both sides — All core specifications verified for both models.
- 4 shared named benchmarks with differing scores — Measured on: Artificial Analysis Intelligence Index, SWE-bench Verified, GPQA Diamond, Humanity's Last Exam.
- Verified within the last 90 days — Newest catalog check was 8 days ago.
- Both models carry source citations — Each side has at least two catalog sources on record.
Source receipts
Each catalog figure was checked against the provider or an independent second source on the date shown.
- DeepSeek V4 Pro: DeepSeek — V4 news (accessed 2026-08-29)
- DeepSeek V4 Pro: DeepSeek API pricing (accessed 2026-08-29)
- Kimi K3: HuggingFace — Kimi K3 (accessed 2026-08-29)
- Kimi K3: Moonshot — Kimi K3 guide (accessed 2026-08-29)
Related comparisons
- Claude Fable 5.1 vs DeepSeek V4 Pro
- Claude Fable 5.1 vs Kimi K3
- Claude Fable 5 vs DeepSeek V4 Pro
- Claude Fable 5 vs Kimi K3
- Claude Mythos 5.1 vs DeepSeek V4 Pro
- Claude Mythos 5.1 vs Kimi K3
Diving deeper on one model? DeepSeek V4 Pro · Kimi K3
Common questions
DeepSeek V4 Pro vs Kimi K3
Answered from the verified figures on this page rather than general guidance.
Is DeepSeek V4 Pro or Kimi K3 cheaper for input?
DeepSeek V4 Pro is cheaper at $1.32 per million input tokens, against $3 for Kimi K3 — roughly 2.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; DeepSeek V4 Pro has tiered pricing: Official peak rates $1.32/$3.96 per MTok; off-peak $0.66/$1.98 (cache-miss). Open weights (MIT). 1.6T/49B active MoE. Kimi K3 has tiered pricing: $3/$15 per MTok; cached input $0.30/MTok. Open-weight under the custom Kimi K3 License (not a standard open-source licence). 2.8T MoE with native vision.
Is DeepSeek V4 Pro or Kimi K3 cheaper for output?
DeepSeek V4 Pro is cheaper at $3.96 per million output tokens, against $15 for Kimi K3 — roughly 3.8× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; DeepSeek V4 Pro has tiered pricing: Official peak rates $1.32/$3.96 per MTok; off-peak $0.66/$1.98 (cache-miss). Open weights (MIT). 1.6T/49B active MoE. Kimi K3 has tiered pricing: $3/$15 per MTok; cached input $0.30/MTok. Open-weight under the custom Kimi K3 License (not a standard open-source licence). 2.8T MoE with native vision.
Which has the larger context window, DeepSeek V4 Pro or Kimi K3?
Kimi K3 accepts 1.05M tokens against 1M for DeepSeek V4 Pro. This only matters if you routinely send very long documents or large codebases.
Do DeepSeek V4 Pro and Kimi K3 support the same reasoning levels?
Yes — both accept the same effort settings: "low", "high", "max". Higher effort costs more and takes longer, so start low and raise it only where output quality actually improves.
Should I use DeepSeek V4 Pro or Kimi K3?
Both sit in the frontier tier, so the choice usually comes down to price and context rather than capability. DeepSeek V4 Pro suits cost-sensitive hosted agents; Kimi K3 suits open-weight frontier work.
Next step
Choosing between them
The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.
- Input price: DeepSeek V4 Pro costs $1.32 per 1M tokens versus $3 for Kimi K3 — a 2.3x difference at the headline tier.
- Context: Kimi K3 takes 1.05M against 1M for DeepSeek V4 Pro — only decisive if your prompts approach the smaller window.
- Measured capability: Kimi K3 leads Artificial Analysis Intelligence Index 60 to 53 (measured 2026-08-14).
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.