Model comparison
DeepSeek V4 Pro vs MiniMax M3
DeepSeek against MiniMax, compared on context, price, and verified benchmark results.
Catalog record checked September 5, 2026Individual provider fields may changeEvidence confidence: High — see receipts below
DeepSeek
DeepSeek V4 Pro
Frontier · Open weights
MiniMax
MiniMax M3
Frontier · Open weights
| Specification | DeepSeek V4 Pro | MiniMax M3 |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Tier | Frontier | Frontier |
| Context window | 1M | 1M |
| Max output | 384K | Not verifiedUnverified |
| Input / 1M tokens | $1.32 | Winner: $0.30 |
| Output / 1M tokens | $3.96 | Winner: $1.20 |
| Weights | Open | Open |
| Parameters | 1.6T total / 49B active (MoE) | 428B total / 23B active (MoE) |
| Reasoning levels | low, high, max | low, high, max |
| Modalities | text | text, image, video |
| License | MIT | Not disclosedUnverified |
| API model id | deepseek-v4-pro | minimax-m3 |
| Released | April 24, 2026 | June 1, 2026 |
| Artificial Analysis Intelligence Index (2026-08-14) | Winner: 53 | 51 |
| SWE-bench Verified (2026-04-24) | 80.6 | Not verifiedUnverified |
| GPQA Diamond (2026-04-24) | 90.1 | Not verifiedUnverified |
| Humanity's Last Exam (2026-04-24) | 48.2 | Not verifiedUnverified |
| MMLU-Pro (2026-04-24) | 87.5 | Not verifiedUnverified |
| Terminal-Bench 2.1 (2026-06-01) | Not verifiedUnverified | 66 |
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
- 2026-08-14: 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).
- 2026-06-01: MiniMax blog (vendor, Terminus 2 scaffolding, 2h timeout)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. · MiniMax M3: $0.30/$1.20 per MTok; open (community license). 428B/23B active MoE, native multimodal. Rate is the ≤512K-prompt tier; higher above.
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.
MiniMax M3
MiniMax M3 is an open-weight (community license) 428B MoE with native multimodal and 1M context.
Best for
- Open-weight deployments
- Multimodal
- Long-context
Watch out
Community license, not fully open; verify terms.
When the cheaper one wins
MiniMax M3 is cheaper on output at $1.20 per million tokens against $3.96 for DeepSeek V4 Pro — about 3.3×. 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.
- 4/5 core specs verified on both sides — Not published for at least one side: max output.
- 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
- Verified within the last 90 days — Newest catalog check was 6 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)
- MiniMax M3: MiniMax — M3 (accessed 2026-08-29)
- MiniMax M3: MiniMax M3 release (accessed 2026-08-29)
Related comparisons
- Claude Fable 5.1 vs DeepSeek V4 Pro
- Claude Fable 5.1 vs MiniMax M3
- Claude Fable 5 vs DeepSeek V4 Pro
- Claude Fable 5 vs MiniMax M3
- Claude Mythos 5.1 vs DeepSeek V4 Pro
- Claude Mythos 5.1 vs MiniMax M3
Diving deeper on one model? DeepSeek V4 Pro · MiniMax M3
Common questions
DeepSeek V4 Pro vs MiniMax M3
Answered from the verified figures on this page rather than general guidance.
Is DeepSeek V4 Pro or MiniMax M3 cheaper for input?
MiniMax M3 is cheaper at $0.30 per million input tokens, against $1.32 for DeepSeek V4 Pro — roughly 4.4× 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. MiniMax M3 has tiered pricing: $0.30/$1.20 per MTok; open (community license). 428B/23B active MoE, native multimodal. Rate is the ≤512K-prompt tier; higher above.
Is DeepSeek V4 Pro or MiniMax M3 cheaper for output?
MiniMax M3 is cheaper at $1.20 per million output tokens, against $3.96 for DeepSeek V4 Pro — roughly 3.3× 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. MiniMax M3 has tiered pricing: $0.30/$1.20 per MTok; open (community license). 428B/23B active MoE, native multimodal. Rate is the ≤512K-prompt tier; higher above.
Which has the larger context window, DeepSeek V4 Pro or MiniMax M3?
Both accept about 1M tokens of context, so document length will not decide between them.
Do DeepSeek V4 Pro and MiniMax M3 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 MiniMax M3?
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; MiniMax M3 suits open-weight deployments.
Next step
Choosing between them
The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.
- Input price: MiniMax M3 costs $0.30 per 1M tokens versus $1.32 for DeepSeek V4 Pro — a 4.4x difference at the headline tier.
- Measured capability: DeepSeek V4 Pro leads Artificial Analysis Intelligence Index 53 to 51 (measured 2026-08-14).
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.