Mistral Large 4 vs DeepSeek V4 Pro
Official Mistral and DeepSeek API prices and LMArena scores, checked 2026-10-21. Add up to 2 more models to compare 4.
DeepSeek V4 Pro is cheaper and wins more LMArena tasks.
DeepSeek V4 Pro is slightly cheaper on input and 1.1x cheaper on output. Mistral Large 4 scores 2 points higher for coding; DeepSeek V4 Pro scores 1 point higher for creative writing. Across 5 shared LMArena tasks, DeepSeek V4 Pro leads 2 to 1 (2 tied). A medium month (20M input + 5M output tokens) costs $48.10 on Mistral Large 4 and $46.20 on DeepSeek V4 Pro.
- Pick Mistral Large 4 if nothing here clearly favors it (no lower bill, bigger context, cheaper cache or LMArena lead of 3+ points over DeepSeek V4 Pro).
- Pick DeepSeek V4 Pro if you want the lower bill ($46.20 vs $48.10 for a medium month) or you reuse long prompts (cached input $0.044 vs $0.14).
Medium: 20M input + 5M output tokens a month at list price (short-context rate, no caching or batch discounts).
Marked side is better: lower for prices, higher for context and scores. Bars are scaled to the larger of the two.
| Spec | Mistral Large 4 | DeepSeek V4 Pro |
|---|---|---|
| Price per 1M tokens | ||
| Input | $1.36 | $1.32 |
| Cached input | $0.14 | $0.044 |
| Output | $4.18 | $3.96 |
| Blend 3:1 | $2.06 | $1.98 |
| Sample month, medium | $48.10 | $46.20 |
| Context | ||
| Context window | 1M tokens | 1M tokens |
| Quality (LMArena, out of 100) | ||
| Coding | 2/100 #17 of 23 | 0/100 #19 of 23 |
| Chat | 0/100 #24 of 25 | 0/100 #18 of 25 |
| Creative writing | 0/100 #25 of 25 | 1/100 #15 of 25 |
| Roleplay and characters | 0/100 #23 of 25 | 1/100 #14 of 25 |
| Reasoning and math | 0/100 #17 of 25 | 0/100 #21 of 25 |
| Vision | 0/100 #18 of 22 | Not ranked |
| Long documents | Not ranked | Not ranked |
| Cheap bulk and agents | 23/100 #21 of 23 | Not ranked |
| Details | ||
| Provider | Mistral | DeepSeek |
| API model id | mistral-large-4 | deepseek-v4-pro |
| Notes | Standard list price (the earlier sale price of $0.68 in / $2.09 out is no longer shown). | Peak rate. Off-peak is half price. |
| Sources | ||
| Last checked | 2026-10-21 | 2026-10-21 |
| Official pricing | Mistral pricing | DeepSeek pricing |
Plans from data checked hourly against each vendor's official pricing page. Vendors state limits in different units, so we quote them as published. Team and enterprise plans are per seat.
API prices in USD per 1M tokens from each provider's official pricing page. Blend 3:1 = (3 x input + output) / 4. Sample month = stated input and output tokens at the list price, no caching. Quality: relative score out of 100 on each LMArena leaderboard (100 = top model we price on that board, n/a = not ranked there), data licensed CC BY 4.0. See how we pick.
Where each one ranks on LMArena
Relative score out of 100 on each leaderboard (100 = the top model we price there), with the rank among the models from our API price table that appear on that board.
- Coding (Code Arena): Mistral Large 4 #17 of 23 (2/100), DeepSeek V4 Pro #19 of 23 (0/100)
- Chat (Text Arena): Mistral Large 4 #24 of 25 (0/100), DeepSeek V4 Pro #18 of 25 (0/100)
- Creative writing (Text Arena creative writing): Mistral Large 4 #25 of 25 (0/100), DeepSeek V4 Pro #15 of 25 (1/100)
- Roleplay and characters (Text Arena multi-turn): Mistral Large 4 #23 of 25 (0/100), DeepSeek V4 Pro #14 of 25 (1/100)
- Reasoning and math (Text Arena math): Mistral Large 4 #17 of 25 (0/100), DeepSeek V4 Pro #21 of 25 (0/100)
- Vision (Vision Arena): Mistral Large 4 #18 of 22 (0/100), DeepSeek V4 Pro not ranked
- Long documents (Document Arena): Mistral Large 4 not ranked, DeepSeek V4 Pro not ranked
- Cheap bulk and agents (Agent Arena): Mistral Large 4 #21 of 23 (23/100), DeepSeek V4 Pro not ranked
Pricing details from the official pages
Mistral Large 4 lists $1.36 input, $4.18 output, $0.14 cached input per 1M tokens on Mistral pricing. DeepSeek V4 Pro lists $1.32 input, $3.96 output, $0.044 cached input per 1M tokens on DeepSeek pricing. Prices checked 2026-10-21.
- Mistral Large 4: Standard list price (the earlier sale price of $0.68 in / $2.09 out is no longer shown).
- DeepSeek V4 Pro: Peak rate. Off-peak is half price.
Sample monthly bill at list price, no caching: Light (2M input + 0.5M output tokens): $4.81 vs $4.62. Medium (20M input + 5M output tokens): $48.10 vs $46.20. Heavy (200M input + 50M output tokens): $481 vs $462.
FAQ
Is Mistral Large 4 cheaper than DeepSeek V4 Pro?
Mistral Large 4 costs $1.36 input and $4.18 output per 1M tokens; DeepSeek V4 Pro costs $1.32 and $3.96. For a medium month (20M input + 5M output tokens) DeepSeek V4 Pro is cheaper: $46.20 vs $48.10.
Which is better for coding, Mistral Large 4 or DeepSeek V4 Pro?
On LMArena's Code Arena Mistral Large 4 scores 2/100 (#17 of 23) and DeepSeek V4 Pro 0/100 (#19 of 23), so Mistral Large 4 is ahead by 2 points.
Which has the bigger context window?
Mistral Large 4: 1M tokens. DeepSeek V4 Pro: 1M tokens. Both list the same window.
How much do Mistral Large 4 and DeepSeek V4 Pro cost per month?
Light (2M input + 0.5M output tokens): $4.81 vs $4.62. Medium (20M input + 5M output tokens): $48.10 vs $46.20. Heavy (200M input + 50M output tokens): $481 vs $462. Pick your own token counts in the plan vs API calculator.
Where do these numbers come from?
Prices come from each provider's official pricing page, checked daily. Quality is the relative score on the LMArena leaderboard dataset, licensed CC BY 4.0. Where a model is not ranked we show n/a.