DeepSeek V4.1 Flash vs Gemini 3.8 Flash
Official DeepSeek and Google API prices and LMArena scores, checked 2026-10-19. Add up to 2 more models to compare 4.
DeepSeek V4.1 Flash costs less; Gemini 3.8 Flash wins more LMArena tasks.
DeepSeek V4.1 Flash is 2.5x cheaper on input and 3.1x cheaper on output. Gemini 3.8 Flash scores 64 points higher for vision; DeepSeek V4.1 Flash scores 30 points higher for coding. Across 7 shared LMArena tasks, Gemini 3.8 Flash leads 6 to 1. A medium month (20M input + 5M output tokens) costs $12 on DeepSeek V4.1 Flash and $33.75 on Gemini 3.8 Flash.
- Pick DeepSeek V4.1 Flash if you want the lower bill ($12 vs $33.75 for a medium month), you care most about coding (+30) or you reuse long prompts (cached input $0.006 vs $0.075).
- Pick Gemini 3.8 Flash if you care most about vision (+64), creative writing (+57) and reasoning and math (+48).
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 | DeepSeek V4.1 Flash | Gemini 3.8 Flash |
|---|---|---|
| Price per 1M tokens | ||
| Input | $0.30 | $0.75 |
| Cached input | $0.006 | $0.075 |
| Output | $1.20 | $3.75 |
| Blend 3:1 | $0.525 | $1.50 |
| Sample month, medium | $12 | $33.75 |
| Context | ||
| Context window | 1M tokens | 1M tokens |
| Quality (LMArena, out of 100) | ||
| Coding | 52/100 #10 of 23 | 22/100 #15 of 23 |
| Chat | 13/100 #15 of 25 | 52/100 #5 of 25 |
| Creative writing | 0/100 #16 of 25 | 57/100 #3 of 25 |
| Roleplay and characters | 0/100 #17 of 25 | 37/100 #3 of 25 |
| Reasoning and math | 40/100 #11 of 24 | 88/100 #4 of 24 |
| Vision | 10/100 #17 of 21 | 74/100 #5 of 21 |
| Long documents | Not ranked | Not ranked |
| Cheap bulk and agents | 51/100 #16 of 23 | 54/100 #12 of 23 |
| Details | ||
| Provider | DeepSeek | |
| API model id | deepseek-flash | gemini-3.8-flash |
| Notes | Peak rate. Off-peak is half price. | Through Dec 31, 2026. From Jan 1, 2027: $1.50 in, $7.50 out. |
| Sources | ||
| Last checked | 2026-10-19 | 2026-10-19 |
| Official pricing | DeepSeek pricing | Google 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): DeepSeek V4.1 Flash #10 of 23 (52/100), Gemini 3.8 Flash #15 of 23 (22/100)
- Chat (Text Arena): DeepSeek V4.1 Flash #15 of 25 (13/100), Gemini 3.8 Flash #5 of 25 (52/100)
- Creative writing (Text Arena creative writing): DeepSeek V4.1 Flash #16 of 25 (0/100), Gemini 3.8 Flash #3 of 25 (57/100)
- Roleplay and characters (Text Arena multi-turn): DeepSeek V4.1 Flash #17 of 25 (0/100), Gemini 3.8 Flash #3 of 25 (37/100)
- Reasoning and math (Text Arena math): DeepSeek V4.1 Flash #11 of 24 (40/100), Gemini 3.8 Flash #4 of 24 (88/100)
- Vision (Vision Arena): DeepSeek V4.1 Flash #17 of 21 (10/100), Gemini 3.8 Flash #5 of 21 (74/100)
- Long documents (Document Arena): DeepSeek V4.1 Flash not ranked, Gemini 3.8 Flash not ranked
- Cheap bulk and agents (Agent Arena): DeepSeek V4.1 Flash #16 of 23 (51/100), Gemini 3.8 Flash #12 of 23 (54/100)
Pricing details from the official pages
DeepSeek V4.1 Flash lists $0.30 input, $1.20 output, $0.006 cached input per 1M tokens on DeepSeek pricing. Gemini 3.8 Flash lists $0.75 input, $3.75 output, $0.075 cached input per 1M tokens on Google pricing. Prices checked 2026-10-19.
- DeepSeek V4.1 Flash: Peak rate. Off-peak is half price.
- Gemini 3.8 Flash: Through Dec 31, 2026. From Jan 1, 2027: $1.50 in, $7.50 out.
Sample monthly bill at list price, no caching: Light (2M input + 0.5M output tokens): $1.20 vs $3.38. Medium (20M input + 5M output tokens): $12 vs $33.75. Heavy (200M input + 50M output tokens): $120 vs $337.50.
FAQ
Is DeepSeek V4.1 Flash cheaper than Gemini 3.8 Flash?
DeepSeek V4.1 Flash costs $0.30 input and $1.20 output per 1M tokens; Gemini 3.8 Flash costs $0.75 and $3.75. For a medium month (20M input + 5M output tokens) DeepSeek V4.1 Flash is cheaper: $12 vs $33.75.
Which is better for coding, DeepSeek V4.1 Flash or Gemini 3.8 Flash?
On LMArena's Code Arena DeepSeek V4.1 Flash scores 52/100 (#10 of 23) and Gemini 3.8 Flash 22/100 (#15 of 23), so DeepSeek V4.1 Flash is ahead by 30 points.
Which has the bigger context window?
DeepSeek V4.1 Flash: 1M tokens. Gemini 3.8 Flash: 1M tokens. Both list the same window.
How much do DeepSeek V4.1 Flash and Gemini 3.8 Flash cost per month?
Light (2M input + 0.5M output tokens): $1.20 vs $3.38. Medium (20M input + 5M output tokens): $12 vs $33.75. Heavy (200M input + 50M output tokens): $120 vs $337.50. 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.