DeepSeek V4.1 Flash
DeepSeekOpen weightsMITReleased Sep 10, 2026
On the arena.ai Agents leaderboard, DeepSeek V4.1 Flash has a Net Improvement of 1.91% (Max, rank #20, 95% interval 1.58%–2.25%). DeepSeek V4.1 Flash ranks #35 on the LMArena Text leaderboard (style control) with an Arena score of 1476.2 (±6.1, 13,657 votes). API price: $0.30 input / $1.20 output per 1M tokens. Context: 1.05M. Nearest rivals: GLM-5.3 Flash (1476.5) above and GPT-5.2 Chat (1475.7) below.
Quick answer
- Agents leaderboard
- #20 of 37 · 1.91% success
- Text (LMArena)
- #35 · 1476.2
- 17NAS overall
- #17 of 36
- API price (in / out)
- $0.30 / $1.20 per 1M tokens
- Closest rival
- GLM-5.3 Flash · 1476.5
- Cheaper alternative
- GLM-5.3 Flash: Text 1476.5, output $0.50 (58% cheaper)
- Data updated
- Oct 29, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Rank history
LMArena rank, last 14 days#38 on Oct 16, #35 now; best #34 in this period.
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 26 |  Gemini 3.5 Flash | 1477.6 | – | $9.00 | – |
| 27 |  Claude Sonnet 5.5 | 1477.1 | 54.2 | $10.00 | 137 |
| 28 |  GLM-5.3 Flash | 1476.5 | – | $0.50 | 67 |
| 29 | DeepSeek V4.1 FlashThis page | 1476.2 | – | $1.20 | – |
| 30 |  GPT-5.2 Chat | 1475.7 | – | $14.00 | – |
| 31 | GPT-6 Astra | 1475.6 | 56.9 | $50.00 | 70 |
| 32 | GLM-5.2 | 1475.3 | – | $4.40 | – |
More from DeepSeek
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 42 | DeepSeek V4 Pro | 1465.1 | 23.1 | $3.96 | 76 |
| 57 | DeepSeek V4 Flash | 1435.7 | – | $0.28 | – |
| 61 | DeepSeek V3.2 | 1424.6 | – | $0.42 | – |
Pricing
- Official API list price: $0.30 input and $1.20 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $0.53 per 1M tokens.
- Among 67 models with an output price, it is the #8 cheapest.
- The cheapest OpenRouter route charges $0.045 input / $0.50 output. That route is over 60% below list price — usually a promotion or a single provider, so check its reliability.
Sources & methodology
On the arena.ai Agents leaderboard, DeepSeek V4.1 Flash has a Net Improvement of 1.91% (Max, rank #20, 95% interval 1.58%–2.25%).
- arena.ai Agents — agent Net Improvement, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
- LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.
FAQ
How does DeepSeek V4.1 Flash do on the Agents leaderboard?
On the arena.ai Agents leaderboard, DeepSeek V4.1 Flash has a Net Improvement of 1.91% (Max, rank #20, 95% interval 1.58%–2.25%).
What rank is DeepSeek V4.1 Flash right now?
DeepSeek V4.1 Flash is #29 on our leaderboard of 63 scored models (Arena score 1476.2); its raw LMArena rank is #35.
What does DeepSeek V4.1 Flash cost via API?
Input $0.30 / output $1.20 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $0.53 per 1M tokens.
How close is DeepSeek V4.1 Flash to the models ranked next to it?
It is 0.3 points behind GLM-5.3 Flash (1476.5) and 0.5 points ahead of GPT-5.2 Chat (1475.7); gaps smaller than the confidence interval (±6.1) are not significant.
Is DeepSeek V4.1 Flash open source? Can it be self-hosted?
DeepSeek V4.1 Flash is an open-weights model (license: MIT); you can download the weights and self-host.
What is the context length of DeepSeek V4.1 Flash?
1.05M (1,048,576 tokens, as listed on OpenRouter).
DeepSeek V4.1 Flash vs GLM-5.3 Flash: which is better?
On the LMArena Text leaderboard DeepSeek V4.1 Flash scores 1476.2 and GLM-5.3 Flash scores 1476.5 (a 0.3-point gap, within the confidence interval, so not significant). Agent task success: DeepSeek V4.1 Flash 1.91%, GLM-5.3 Flash -2.33%. On price, DeepSeek V4.1 Flash costs $1.20 and GLM-5.3 Flash $0.50 per 1M output tokens.
Is there a cheaper model close to DeepSeek V4.1 Flash?
Yes: GLM-5.3 Flash scores 1476.5 on the Text leaderboard (DeepSeek V4.1 Flash: 1476.2) and costs $0.50 per 1M output tokens, about 58% less than DeepSeek V4.1 Flash ($1.20).
Where does the DeepSeek V4.1 Flash data come from and how often is it updated?
Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Oct 29, 2026.