DeepSeek-V4-Flash
01
Snapshot
Overall
67
rank #16 of 22
Coding
65
rank #16 of 22
Multimodal
65
rank #20 of 22
Input / Output
$0.14 / $0.28
USD per 1M tokens
Context
1M
usable recall 90
Speed
~85 tok/s
TTFT 0.3s
Aggregated from public sources and independently weighted; methodology on the Terms page. Scores within 3 points are treated as statistically tied.
02
Specs & pricing
Every tracked field. List API prices in USD per 1M tokens; verify current vendor pricing before purchase.
| Vendor | DeepSeek (CN) |
| Released / current | 2026.04 |
| Licensing | Open weights |
| Context window | 1M |
| Max output | 128K |
| Effective-context score | 90 |
| Input / output price | $0.14 / $0.28 per 1M tokens |
| Cache discount | No published cache discount |
| Free tier | DeepSeek App free |
| Speed / TTFT | ~85 tok/s / 0.3s |
| Function calling | 72 |
| Refusal rate | ~5% |
| English / Chinese | 75 / 80 |
| Modalities | text |
| Fine-tuning | Yes |
| Private deployment | Yes (enterprise) |
| SOC2 / no-train | no / yes |
03
Strengths & watch-outs
Strengths
- Rock-bottom price
- Fast
- Open source
- Fit for simple tasks
Watch-outs
- Weak on complex tasks
- Text-only
04
Where it ranks among 22 models
Overall 67/100 (#16), coding 65 (#16), multimodal 65 (#20). See the full boards and side-by-side compare on the leaderboard.
05
Pricing in practice
Illustrative monthly bill for 100M input + 30M output tokens: $22 at list. Your mix and cache-hit ratio change this.
Illustrative model using public list rates before any enterprise agreement; cache discount: No published cache discount.
06
Frequently asked questions
How much does DeepSeek-V4-Flash cost?
List API pricing is $0.14 input and $0.28 output per 1M tokens. No published cache discount. DeepSeek App free
What is DeepSeek-V4-Flash's context window, and is it usable end to end?
It advertises a 1M window with 128K max output; its effective-context score is 90/100, which is the better predictor of whether long-document details are actually retained.
Is DeepSeek-V4-Flash good for coding?
Its coding aggregate is 65/100, rank #16 of 22. It is adequate for scripts and assisted completion rather than the most demanding SWE-style work.
Can I self-host DeepSeek-V4-Flash?
Yes — it ships open weights and supports private deployment, so you can run it on your own infrastructure for data control; budget for GPU and operations.
How strong is it in Chinese and on multimodal inputs?
Chinese score is 80 versus English 75; multimodal aggregate is 65/100 (rank #20), accepting text.