← Leaderboard
DeepSeek V4 Flash Vision Exp
Open source
Self-hostable
Free to run
DeepSeek
Open license
text
vision
Released 2mo agoAvg score
49.7
/ 100 · not enough data for the index
Context
1.0M
Output limit
262k
Input price
$0.22 /M
Output price
$0.65 /M
Parameters
304.6B · 15.2B active
Est. VRAM (Q4)
~182.8 GB
Public list price, verified 8h ago · cached input $0.0069 /M
Added automatically from the public model catalog. Family and licence details are not curated yet; benchmark scores appear as upstream leaderboards list this model.
Benchmarks
performance
Output SpeedN/A
tok/sMedian output speed in tokens per second over the last 14 days on the model maker's own API, measured nightly with a fixed ~800-token prompt and ~250-token answer. Models not yet probed fall back to a dated manual figure. Higher is faster.
Time to First TokenN/A
msMedian time from request to first streamed token in milliseconds over the last 14 days on the model maker's own API, using the same nightly probe prompt. Lower is snappier; reasoning models are penalised here because they think before talking.
Reliability monitor
Loading drift signal…
Hosted endpoints
| Host | Input $/M | Output $/M | Context | Speed | TTFT | Uptime 24h | Quant |
|---|---|---|---|---|---|---|---|
| Host 37 | $0.22 | $0.65 | 1.0M | 113 tok/s | 0.99 s | 100.0% | fp8 |
| Host 44 | $0.44 | $1.32 | 1.0M | 129 tok/s | 1.19 s | 100.0% | fp8 |
| Host 43 | $0.44 | $1.32 | 1.0M | — | — | 100.0% | fp8 |
Anonymised third-party hosts. Sorted by lowest output price. Speed and time to first token are medians from our nightly probe where measured; uptime is the catalog's 24-hour figure.