DeepSeek-V4-Pro vs Kimi-K2.5
Specs, VRAM requirements and download trends — updated 14 August 2026.
deepseek-ai · A · Open weights
Params
1,598.8 B
Context
1,048,576
30d
336 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Pro | Kimi-K2.5 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 1,598.8 B | 1,026.4 B |
| Architecture | DeepseekV4ForCausalLM | KimiK25ForConditionalGeneration |
| Context length | 1,048,576 | — |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 335,647 | 166,174 |
| Downloads all time | 11.2 M | 6.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-22 | 2026-01-27 |
| API input price / 1M tokens | $0.96 | not on OpenRouter |
| API output price / 1M tokens | $1.91 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $2.87 | not on OpenRouter |
| Cached input / 1M tokens | $0.08 | not on OpenRouter |
| AA Intelligence Index | 12.6 | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 384,000 | not on OpenRouter |
| API providers | 12 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Pro
$2.87
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.4 M166 K
DeepSeek-V4-Pro
Kimi-K2.5
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Kimi-K2.5 · fp16
877.8 GB / 24 GB
DeepSeek-V4-Pro · fp16 @ 1024K ctx
31,649.4 GB / 24 GB