DeepSeek-V4-Pro vs Qwen3.8-2.4T-A95B
Specs, VRAM requirements and download trends — updated 24 October 2026.
deepseek-ai · A · Open weights
Params
1,598.8 B
Context
1,048,576
30d
355 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Pro | Qwen3.8-2.4T-A95B |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 1,598.8 B | 2,446.2 B |
| Architecture | DeepseekV4ForCausalLM | Qwen3_5MoeForCausalLM |
| Context length | 1,048,576 | 262,144 |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 355,279 | 24,938 |
| Downloads all time | 11.0 M | 101 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-22 | 2026-08-08 |
| API input price / 1M tokens | $0.56 | $2.00 |
| API output price / 1M tokens | $1.12 | $6.00 |
| Est. cost per 1M input + 1M output tokens | $1.68 | $8.00 |
| Cached input / 1M tokens | $0.047 | $0.25 |
| AA Intelligence Index | 30.4 | 39.9 |
| AA Coding Index | 59.4 | 71.9 |
| AA Agentic Index | 26.3 | 50.1 |
| Max output tokens | 384,000 | 909,000 |
| API providers | 14 | 5 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Pro
$1.68
Qwen3.8-2.4T-A95B
$8.00
DeepSeek-V4-Pro is 4.8× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
1.7 M25 K
DeepSeek-V4-Pro
Qwen3.8-2.4T-A95B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.8-2.4T-A95B · fp16 @ 256K ctx
17,123.8 GB / 24 GB
DeepSeek-V4-Pro · fp16 @ 1024K ctx
31,649.4 GB / 24 GB