DeepSeek-V4-Flash-0731 vs Qwen3-Next-80B-A3B-Thinking
Specs, VRAM requirements and download trends — updated 24 October 2026.
deepseek-ai · A · Open weights
Params
304.2 B
Context
1,048,576
30d
4.3 M
mit · commercial OK
Qwen · B · Open weights
Params
81.3 B
Context
262,144
30d
38 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash-0731 | Qwen3-Next-80B-A3B-Thinking |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 304.2 B | 81.3 B |
| Architecture | DeepseekV4ForCausalLM | Qwen3NextForCausalLM |
| Context length | 1,048,576 | 262,144 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 4,348,313 | 38,286 |
| Downloads all time | 11.9 M | 2.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-31 | 2025-09-09 |
| API input price / 1M tokens | $0.044 | $0.15 |
| API output price / 1M tokens | $0.13 | $1.20 |
| Est. cost per 1M input + 1M output tokens | $0.18 | $1.35 |
| Cached input / 1M tokens | $0.0014 | — |
| AA Intelligence Index | 34.3 | 11.2 |
| AA Coding Index | 69.1 | 17.4 |
| AA Agentic Index | 41 | — |
| Max output tokens | 131,072 | 235,929 |
| API providers | 22 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Flash-0731
$0.18
Qwen3-Next-80B-A3B-Thinking
$1.35
DeepSeek-V4-Flash-0731 is 7.6× cheaper at list price.
Download trend
Daily snapshots, last 82 days (4 Aug – 24 Oct)
4.7 M39 K
DeepSeek-V4-Flash-0731
Qwen3-Next-80B-A3B-Thinking
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-Next-80B-A3B-Thinking · fp16 @ 256K ctx
569.8 GB / 24 GB
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB