DeepSeek-V4-Flash-0731 vs Qwen3-235B-A22B-Instruct-2507
Specs, VRAM requirements and download trends — updated 10 November 2026.
deepseek-ai · A · Open weights
Params
304.2 B
Context
1,048,576
30d
2.7 M
mit · commercial OK
Qwen · B · Open weights
Params
235.1 B
Context
262,144
30d
139 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash-0731 | Qwen3-235B-A22B-Instruct-2507 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 304.2 B | 235.1 B |
| Architecture | DeepseekV4ForCausalLM | Qwen3MoeForCausalLM |
| Context length | 1,048,576 | 262,144 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 2,697,621 | 139,396 |
| Downloads all time | 13.2 M | 1.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-31 | 2025-07-21 |
| API input price / 1M tokens | $0.043 | $0.14 |
| API output price / 1M tokens | $0.30 | $0.80 |
| Est. cost per 1M input + 1M output tokens | $0.34 | $0.94 |
| Cached input / 1M tokens | $0.035 | $0.05 |
| AA Intelligence Index | — | — |
| AA Coding Index | 69.1 | — |
| AA Agentic Index | 41 | — |
| Max output tokens | 943,718 | 117,964 |
| API providers | 24 | 4 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Flash-0731
$0.34
Qwen3-235B-A22B-Instruct-2507
$0.94
DeepSeek-V4-Flash-0731 is 2.7× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.7 M139 K
DeepSeek-V4-Flash-0731
Qwen3-235B-A22B-Instruct-2507
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-235B-A22B-Instruct-2507 · fp16 @ 256K ctx
1,646.2 GB / 24 GB
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB