DeepSeek-V4-Flash-0731 vs c4ai-command-a-03-2025
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
CohereLabs · B · Open weights
Params
111.1 B
Context
—
30d
1 K
cc-by-nc-4.0 · non-commercial
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash-0731 | c4ai-command-a-03-2025 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 304.2 B | 111.1 B |
| Architecture | DeepseekV4ForCausalLM | Cohere2ForCausalLM |
| Context length | 1,048,576 | 256,000 |
| Licence | mit | cc-by-nc-4.0 |
| Commercial use | Allowed | Not allowed |
| Languages | — | 23 |
| Downloads 30d | 4,348,313 | 1,494 |
| Downloads all time | 11.9 M | 126 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2026-07-31 | 2025-03-11 |
| API input price / 1M tokens | $0.044 | $2.50 |
| API output price / 1M tokens | $0.13 | $10.00 |
| Est. cost per 1M input + 1M output tokens | $0.18 | $12.50 |
| Cached input / 1M tokens | $0.0014 | — |
| AA Intelligence Index | 34.3 | 13.1 |
| AA Coding Index | 69.1 | 27.8 |
| AA Agentic Index | 41 | 1 |
| Max output tokens | 131,072 | 8,192 |
| API providers | 22 | 1 |
| Tool calling | Yes | No |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Flash-0731
$0.18
c4ai-command-a-03-2025
$12.50
DeepSeek-V4-Flash-0731 is 70.3× cheaper at list price.
Download trend
Daily snapshots, last 82 days (4 Aug – 24 Oct)
4.7 M2 K
DeepSeek-V4-Flash-0731
c4ai-command-a-03-2025
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
c4ai-command-a-03-2025 · fp16
261.5 GB / 24 GB
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB