DeepSeek-V4-Flash-0731 vs Muse Spark 1.1
API pricing, benchmark indices and specs — updated 19 October 2026.
deepseek-ai · A · Open weights
Params
304.2 B
Context
1,048,576
30d
4.3 M
mit · commercial OK
meta · B · API-only
Input / 1M
$1.25
Output / 1M
$4.25
AA index
33.7
proprietary · 1M context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash-0731 | Muse Spark 1.1 |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 304.2 B | n/a — API-only |
| Architecture | DeepseekV4ForCausalLM | n/a — API-only |
| Context length | 1,048,576 | 1,048,576 |
| Licence | mit | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 4,348,313 | n/a — API-only |
| Downloads all time | 11.9 M | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2026-07-31 | n/a — API-only |
| API input price / 1M tokens | $0.044 | $1.25 |
| API output price / 1M tokens | $0.13 | $4.25 |
| Est. cost per 1M input + 1M output tokens | $0.18 | $5.50 |
| Cached input / 1M tokens | $0.0014 | $0.15 |
| AA Intelligence Index | 34.3 | 33.7 |
| AA Coding Index | 69.1 | 71.3 |
| AA Agentic Index | 41 | 25.8 |
| Max output tokens | 131,072 | 943,718 |
| 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
Muse Spark 1.1
$5.50
DeepSeek-V4-Flash-0731 is 31.0× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB