DeepSeek-V4.1-Flash-1017 vs Muse Spark 1.2

API pricing, benchmark indices and specs — updated 19 October 2026.

deepseek-ai · A · Open weights

Params

763.2 B

Context

—

30d

58 K

mit · commercial OK

meta · B · API-only

Input / 1M

$1.25

Output / 1M

$4.25

AA index

39.6

proprietary · 1M context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	DeepSeek-V4.1-Flash-1017	Muse Spark 1.2
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	763.2 B	n/a — API-only
Architecture	DeepseekV41ForCausalLM	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	57,715	n/a — API-only
Downloads all time	58 K	n/a — API-only
Quantizations on the Hub	SAFETENSORS	n/a — API-only
Gated	No	n/a — API-only
First seen on the Hub	2026-10-17	n/a — API-only
API input price / 1M tokens	$0.15	$1.25
API output price / 1M tokens	$0.60	$4.25
Est. cost per 1M input + 1M output tokens	$0.75	$5.50
Cached input / 1M tokens	$0.003	$0.15
AA Intelligence Index	39.5	39.6
AA Coding Index	—	72.2
AA Agentic Index	—	43.2
Max output tokens	393,216	943,718
API providers	29	1
Tool calling	Yes	Yes
Reasoning mode	Yes	Yes

Estimated cost of 1M input + 1M output tokens via OpenRouter

DeepSeek-V4.1-Flash-1017 $0.75

Muse Spark 1.2 $5.50

DeepSeek-V4.1-Flash-1017 is 7.3× cheaper at list price.

On RTX 4090 · 24 GB · 8K context unless noted

DeepSeek-V4.1-Flash-1017 · fp16 676.3 GB / 24 GB

❌ Won’t fit