jishie

Muse Spark 1.1

meta/muse-spark-1.1 · family muse · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagepdfvideo.

$2.00Blended $/1M (3:1)
$1.25Input $/1M
$4.25Output $/1M
$5.501M in + 1M out
$0.15 −88%Cache read $/1M
#3979 of 5,000Cheapest rank
Provider
Meta (meta)
Context
1,000,000 tokens
Max output
32,000 tokens
Capabilities
toolsreasoningtextimagepdfvideo

Same model, other providers

“Muse Spark 1.1” is offered by 9 providers — cheapest-effective first. This one (Meta) is the cheapest.

ProviderInputOutputBlendedContext
Meta (this)$1.25$4.25$2.001000k
NanoGPT$1.25$4.25$2.001000k
LLM Gateway$1.25$4.25$2.001049k
Pioneer$1.25$4.25$2.001049k
Abacus$1.25$4.25$2.001000k
EmpirioLabs AI$1.25$4.25$2.001049k
Kilo Gateway$1.25$4.25$2.001049k
Merge Gateway$1.25$4.25$2.001049k
Vercel AI Gateway$1.25$4.25$2.001049k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Meta and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"muse-spark-1.1","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):