jishie

Muse Spark 1.2

kilo/meta/muse-spark-1.2 · family muse · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideopdfaudio.

$2.00Blended $/1M (3:1)
$1.25Input $/1M
$4.25Output $/1M
$5.501M in + 1M out
$0.15 −88%Cache read $/1M
#3998 of 5,000Cheapest rank
Provider
Kilo Gateway (kilo)
Context
1,048,576 tokens
Max output
1,048,576 tokens
Capabilities
toolsreasoningtextimagevideopdfaudio

Same model, other providers

“Muse Spark 1.2” is offered by 7 providers — cheapest-effective first. This one (Kilo Gateway) is the cheapest.

ProviderInputOutputBlendedContext
Kilo Gateway (this)$1.25$4.25$2.001049k
NanoGPT$1.25$4.25$2.001000k
LLM Gateway$1.25$4.25$2.001049k
Meta$1.25$4.25$2.001049k
Merge Gateway$1.25$4.25$2.001049k
Vercel AI Gateway$1.25$4.25$2.001049k
OpenRouter$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 Kilo Gateway and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"meta/muse-spark-1.2","messages":[{"role":"user","content":"hello"}]}'

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