jishie

Muse Spark 1.2

abacus/muse-spark-1.2 · family muse · in: text, image, audio, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image audio video.

$2.00
Blended $/1M (3:1)
$1.25
Input $/1M
$4.25
Output $/1M
$5.50
1M in + 1M out
$0.15 −88%
Cache read $/1M
#4383 of 6,379
Cheapest rank
Provider
Abacus (abacus)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text image audio video

Same model, other providers

“Muse Spark 1.2” is offered by 11 providers — cheapest-effective first. OpenCode Go is the cheapest at $0.13 blended.

ProviderInputOutputBlendedContext
OpenCode Go$0.1$0.2$0.131M
Abacus (this)$1.25$4.25$2.001M
NanoGPT$1.25$4.25$2.001M
Meta$1.25$4.25$2.001M
OpenRouter$1.25$4.25$2.001M
Merge Gateway$1.25$4.25$2.001M
OpenCode Zen$1.25$4.25$2.001M
EmpirioLabs AI$1.25$4.25$2.001M
Vercel AI Gateway$1.25$4.25$2.001M
LLM Gateway$1.25$4.25$2.001M
Kilo Gateway$1.25$4.25$2.001M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Abacus 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-1.2","messages":[{"role":"user","content":"hello"}]}'

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

← all Abacus models · model index · JSON