Muse Spark 1.3
aihubmix/muse-spark-1.3 · family muse · in: text, image, video, pdf, audio → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video pdf audio.
$2.20
Blended $/1M (3:1)
$1.38
Input $/1M
$4.68
Output $/1M
$6.05
1M in + 1M out
$0.165 −88%
Cache read $/1M
#5485 of 7,708
Cheapest rank
- Provider
- AIHubMix (
aihubmix) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text image video pdf audio
Same model, other providers
“Muse Spark 1.3” is offered by 10 providers — cheapest-effective first. EmpirioLabs AI is the cheapest at $2.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| EmpirioLabs AI | $1.25 | $4.25 | $2.00 | 1M |
| NanoGPT | $1.25 | $4.25 | $2.00 | 1M |
| Kilo Gateway | $1.25 | $4.25 | $2.00 | 1M |
| OpenRouter | $1.25 | $4.25 | $2.00 | 1M |
| Meta | $1.25 | $4.25 | $2.00 | 1M |
| Vercel AI Gateway | $1.25 | $4.25 | $2.00 | 1M |
| Opper | $1.25 | $4.25 | $2.00 | 1M |
| OpenCode Zen | $1.25 | $4.25 | $2.00 | 1M |
| DevPass (LLM Gateway) | $1.25 | $4.25 | $2.00 | 1M |
| AIHubMix (this) | $1.38 | $4.68 | $2.20 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at AIHubMix 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-1.3","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):