Muse Ember
kenari/muse-ember-1-0 · family muse · in: image, pdf, text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning image pdf text.
$0.34
Blended $/1M (3:1)
$0.1714
Input $/1M
$0.8571
Output $/1M
$1.03
1M in + 1M out
$0.0086 −95%
Cache read $/1M
#2782 of 9,440
Cheapest rank
- Provider
- Kenari (
kenari) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 524,288 tokens
- Capabilities
- tools reasoning image pdf text
Same model, other providers
“Muse Ember” is offered by 6 providers — cheapest-effective first. Meta is the cheapest at $0.20 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Meta | $0.1 | $0.5 | $0.20 | 1M |
| NanoGPT | $0.1 | $0.5 | $0.20 | 1M |
| Vercel AI Gateway | $0.1 | $0.5 | $0.20 | 1M |
| OpenRouter | $0.1 | $0.5 | $0.20 | 1M |
| Cloudflare AI Gateway | $0.1 | $0.5 | $0.20 | 1M |
| Kenari (this) | $0.1714 | $0.8571 | $0.34 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Kenari and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"muse-ember-1-0","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):