Kolibri 1
aki-io/kolibri-1-tl5 · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.28
Blended $/1M (3:1)
$0.1675
Input $/1M
$0.6141
Output $/1M
$0.78
1M in + 1M out
$0.0837 −50%
Cache read $/1M
#2585 of 9,563
Cheapest rank
- Provider
- AKI.IO (
aki-io) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 81,920 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Kolibri 1” is offered by 4 providers — cheapest-effective first. Munito AI is the cheapest at $0.23 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Munito AI | $0.13 | $0.51 | $0.23 | 1M |
| Munito AI (EU) | $0.16 | $0.56 | $0.26 | 1M |
| NanoGPT | $0.168 | $0.588 | $0.27 | 1M |
| AKI.IO (this) | $0.1675 | $0.6141 | $0.28 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at AKI.IO and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"kolibri-1-tl5","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):