Inkling Small
edenai/together_ai/thinkingmachines/Inkling-Small · family ling · in: text, image, audio → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image audio.
$0.68
Blended $/1M (3:1)
$0.5
Input $/1M
$1.2
Output $/1M
$1.70
1M in + 1M out
$0.1 −80%
Cache read $/1M
#2666 of 6,123
Cheapest rank
- Provider
- Eden AI (
edenai) - Kind
- text (outputs text)
- Context
- 524,288 tokens
- Max output
- 1,048,576 tokens
- Capabilities
- tools reasoning text image audio
Same model, other providers
“Inkling Small” is offered by 8 providers — cheapest-effective first. Deep Infra is the cheapest at $0.64 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Deep Infra | $0.45 | $1.2 | $0.64 | 524k |
| OpenRouter | $0.45 | $1.2 | $0.64 | 524k |
| Kilo Gateway | $0.45 | $1.2 | $0.64 | 524k |
| Eden AI (this) | $0.5 | $1.2 | $0.68 | 524k |
| NanoGPT | $0.5 | $1.2 | $0.68 | 524k |
| Hugging Face | $0.5 | $1.2 | $0.68 | 524k |
| Baseten | $0.5 | $1.2 | $0.68 | 1M |
| Vercel AI Gateway | $0.5 | $1.2 | $0.68 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Eden AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"together_ai/thinkingmachines/Inkling-Small","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):