Inkling Small
llmtr/thinkingmachines/inkling-small · family ling · in: text, image, audio → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image audio.
$0.79
Blended $/1M (3:1)
$0.58
Input $/1M
$1.44
Output $/1M
$2.02
1M in + 1M out
—
Cache read $/1M
#3729 of 7,881
Cheapest rank
- Provider
- LLMTR (
llmtr) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text image audio
Same model, other providers
“Inkling Small” is offered by 10 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 |
| Kilo Gateway | $0.45 | $1.2 | $0.64 | 524k |
| OpenRouter | $0.45 | $1.2 | $0.64 | 524k |
| Vercel AI Gateway | $0.45 | $1.2 | $0.64 | 1M |
| NanoGPT | $0.5 | $1.2 | $0.68 | 524k |
| Baseten | $0.5 | $1.2 | $0.68 | 1M |
| Hugging Face | $0.5 | $1.2 | $0.68 | 524k |
| Pioneer | $0.5 | $1.2 | $0.68 | 1M |
| Arcee | $0.5 | $1.2 | $0.68 | 262k |
| LLMTR (this) | $0.58 | $1.44 | $0.79 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at LLMTR and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"thinkingmachines/inkling-small","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):