Inkling Small
nano-gpt/thinkingmachines/Inkling-Small · family ling · in: text, image, audio → out: text · price provider-declared (via models.dev). Capabilities: tools 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
#3358 of 7,708
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 524,288 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools text image audio
Same model, other providers
“Inkling Small” is offered by 11 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 | 1M |
| DevPass (LLM Gateway) | $0.45 | $1.2 | $0.64 | 524k |
| NanoGPT (this) | $0.5 | $1.2 | $0.68 | 524k |
| Baseten | $0.5 | $1.2 | $0.68 | 1M |
| Hugging Face | $0.5 | $1.2 | $0.68 | 524k |
| Vercel AI Gateway | $0.5 | $1.2 | $0.68 | 1M |
| Pioneer | $0.5 | $1.2 | $0.68 | 1M |
| Arcee | $0.5 | $1.2 | $0.68 | 262k |
| LLMTR | $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 NanoGPT 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):