Inkling Small
thinkingmachines/thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4 · family ling · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.52
Blended $/1M (3:1)
$0.3
Input $/1M
$1.2
Output $/1M
$1.50
1M in + 1M out
$0.06 −80%
Cache read $/1M
#3178 of 8,511
Cheapest rank
- Provider
- Thinking Machines (
thinkingmachines) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Inkling Small” is offered by 11 providers — cheapest-effective first. This one (Thinking Machines) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Thinking Machines (this) | $0.3 | $1.2 | $0.52 | 262k |
| Deep Infra | $0.45 | $1.2 | $0.64 | 524k |
| Vercel AI Gateway | $0.45 | $1.2 | $0.64 | 1M |
| Kilo Gateway | $0.45 | $1.2 | $0.64 | 524k |
| OpenRouter | $0.45 | $1.2 | $0.64 | 524k |
| NanoGPT | $0.45 | $1.2 | $0.64 | 524k |
| CommandCode | $0.5 | $1.2 | $0.68 | 1M |
| Arcee | $0.5 | $1.2 | $0.68 | 262k |
| Hugging Face | $0.5 | $1.2 | $0.68 | 524k |
| LLMTR | $0.58 | $1.44 | $0.79 | 262k |
| AI/ML API | $0.6136 | $1.52 | $0.84 | 524k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Thinking Machines 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:peft:262144:sampling-nvfp4","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):