All models1 shown
Inkling Small
DeepInfradeepinfra/Inkling-Small
Released Jul 30, 2026
- providers
- 1
- context
- 524.2K
- input /M
- $0.45
- output /M
- $1.20
- cached input /M
- $0.10
also answers tothinkingmachines/inkling-smallthinkingmachines/inkling-small-20260730
About
- open weights
- yes
- best for
- extractioncodingcompute
Capabilities
What the model accepts and returns, where a probe through our own gateway proved it.
- streaming
- tools
- json mode
- vision
- audio
Providers
What you pay through us for each provider, and its own list price where that differs.
DeepInfra
deepinfra/Inkling-Small- input /M
- $0.45
- output /M
- $1.20
- cache read /M
- $0.10
Cache read $0.10/M
cache read list price /M$0.10524.2K context
Speed
- fastest over 24 hours
- 162.0 t/s
Fastest: DeepInfra
- DeepInfra625 ms to first token162.0 t/smedian of 23
Served
- served in the last 24 hours
- 86.96%
Across 1 provider, 20 of 23 requests
- DeepInfra86.96% · 20 of 23
Rebuilt once a day from the requests we sent, so it is a daily figure and not a live one.
not yet
Not yet. These figures come from Artificial Analysis, which the publish pipeline reads once a day.
Integrations
What the model holds, rather than a compatibility grade: nothing here measures how well a particular tool gets on with it, so nothing here scores one.
- answers on
- chat completions
- accepts
- textimageaudio
- returns
- text
Use this model
Works with the OpenAI SDK. Point it at our base URL and use this id.
curl https://api.hopscotchlabs.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepinfra/Inkling-Small",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 256
}'