per 1M tokens
thinkingmachines/Inkling-Small
deepinfra/thinkingmachines/Inkling-Small
Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable thinking effort
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
No provider prices yet.
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$1.65 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.45/1M | $1.2/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.45 | $1.2 | Not published— |
| 2026-10-09 | token | $0.45 | $1.2 | Not published— |
| 2026-10-10 | token | $0.45 | $1.2 | Not published— |
| 2026-10-11 | token | $0.45 | $1.2 | Not published— |
| 2026-10-12 | token | $0.45 | $1.2 | Not published— |
| 2026-10-13 | token | $0.45 | $1.2 | Not published— |
| 2026-10-14 | token | $0.45 | $1.2 | Not published— |
| 2026-10-15 | token | $0.45 | $1.2 | Not published— |
| 2026-10-16 | token | $0.45 | $1.2 | Not published— |
| 2026-10-17 | token | $0.45 | $1.2 | Not published— |
| 2026-10-18 | token | $0.45 | $1.2 | Not published— |
| 2026-10-19 | token | $0.45 | $1.2 | Not published— |
| 2026-10-20 | token | $0.45 | $1.2 | Not published— |
| 2026-10-21 | token | $0.45 | $1.2 | Not published— |
| 2026-10-22 | token | $0.45 | $1.2 | Not published— |
| 2026-10-23 | token | $0.45 | $1.2 | Not published— |
| 2026-10-24 | token | $0.45 | $1.2 | Not published— |
| 2026-10-25 | token | $0.45 | $1.2 | Not published— |
| 2026-10-26 | token | $0.45 | $1.2 | Not published— |
| 2026-10-27 | token | $0.45 | $1.2 | Not published— |
| 2026-10-28 | token | $0.45 | $1.2 | Not published— |
| 2026-10-29 | token | $0.45 | $1.2 | Not published— |
| 2026-10-30 | token | $0.45 | $1.2 | Not published— |
Alternatives
- @cf/qwen/qwen3.8-27b$0.45/1M · Compare
- Doubao Seed 2.1 Turbo$0.45/1M · Compare
- GLM 4.7 FP8$0.45/1M · Compare
- Mixtral 8x7B$0.45/1M · Compare
- qwen-3-8-27b$0.45/1M · Compare
- Qwen/Qwen3.5-397B-A17B$0.45/1M · Compare
Parameters (5)
chatvlmvisionprompt_cachereasoning
Call this model
OpenRouter id deepinfra/thinkingmachines/Inkling-Small. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepinfra/thinkingmachines/Inkling-Small","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "deepinfra/thinkingmachines/Inkling-Small",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "deepinfra/thinkingmachines/Inkling-Small", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())