Thinking Machines: Inkling
thinkingmachines/inklingInkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
Modalities
In / out per 1M$1.00 / $4.05
Context512K
ReleasedJul 17, 2026
Providers
2 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $1.00 | $4.05 | $0.17 | 0.29s | 133 tps | 99.64% | |
 DeepInfraus · fp8 | $0.95 | $4.05 | $0.16 | 0.76s | 105 tps | 99.38% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Inkling in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Inkling costs pay-as-you-go elsewhere, not what you pay here.
Input
$1.00
per 1M tokens
Output
$4.05
per 1M tokens
Cache read
$0.17
per 1M cached tokens
Included in every pass
Inkling is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s1.0s2.0s3.0s4.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepInfra (us) Together
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepInfra (us) Together
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 97.37%
Oct 16, 11:00 AMNow
Availability over the last 24 hoursAvailability 98.15%
100% 93% 87% 80%
Oct 18, 11:40 AMNow
Apps
Tools that most often run Inkling, by tokens this week.
Activity
78.4B tokens processed market-wide in the last month.
02.0B4.0B6.0B8.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens
FAQ
Which model id do I use for Inkling?
thinkingmachines/inkling. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Inkling hold?
524,288 tokens per request, of which up to 471,859 can be the response.
What can it accept and return?
Input: text, image, audio. Output: text.
What does Inkling cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $1.00 per 1M input tokens and $4.05 per 1M output tokens.
Who built Inkling?
Thinking Machines, in the Inkling family.
Explore
Other models your pass can call.
