Thinking Machines Lab
Explore Thinking Machines Lab models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Thinking Machines Labthinkingmachines
No provider claim
| Provider | Thinking Machines Lab |
|---|---|
| Routing status | Active |
| Provider website | https://thinkingmachines.ai/ |
| Models | 3 public models |
| Credits routes | 3 |
| BYOK routes | 3 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | No provider-ZDR claim is tracked here. Thinking Machines Lab's model and pricing documentation is linked for model capability and API review. Policy source |
Measured performance
40 samplesContinuously sampled across Thinking Machines Lab's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1611 ms |
|---|---|
| Effective throughput | 41 tok/s n=1 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| thinkingmachines/inkling-small | 1611 ms | — | 100.00% | — | 22 |
| thinkingmachines/inkling | 2781 ms | 41 tok/s n=1 | 100.00% | — | 15 |
| z-ai/glm-5.3 | 2626 ms | — | 100.00% | — | 3 |
Thinking Machines Lab performance history · Full provider & model leaderboard.
Models served by Thinking Machines Lab.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
thinkingmachines/inklingThinking Machines: Inkling |
IQ 108#60 | 1,048,576 | 2 | $1.055/1M | $4.27275/1M | prepaid BYOK |
thinkingmachines/inkling-smallThinking Machines: Inkling Small |
IQ 106#65 | 1,048,576 | 2 | $0.3165/1M | $1.266/1M | prepaid BYOK |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 123#15 | 1,048,576 | 2 | $5.1273/1M | $12.81825/1M | prepaid BYOK |
Questions
Does Thinking Machines Lab have zero data retention?
TrustedRouter does not currently mark Thinking Machines Lab as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Thinking Machines Lab end-to-end encrypted?
TrustedRouter does not currently mark Thinking Machines Lab as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Thinking Machines Lab models are available through TrustedRouter?
This page currently lists 3 public Thinking Machines Lab models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.