Free to start

Thinking Machines: Inkling

Try Inkling on us. Starter credit covers your first requests, then one key reaches all 3 provider routes with automatic failover.

`thinkingmachines/inkling`

open weights US providers EU-focused Thinking Machines Lab

All models

Publisher	Thinking Machines Labthinkingmachines
AI IQ	IQ 107 #90 on AI IQ
Context	524,288 tokens
Providers	Together ZDR Thinking Machines Lab Databricks
Credits routes	3 provider routes
Modes	chat open weights US providers EU-focused
Billing	Credits

Current route evidence

Live leaderboard

$1.055/1MLowest Credits input price

$4.27275/1MLowest Credits output price

1279 msFastest measured p50 TTFT via thinkingmachines

not enough dataHighest measured throughput

Recent provider-route uptime spans 11.11% to 100.00% across 3 routes and 3 providers. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.

All route prices All providers

Providers serving this model

Sorted by lowest combined prompt and completion price. Use "provider": {"sort": "throughput"} in the request body (or append :nitro to the model id) to route to the fastest provider instead.

Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture. Company country is separate from inference location. Weight formats are source-backed declarations, not per-request proofs.

Provider	Input	Cached input	Output	Weight format	Provider policy	Company / inference location	Measured speed
Databricksdatabricks	$1.055/1M	$0.17935/1M	$4.27275/1M	Unknown	no verified privacy claim Retention details Databricks Foundation Model APIs are a Designated Service and pay-per-token workloads are HIPAA compliant. Databricks may temporarily process or store inputs and outputs for abuse prevention, and may process data outside the originating cloud or region. This route is therefore standard privacy, not ZDR, confidential compute, or end-to-end encrypted. Provider policy source	Operator country: US Location details Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-31T16:52:59.000Z
Thinking Machines Labthinkingmachines	$1.055/1M	$0.17935/1M	$4.27275/1M	Unknown	privacy unknown Retention details No provider-ZDR claim is tracked here. Thinking Machines Lab's model and pricing documentation is linked for model capability and API review. Provider policy source	Operator country: US Location details Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Full location evidence	TTFT: 1.28 s Speed: insufficient data Last sample: 2026-10-31T17:39:48.000Z
Togethertogether	$1.055/1M	$0.17935/1M	$4.27275/1M	Unknown	ZDR Retention details Tracked as provider ZDR. Together documents that inference inputs and outputs are not stored by default; temporary prompt caching may be used for performance, and sharing content for training is opt-in. Provider policy source	Operator country: US Location details Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Full location evidence	TTFT: insufficient data Speed: insufficient data Last sample: 2026-10-31T13:01:55.000Z

Speed is the median (p50) from TR's recent measured requests for this exact model and provider, refreshed from the cached leaderboard. At least two timing samples are required; workload and network conditions affect results. Performance details

Compare Thinking Machines: Inkling

All comparisons

Thinking Machines: Inkling vs Z.ai: GLM 5.336 combined provider routes
Thinking Machines: Inkling vs Z.ai: GLM 5.235 combined provider routes
Thinking Machines: Inkling vs Z.ai: GLM 5.3 Flash35 combined provider routes
MoonshotAI: Kimi K3 vs Thinking Machines: Inkling31 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs Thinking Machines: Inkling29 combined provider routes
DeepSeek: DeepSeek V4.1 Flash vs Thinking Machines: Inkling27 combined provider routes

Questions

What model ID should I use for Thinking Machines: Inkling?

Use thinkingmachines/inkling as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve Thinking Machines: Inkling?

TrustedRouter currently lists Together, Thinking Machines Lab, and Databricks for Thinking Machines: Inkling. Provider availability and routing eligibility can change as catalog and health data update.

How much does Thinking Machines: Inkling cost through TrustedRouter?

The current lowest Credits input price is $1.055/1M and the lowest Credits output price is $4.27275/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for Thinking Machines: Inkling?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.