Inkling

Thinking Machines Lab's open-weight multimodal MoE model (975B total, 41B active) for reasoning, coding, and agentic tool use.

524,288 context
Released July 18, 2026
Starting at $0.95/M input tokens
Starting at $4.05/M output tokens
Streaming
Vision
Tools
Reasoning
JSON Output
Structured JSON
No ratings yetSign in to rate

Select Provider

All Providers for Inkling

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Context: 524.3kQuant: fp8
Input
$0.95
/M tokens
Cache Read
$0.16
/M tokens
Output
$4.05
/M tokens
Get Started
Context: 524.3kQuant: fp8
Input
$1
/M tokens
Cache Read
$0.17
/M tokens
Output
$4.05
/M tokens
Get Started

Frequently asked questions

What is Inkling?

Thinking Machines Lab's open-weight multimodal MoE model (975B total, 41B active) for reasoning, coding, and agentic tool use. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does Inkling cost?

Pricing for Inkling on LLM Gateway starts at $0.95 per million input tokens and $4.05 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of Inkling?

Inkling supports a context window of up to 524,288 tokens on its largest provider deployment.

Which providers serve Inkling?

Inkling is served by DeepInfra, Together AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does Inkling support tool calling and structured outputs?

Yes. Inkling supports both tool (function) calling and strict JSON output schema (upstream-enforced) through LLM Gateway.

When was Inkling released?

Inkling was released on July 18, 2026.