Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube

The free Inkling endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.

By using this free endpoint, you agree to the TML Free Research API Terms of ServiceOpens in new tab. For more information about Thinking Machines Lab's data processing practices, see this Privacy NoticeOpens in new tab.

Favicon for thinkingmachines

Thinking Machines: Inkling

thinkingmachines/inkling

Model weights
Compare

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

Modalities
In / Out Price
$0.95 / $4.05per 1M
Context
524K
Released
Jul 17, 2026
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), Floor (cheapest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Thinking Machines: Inkling (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisInkling (xhigh) Intelligence Index25.0
Artificial AnalysisInkling (xhigh) Coding Index52.1
Artificial AnalysisInkling (xhigh) Agentic Index22.5
Artificial AnalysisInkling (xhigh) GPQA Diamond87.2%
Artificial AnalysisInkling (xhigh) HLE31.9%
Artificial AnalysisInkling (xhigh) AA-LCR77.3%
Artificial AnalysisInkling (xhigh) GDPval-AA28.2%
Artificial AnalysisInkling (xhigh) CritPt5.4%
Artificial AnalysisInkling (xhigh) SciCode47.0%
Artificial AnalysisInkling (xhigh) AA-Omniscience Accuracy41.5%
Artificial AnalysisInkling (xhigh) AA-Omniscience Non-Hallucination Rate32.3%
Design ArenaInkling Models Arena 3D Elo1178
Design ArenaInkling Models Arena Asciiart Elo1101
Design ArenaInkling Models Arena Code Categories Elo1213
Design ArenaInkling Models Arena Data Visualization Elo1178
Design ArenaInkling Models Arena Game Development Elo1176
Design ArenaInkling Models Arena SVG Elo1111
Design ArenaInkling Models Arena UI Component Elo1208
Design ArenaInkling Models Arena Website Elo1229

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
$0.95$4.05$0.160.73s48 tps
98.96%
$1.00$4.05$0.171.29s82 tps
96.68%
Throughput
82tok/s

P50, best across providers

Latency
0.73s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchDeepInfra84.1%--Baseten82.1%--Together84.1%68.0%Baseten82.3%69.8%auto-routing82.6%66.3%
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.26%

Availability over the last 3 days

Last 72 hours
Availability 99.26%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.43%
Without Routing
88.79%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
4.56Btokens
2.
Favicon for https://instaplay.ai/
Instaplay
new
3.86Btokens
3.
Favicon for https://github.com/Toloka-F/tolokaforge
Tolokaforge Evaluation
new
1.18Btokens
4.
Favicon for https://portkey.ai/
Portkey AI
Control panel for AI apps
1.03Btokens
5.
Favicon for https://claude.ai/apple-touch-icon.png
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
882Mtokens

Frequently asked questions

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications.

Inkling costs $0.95/M input tokens and $4.05/M output tokens, with separate rates for Cache Read at $0.16/M tokens.

Inkling has a 524,288 token context window. It supports up to 262,144 completion tokens.

Yes. Inkling accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.

Inkling accepts text, images, and audio as input and returns text.

Inkling is served by 2 providers on OpenRouter: DeepInfra and Together. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Inkling was released on July 17, 2026.

More models from thinkingmachines

Inkling Small

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

Text524K context$0.45 / $1.20
Inkling Small

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

Text1.0M contextFree
Inkling

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

Text1.0M contextFree