The AI arena is free today

Open Superagent
Thinking Machines LabReleased on Nov 20, 2026

Inkling 2 Mini: Benchmarks, Pricing & Context Window

Inkling 2 Mini is a language model from Thinking Machines Lab, released in November 2026, with multimodal input, a 1M-token context window, and pricing from $0.150/M input, $0.015/M cached input, $0.500/M output.

Inkling 2 Mini is Thinking Machines Lab's small open-weight multimodal model, released 2026-11-20 under Apache 2.0. It is a looped Mixture-of-Experts transformer (26.4B total / 3.4B active parameters; the middle 12 of 24 layers run three

Input
TextImage
Output
Text

Inkling 2 Mini benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Inkling 2 Mini across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Inkling 2 Mini holds up as conversations get longer.

Quality Tracker

Inkling 2 Mini Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Fri Nov 20 2026
Notice missing or incorrect data?

Inkling 2 Mini pricing

Providers

Inkling 2 Mini starts at $0.150 per million input tokens and $0.500 per million output tokens via Thinking Machines Lab. Reused prompt prefixes cost $0.0150 per million cached input tokens.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
Thinking Machines Lab logoThinking Machines Lab
$0.150$0.0150$0.5001.0M/—
—
—
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Inkling 2 Mini model size

Inkling 2 Mini has 26.4 billion parameters. See how it compares to other models in the same parameter range.

Parameters
26.4BMoE
Medium (10–30B)
26.4B
1B7B70B405B

Inkling 2 Mini context window

Input and output token limits for Inkling 2 Mini, plus how it ranks on long-context understanding.

Input
1Mtokens
≈ 1.5k pages of text
1M
8K128K1M

Try now

huggle
Inkling 2 Miniin Huggle

Make it with
Inkling 2 Mini.

Inkling 2 Mini

Inkling 2 Mini latency

Inkling 2 Mini time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Inkling 2 Mini examples

Recent arena outputs from Inkling 2 Mini, picked from the highest-ranked matchups.

Inkling 2 Mini license

Inkling 2 Mini is released under the Apache 2.0 license, which permits commercial use, has 26.4B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
26.4B

Apache License 2.0 - allows commercial use

Inkling 2 Mini resources

Official sources for Inkling 2 Mini: provider documentation, official playground, official launch post, source repository.

Inkling 2 Mini vs other models

The most-compared alternatives to Inkling 2 Mini are GLM-5.1, MiMo-V2.5-Pro, GPT-5.2 Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Inkling 2 Mini

Models ranked just above and below Inkling 2 Mini by LLM Stats score.

 

GLM-5.1

Score pending
 

MiMo-V2.5-Pro

Score pending
 

GPT-5.2 Pro

Score pending
 

GPT-5.2

Score pending
 

Claude Opus 4.7

Score pending
 

Gemini 3.6 Flash

Score pending

FAQ

Common questions about Inkling 2 Mini.

When was Inkling 2 Mini released?

Inkling 2 Mini was released on November 20, 2026 by thinking-machines. This is the official Inkling 2 Mini release date tracked on LLM Stats.

How much does Inkling 2 Mini cost?

Inkling 2 Mini pricing starts at $0.15 per million input tokens, $0.01 per million cached input tokens, $0.50 per million output tokens via Thinking Machines Lab, the lowest price among tracked providers.

How big is Inkling 2 Mini?

Inkling 2 Mini has 26.4 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Inkling 2 Mini?

Inkling 2 Mini was created by thinking-machines.

What is the license for Inkling 2 Mini?

Inkling 2 Mini is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Is Inkling 2 Mini multimodal?

Yes, Inkling 2 Mini is multimodal and can accept both text and images as input.

Where can I use Inkling 2 Mini?

Inkling 2 Mini is available through 1 provider including Thinking Machines Lab.

Where is the Inkling 2 Mini paper or technical report?

Inkling 2 Mini has a paper or technical report available at https://thinkingmachines.ai/news/inkling-2-mini/. Use that source for architecture, training, release and evaluation details.

What models should I compare Inkling 2 Mini against?

Common Inkling 2 Mini comparisons include Inkling 2 Mini vs GLM-5.1, Inkling 2 Mini vs MiMo-V2.5-Pro, Inkling 2 Mini vs GPT-5.2 Pro. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.