Skip to content

thinkingmachines Inkling 2 Mini

Last updated: 10m ago

by thinkingmachines

High confidence

Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE). Its middle layers run three times with shared...

40
Overall Score276
Rank #177 of 452 in Coding(276 24h)
Top 39% · Methodology v3
Score Trend
40/100
14-day history
API Pricing
$0.1/M in
$0.4/M out
Context Window
1.0M
65.5K max output
1.0M token context
Released 2026-11-21
#177range #154-#200Top 39%
#1#452

Signal Overview

Capabilities83Pricing100Context96Recency100Output77

Score Breakdown

SignalStrengthWeightImpact
Capabilitiesjust now
83
30%+25.0
Pricingjust now
100
25%+24.9
Recencyjust now
100
15%+15.0
Context Windowjust now
96
15%+14.3
Output Capacityjust now
77
15%+11.5

Capabilities

Reasoning
Vision
Function Calling
JSON Mode
Streaming
Web Search
Image Output

Modalities

Input
text
image
Output
text

Recent thinkingmachines releases

View this model against the provider’s recent shipping cadence.

Reviews

Community and practitioner feedback adds real-world signal on top of benchmarks and pricing.

Reviews

Be the first to review this model

Share your experience with Inkling 2 Mini and help the community make better decisions.

Frequently Asked Questions

Inkling 2 Mini by thinkingmachines excels in the Coding category, where it ranks #177 with a composite score of 40/100. Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE). Its middle layers run three times with shared... It is particularly strong in areas highlighted by its top benchmark performance and adoption metrics, making it suitable for both individual developers and enterprise teams looking for a reliable coding solution.
Inkling 2 Mini is priced at $0.10 per million input tokens and $0.40 per million output tokens (USD). Contact the provider for volume discounts and enterprise pricing. Pricing is competitive within the coding category and reflects the model's quality-to-cost ratio.
In the Coding category, Inkling 2 Mini holds rank #177 out of 452 models tracked. Its quality rank is #177 and adoption rank is #177. You can use our comparison tool at /compare to see detailed side-by-side metrics with specific alternatives. Key differentiators include its composite scoring across benchmarks, community sentiment, and real-world adoption rates.
Inkling 2 Mini has been evaluated across 5 different signals. Its strongest areas include Capabilities (83/100), Pricing (100/100), Context Window (96/100). These scores are derived from industry-standard benchmarks, community ratings, and real-world performance metrics. The composite score of 40/100 reflects a weighted combination of all tracked signals.
Inkling 2 Mini is a paid model, though some providers may offer trial credits or limited free tiers for evaluation. Check thinkingmachines's website for current free tier availability and promotional offers.
Inkling 2 Mini supports a 1,049K token context window (1,048,576 tokens total). That translates to roughly 786,432 words in a single prompt. This is large enough to process entire codebases, research papers, or long conversation histories in one shot.
Inkling 2 Mini can generate up to 66K output tokens (65,536 tokens) per response. That is roughly 49,152 words. This is enough for generating complete code files, detailed reports, or long-form content in a single response.
Inkling 2 Mini supports image understanding (vision), function/tool calling, structured JSON output, extended reasoning/chain-of-thought, streaming responses. Function calling lets you integrate it with external APIs and tools programmatically. Vision support means it can analyze images, screenshots, and diagrams alongside text. These capabilities determine which workflows and integrations the model can handle natively.
Yes, Inkling 2 Mini is an open-source model. You can download the weights, run it locally, fine-tune it for your use case, or deploy it on your own infrastructure. Many cloud providers also offer hosted versions if you prefer not to manage the infrastructure yourself. Self-hosting gives you full control over data privacy and eliminates per-token API costs.
Inkling 2 Mini was developed by thinkingmachines. It was released on November 21, 2026. You can access it through thinkingmachines's API or download the model weights directly. Check our provider page for all models from thinkingmachines and how they compare against each other.
Pick Inkling 2 Mini when you need a budget-friendly option for high-volume, simpler tasks where you prioritize cost over peak performance. If your task is straightforward text completion or classification, a cheaper model might give you 90% of the quality at a fraction of the price. Run a quick benchmark on your actual use case before committing.
You can access Inkling 2 Mini through thinkingmachines's API using standard HTTP requests or their official SDK. Most providers support OpenAI-compatible endpoints, so switching between models often requires changing just the model name in your API call. Streaming is supported for real-time token-by-token output. For production use, implement proper error handling, rate limiting, and cost monitoring.

Key Info

CategoryCoding
Max Output65.5K tokens
LicenseOpen Source
Statusstable
HuggingFaceInkling-2-Mini
Data updated: Nov 21, 2026

Pricing Tools

Pricingper 1M tokens
Best value
95% cheaper than category average
Input
$0.10
-94% vs avg
Output
$0.40
-95% vs avg

Cost Estimator

Input: 70%Output: 30%
Est. monthly cost$1.90
Category average$36.29

You save $34.39/month vs category average

Access & Availability

Hosted APIAvailable
PlaygroundAvailable
Open weightsYes
Hugging FaceWeights

Why This Rank

+Capabilities
+Pricing
+Recency
+Context Window

Similar Models

View all