NVIDIA

Inkling — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCENVIDIA
Input Cost
$1.0/1M
Output Cost
$4.0/1M
Context Window
1.0M
Max Output
16K
Accepts
text, image, audio

Inkling is an AI model by NVIDIA. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

General Benchmarks

AA Intelligence Index
25.533rd of 66

Artificial Analysis composite intelligence score across 10 sub-benchmarks

Artificial Analysis (via OpenRouter)

Coding Benchmarks

Design Arena ELO
118351st of 120

Human preference ELO for building things — websites, UI, games, charts, SVG

Design Arena (via OpenRouter)
AA Coding Index
52.142nd of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)
Website Arena ELO
122743rd of 108

Human preference ELO for building a working web page from a brief

Design Arena (via OpenRouter)

Reasoning Benchmarks

AA Agentic Index
24.330th of 70

Artificial Analysis composite score for multi-step tool-using tasks

Artificial Analysis (via OpenRouter)
GPQA Diamond
83.2%49th of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
67.3%57th of 93

Multi-turn service agent making tool calls under strict policy constraints

OpenRouter (measured)

Cost Benchmarks

Cached Input Cost
$0.1787th of 136

Cost per 1M cached input tokens — the price that actually applies to a long agent conversation

OpenRouter API
Input Cost
$1.0293rd of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$4.0297th of 413

Cost per 1M output tokens

OpenRouter API

Context Benchmarks

Context Length
1.0M18th of 451

Maximum context window size

OpenRouter API

Available from 21 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 7 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Nvidia$0$01.0M
Deep Infra$0.95$4.05$0.16524KSupported
Kilo Gateway$0.95$4.05$0.16524K
Baseten$1$4.051.0MSupported
Eden AI$1$4.05$0.17524K
Fireworks AI$1$4.05$0.171.0MSupported
Hugging Face$1$4.051.0MSupported
Merge Gateway$1$4.05$0.171.0M
NanoGPT$1$4.05$0.171.0M
Neon$1$4.05$0.171.0M
OpenRouter$1$4.05$0.171.0MSupported
Together AI$1$4.05$0.17524KSupported
Vercel AI Gateway$1$4.05$0.17256KSupported
Charm Hyper$1.0888$4.40964$0.1850961.0M
Modal$1.2$5$0.271.0M
Venice AI$1.25$5.0625$0.2125524K
Impossibl$1.87$4.68$0.37466K
LLMTR$1.87$4.68262K
Requesty$1.87$4.68$0.37466K
Abacus$3.74$9.36$0.748262K
Thinking Machines$3.74$9.36$0.748262K

Inkling — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Inkling — Frequently Asked Questions

How much does Inkling cost?

Inkling costs $1.0 per 1M input tokens and $4.0 per 1M output tokens. This is mid-range pricing for its capability level.

What is the context window of Inkling?

Inkling has a context window of 1.0M tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Inkling?

Inkling was created by NVIDIA. It is classified as a open source model in our catalogue.

Is Inkling open source?

Yes, Inkling is an open-source model. The model weights are publicly available for download and self-hosting.