Inkling Official Specifications, Pricing & Benchmarks
Inkling (inkling) by Thinking Machines, released 2026-07-15, featuring 524,288 context window, 471,859 max output tokens, and Text+Image+Audio input.
📋 Inkling Official API & System Card Specifications
Verified against official Thinking Machines developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- inkling
- Release Date
- 2026-07-15
- Weight License
- Open-Weight (API Spec)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- 部分支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 524,000 tokens (524K)
- Max Output Tokens
- 471,859 tokens
- Input Modalities
- Text + Image + Audio
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Open-Weight + Cloud API
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 1
- Cached Input / 1M
- $ 0.17 -83%
- Output / 1M Tokens
- $ 4.05
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Inkling Full Benchmark Scorecard
16 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 3 items
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.
Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.
🤖 Agents & Tools 2 items
GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.
τ³-Bench banking domain evaluates agentic models on multi-turn, tool-using customer-support scenarios in a simulated retail banking environment.
📐 Math 3 items
All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999.
Text-only Humanity's Last Exam variant evaluated with tool use enabled.
Text-only Humanity's Last Exam variant evaluated without tool use.
👁️ Multimodal 3 items
CharXiv-R is the reasoning component of the CharXiv benchmark, focusing on complex reasoning questions that require synthesizing information across visual chart elements.
A massive multi-task audio understanding and reasoning benchmark comprising 10,000 carefully curated audio clips paired with human-annotated natural language questions spanning speech, environmental sounds, and music.
A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings.
🧠 Reasoning & Science 4 items
VoiceBench is the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants, evaluating capabilities including general knowledge, instruction-following, reasoning, and safety using both synthetic and real spoken instruction data with diverse…
A lightweight version of Global MMLU benchmark that evaluates language models across multiple languages while addressing cultural and linguistic biases in multilingual evaluation.
SimpleQA Verified is a curated, reliability-focused subset of SimpleQA that addresses label noise and redundancy in the original benchmark, measuring short-form parametric factual accuracy of large language models on fact-seeking questions with single, indisputable answers.
AA-Omniscience Index is Artificial Analysis's knowledge-reliability metric. It rewards correct answers, penalizes hallucinations, and does not penalize abstention. Scores range from -100 to 100, where 0 means as many correct as incorrect answers.
📚 Knowledge & General 1 items
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Inkling
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Inkling open-source or proprietary?
Inkling (inkling) is a proprietary commercial model by Thinking Machines. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Inkling?
Inkling supports 524K input context and 471,859 max output tokens, priced at $1/1M input ($0.17/1M cached) and $4.05/1M output.