Inkling 2 Small Official Specifications, Pricing & Benchmarks
Inkling 2 Small (inkling-2-small) by Thinking Machines, released 2026-11-05, featuring 1,048,576 context window, 943,718 max output tokens, and Text+Image input.
📋 Inkling 2 Small Official API & System Card Specifications
Verified against official Thinking Machines developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- inkling-2-small
- Release Date
- 2026-11-05
- Weight License
- Open-Weight (API Spec)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 1,049,000 tokens (1049K)
- Max Output Tokens
- 943,718 tokens
- Input Modalities
- Text + Image
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Open-Weight + Cloud API
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 0.3
- Cached Input / 1M
- $ 0.03 -90%
- Output / 1M Tokens
- $ 1
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Inkling 2 Small Full Benchmark Scorecard
11 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 2 items
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.
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.
🤖 Agents & Tools 4 items
BrowseComp is a benchmark comprising 1,266 questions that challenge AI agents to persistently navigate the internet in search of hard-to-find, entangled information.
GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.
AA-Briefcase is an Artificial Analysis evaluation of AI systems on professional knowledge-work tasks, reported 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.
👁️ Multimodal 2 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 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 1 items
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Inkling 2 Small
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Inkling 2 Small open-source or proprietary?
Inkling 2 Small (inkling-2-small) 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 2 Small?
Inkling 2 Small supports 1049K input context and 943,718 max output tokens, priced at $0.3/1M input ($0.03/1M cached) and $1/1M output.