LLM Pricing

← All Models

Thinking Machines: Inkling

thinkingmachines · Inkling

Input Price $1.00 per million tokens NT$32.0
Output Price $4.05 per million tokens NT$130
Context Window 1.05M tokens
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

Thinking Machines: Inkling is a large language model API from thinkingmachines, part of its Inkling model family. Priced at $1.00 per million input tokens and $4.05 per million output tokens, it occupies the mid-range, balancing capability against running cost. Output tokens cost about 4× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. An exceptionally large 1.05M-token context window (≈1,573 pages of text) means entire repositories or document collections can be processed without chunking. Beyond plain text it also accepts Image, Audio input, so it can be applied to multimodal tasks rather than text alone. On Artificial Analysis's Intelligence Index it scores 41 (B grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.

Dimension Unit Price (USD) Price (TWD) Effective From
Input per 1M tokens $1.00 NT$32.0
Output per 1M tokens $4.05 NT$130
Cached Input per 1M tokens $0.170 NT$5.4

Provider
thinkingmachines
Model Family
Inkling
Version String
thinkingmachines/inkling
Status
Active
Modality
Text, Image, Audio
Context Window
1,048,576 tokens
Output Limit
— tokens

Index Metrics

Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis

Agentic Index 32 C Measured: 2026-07-25
Coding Index 52 A Measured: 2026-07-25
Intelligence Index 41 B Measured: 2026-07-25

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 63.3% B Measured: 2026-07-25
GPQA Diamond 87.2% S Measured: 2026-07-25
HLE 29.7% A Measured: 2026-07-25
HLE 29.7% A Measured: 2026-07-25
MMMU Pro 73.5% B Measured: 2026-07-25
Non-Hallucination 36.9% Measured: 2026-07-25
Omniscience Accuracy 40.0% Measured: 2026-07-25
SciCode 46.1% A Measured: 2026-07-25

Performance Metrics

Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis

First Token Latency 1.8s Measured: 2026-07-25
Output Speed 69 t/s Measured: 2026-07-25
Response Time 38.1s Measured: 2026-07-25

90-Day Price Trend

Input / Output price (USD per 1M tokens)

Past 90 days of records; every price change is shown here

Date Dimension Price (USD) Source
Cached Input $0.170 OpenRouter
Output $4.05 OpenRouter
Input $1.00 OpenRouter
Cached Input $0.170 OpenRouter
Output $4.05 OpenRouter
Input $1.00 OpenRouter
Cached Input $0.170 OpenRouter
Output $4.05 OpenRouter
Input $1.00 OpenRouter
Cached Input $0.170 OpenRouter
Output $4.05 OpenRouter
Input $1.00 OpenRouter
Cached Input $0.170 OpenRouter
Output $4.05 OpenRouter
Input $1.00 OpenRouter
Cached Input $0.170 OpenRouter
Output $4.05 OpenRouter
Input $1.00 OpenRouter
Cached Input $0.170 OpenRouter
Output $4.05 OpenRouter
Input $1.00 OpenRouter
Cached Input $0.170 OpenRouter
Output $4.05 OpenRouter
Input $1.00 OpenRouter

Key Insights

Key data points from this page for quick reference and citation.

  • Thinking Machines: Inkling Input price: $1/M tokens
  • Thinking Machines: Inkling Output price: $4.05/M tokens
  • Context window: 1,048,576 tokens
  • Provider: thinkingmachines
  • Model family: Inkling
  • Modalities: Text, Image, Audio
  • Data source: OpenRouter, updated daily