Thinking Machines: Inkling
Thinking Machines
Thinking Machines: Inkling by Thinking Machines costs $1.00 per 1M input tokens and $4.05 per 1M output tokens, with a 524K-token context window.
Pricing
Input (per 1M tokens)
$1.00
Output (per 1M tokens)
$4.05
Cached input (per 1M)
$0.17
Specifications
- Provider
- Thinking Machines
- Context window
- 524K tokens
- Parameters
- —
- Released
- —
- Open weights
- —
- Frontier model
- No
- Hugging Face
- thinkingmachines/Inkling
Benchmarks
- GPQA Diamond
- 88.3
- LMArena WebDev Elo
- 1412.6
Speed & latency
Time to first token
1.46s
Output speed
356 tok/s
Fastest host: thinkingmachines (via vercel-ai-gateway).
Compare Thinking Machines: Inkling with…
Thinking Machines: Inkling vs GLM 5V Turbo$4.00/1MThinking Machines: Inkling vs Claude 3.5 Haiku$4.00/1MThinking Machines: Inkling vs GLM 5V Turbo Thinking$4.00/1MThinking Machines: Inkling vs Qwen2.5 VL 32B Instruct$4.20/1MThinking Machines: Inkling vs Muse Spark 1.1$4.25/1MThinking Machines: Inkling vs Muse Spark 1.2$4.25/1M
FAQ
How much does Thinking Machines: Inkling cost?
Thinking Machines: Inkling is priced at $1.00 per 1M input tokens and $4.05 per 1M output tokens. Output tokens cost more than input.
What is Thinking Machines: Inkling's context window?
Thinking Machines: Inkling supports a context window of 524K tokens — the maximum prompt plus response length it can handle in a single request.
Is Thinking Machines: Inkling open weight?
Open-weight status for Thinking Machines: Inkling is not recorded in our dataset.
Data as of 2026-10-15. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.