Thinking Machines: Inkling Small
Thinking Machines
Thinking Machines: Inkling Small by Thinking Machines costs $0.45 per 1M input tokens and $1.20 per 1M output tokens, with a 524K-token context window.
Pricing
Input (per 1M tokens)
$0.45
Output (per 1M tokens)
$1.20
Cached input (per 1M)
$0.10
Specifications
- Provider
- Thinking Machines
- Context window
- 524K tokens
- Parameters
- —
- Released
- —
- Open weights
- —
- Frontier model
- No
- Hugging Face
- thinkingmachines/Inkling-Small
Benchmarks
- GPQA Diamond
- 88.5
- LMArena Vision Elo
- 1235.3
- LMArena WebDev Elo
- 1408.4
Speed & latency
Time to first token
1.51s
Output speed
324 tok/s
Fastest host: thinkingmachines (via vercel-ai-gateway).
Compare Thinking Machines: Inkling Small with…
Thinking Machines: Inkling Small vs MiniMax M2.7$1.20/1MThinking Machines: Inkling Small vs MiniMax M3$1.20/1MThinking Machines: Inkling Small vs GPT-5.6 Luna$1.20/1MThinking Machines: Inkling Small vs Qwen3 Next 80B A3B Thinking$1.20/1MThinking Machines: Inkling Small vs MiniMax M3 Thinking$1.20/1MThinking Machines: Inkling Small vs KAT-Coder-Pro V1$1.20/1M
FAQ
How much does Thinking Machines: Inkling Small cost?
Thinking Machines: Inkling Small is priced at $0.45 per 1M input tokens and $1.20 per 1M output tokens. Output tokens cost more than input.
What is Thinking Machines: Inkling Small's context window?
Thinking Machines: Inkling Small supports a context window of 524K tokens — the maximum prompt plus response length it can handle in a single request.
Is Thinking Machines: Inkling Small open weight?
Open-weight status for Thinking Machines: Inkling Small 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.