thinkingmachines/inkling:batchInkling (batch) is Thinking Machines’s AI model, released Jul 17, 2026. It costs $1/M input and $4.05/M output tokens, and handles a 524K-token context window.
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
Scores on standardized evaluations. Higher is better — and rank shows where Inkling (batch) lands among all models tracked on Model Beat.
No standardized benchmark scores from Epoch AI yet — common for very recent, image, or niche models. Scores appear here once published.
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
Inkling (batch) is an AI model developed by Thinking Machines, released Jul 17, 2026.
Inkling (batch) is served from $1 per million input tokens and $4.05 per million output tokens (cheapest credible provider on OpenRouter: Together).
Inkling (batch) supports a context window of up to 524K tokens.
Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Aug 21, 2026.