Model Detail

Inkling-Small is a multimodal model with 133.0B parameters released by thinkingmachines. The model is registered under the image-text-to-text pipeline tag on Hugging Face, and supports text+image+audio->text inputs, distributed under the permissive apache-2.0 license.

Inkling-Small is priced at $0.45/M input tokens and $1.2/M output tokens. Operationally the model offers a 524K-token context window, which matters when sizing it for prompt-heavy or latency-sensitive workloads. At this input rate the model sits in the commodity tier and is suitable for high-volume workloads where per-call cost dominates the decision.

Inkling-Small ships with 133.0B parameters. Total weight footprint is approximately 266.0 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.

Inkling-Small is best fit for mixed text-and-image reasoning tasks such as document understanding, high-volume batch jobs where per-call cost dominates the budget, and long-context tasks such as full-codebase analysis or book-length summarization (524K tokens). Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.