Home / Inference APIs / Bespoke Nimble
Icon for Bespoke Nimble

Bespoke Nimble

Open Source Free Trial

Hosted and open decision models that return a probability for every answer

Nimble is Bespoke Labs' decision model. Send the state and the answers you allow (choices or true/false), and it returns the answer and a probability for every option. It is built on Qwen3.8-27B for the current hosted version, nimble-v4-max.

The hosted API charges $0.04 per 1M input tokens from prepaid credit, output free, and new accounts get $1 of credit. Open weights and the training data and recipe are on Hugging Face and GitHub; the 27B weights are licensed CC BY-NC 4.0, which bars commercial use.

Pricing: Per token usage

Hosting Cloud + Self-hosted
Pricing Usage Based, $0.04 per 1M input tokens, output free
License Apache-2.0 (9B), CC BY-NC 4.0 (27B)
Screenshot of Bespoke Nimble webpage

Bespoke Nimble prices by model

Per 1M tokens, read off Bespoke Nimble's own pricing page on the date shown.

Model Input / 1M Cached / 1M Output / 1M Checked Notes
Nimble-v4-max $0.04 – $0.00 25 Oct 2026 Prepaid credit; new accounts get $1. Output tokens are free.

Bespoke Nimble Alternatives

Explore 164 products in the Inference APIs category. View all Bespoke Nimble alternatives.

Strom icon
Celeris-1 Decision icon
Confidential AI icon

Confidential AI

Private LLM inference and GPU VMs that run inside hardware-encrypted enclaves
From DeepSeek V4.1 Flash at $0.30 in / $1.20 out per 1M tokens; GPU VMs from $6.50 per GPU-hour
Orion AI Factory icon

Orion AI Factory

NVIDIA B200 GPU cloud and token-priced inference hosted in Serbia
Free Trial From From EUR 3.00 per hour (0.25x B200, 48 GB); billed in RSD
LowRouter icon

LowRouter

LLM router hosted in France, with a carbon figure on every call
Free Trial From No per-token markup; 5.5% + EUR 0.30 per top-up (EUR 5 minimum)

View all Inference APIs tools ≫

Work on Bespoke Nimble? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →