Unfragile

The request names a specific model, Llama-3.3-8B-Instruct-128K, which none of the candidate sources list directly. The closest match is IBM's Granite-3.3-8B-Instruct, a 128K-context 8B instruction model, offered as an API on Replicate 15. OpenRouter offers a unified API that can route text-to-text requests to many hosted models 48, and Brev.dev offers Llama3-8B-Instruct tasks 26.

1
Replicatereplicate.comverified and signed
Runs open-source machine learning models through a cloud API, including IBM's Granite-3.3-8B-Instruct, a 128K-context 8B instruction model 15.
Website Docs Pricing Get started
for agents: ibm-granite/granite-3.3-8b-instruct
2
OpenRouteropenrouter.aiverified and signed
A unified API that routes text-to-text, tool-calling and structured-output requests to many hosted models from multiple providers 48.
Website Docs Pricing Get started
for agents: text->text · tool-calling · structured-outputs
3
Brev.dev Consolenvidia.comverified and signed
Provides instances on which Llama3-8B-Instruct tasks can be run, though the source does not name the exact Llama-3.3 128K variant 26.
Website Docs Pricing Get started
for agents: llama3-8b-instruct · llama3 · automotive-/-transportation

Sources

1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
2Brev.dev Consolebrev.nvidia.com · read 2026-10-29
4OpenRouteropenrouter.ai · read 2026-10-29
5ibm-granite/granite-3.3-8b-instruct: declares "ibm-granite/granite-3.3-8b-instruct" (the record we read and signed)unfragile.ai · read 2026-10-24
6Meta/Llama3-8b-instruct: declares "llama3-8b-instruct" (the record we read and signed)unfragile.ai · read 2026-10-24
8Meta: Llama 3.1 8B Instruct: declares "text->text" (the record we read and signed)unfragile.ai · read 2026-10-24

For agents: the 10 actions behind this answer

ibm-granite/granite-3.3-8b-instruct · ibm-granite/granite-3.3-8b-instruct verified and signed
Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.
meta/meta-llama-3-8b-instruct · meta/meta-llama-3-8b-instruct verified and signed
An 8 billion parameter language model from Meta, fine tuned for chat completions
ibm-granite/granite-3.2-8b-instruct · ibm-granite/granite-3.2-8b-instruct verified and signed
Granite-3.2-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for reasoning and instruction-following capabilities.
meta/meta-llama-3-70b-instruct · meta/meta-llama-3-70b-instruct verified and signed
A 70 billion parameter language model from Meta, fine tuned for chat completions
meta/llama-4-maverick-instruct · meta/llama-4-maverick-instruct verified and signed
A 17 billion parameter model with 128 experts
ibm-granite/granite-3.1-8b-instruct · ibm-granite/granite-3.1-8b-instruct verified and signed
Granite-3.1-8B-Instruct is a lightweight and open-source 8B parameter model is designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.
microsoft/phi-3-mini-128k-instruct · microsoft/phi-3-mini-128k-instruct verified and signed
Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets
ibm-granite/granite-8b-code-instruct-128k · ibm-granite/granite-8b-code-instruct-128k verified and signed
Join the Granite community where you can find numerous recipe workbooks to help you get started with a wide variety of use cases using this model. https://github.com/ibm-granite-community
llama3-8b-instruct · Meta/Llama3-8b-instruct verified and signed
Task: Llama3-8b-instruct
llama3.1-8b-instruct · Llama-3.1-8B-Instruct verified and signed
Task: Llama3.1-8b-instruct

Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.