The request names a specific model, in-character-rp-12b-v0.1, which none of the candidate sources document. Since the name is a model rather than a product, the candidates are general AI and model-hosting platforms; the closest fits for running a 12B roleplay model are NVIDIA (via its NIM and Brev instances, which serve 12B-class models) and Replicate (which runs open-source models through a cloud API). The request does not say which platform, hardware, or hosting constraints apply, so the best
A question back: Do you want to self-host the model on your own GPU, or call it through a managed hosted API?
- 1
NVIDIA NIMnvidia.comverified and signed
NVIDIA's NIM service runs hosted AI models, including 12B-class instruct models, on Brev.dev GPU instances 1.
official:MCP server · NVIDIA CUDA Docs+84 community tools built for it
for agents: mistral-nemo-12b-instruct · mixtral-8x22b-instruct-v0.1 · nim
- 2
Replicatereplicate.comverified and signed
Replicate runs open-source machine learning models through a cloud API, so a 12B model could be called without managing GPUs 7.
+14 community tools built for it
for agents: fofr/0_1-webp · uthana/text-to-motion-vqvae-v1 · ideogram-ai/ideogram-character
- 3
OpenAI APIopenai.comverified and signed
The OpenAI API provides hosted language models through an official API and SDK, though it does not list this specific roleplay model 3.
official:MCP server · mcp-extensionsAPI · OpenAI APISDK · openailibrary · OpenAICLI · openai-whisper+177 community tools built for it
for agents: hatch-pet · openai · codex
Sources
- 1Brev.dev Consolebrev.nvidia.com · read 2026-10-29
- 3babysit-pr — openai/codexskills.sh · read 2026-10-29
- 7Replicate - Run AI with an APIreplicate.com · read 2026-10-29
For agents: the 10 actions behind this answer
mistral-nemo-12b-instruct · Mistral-Nemo-12B-Instruct verified and signed
Task: Mistral-Nemo-12B-Instruct
create-llms · create-llms verified and signed
Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/
hatch-pet · hatch-pet verified and signed
Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect o
add · gpt-rag-mcp found in code, not yet checked
unicode · ebcdic verified and signed
analyze_token_usage · docs found in code, not yet checked
Analyze character, word, and token usage of documentation content for a given model using a tiktoken-compatible tokenizer.
fofr/0_1-webp · fofr/0_1-webp verified and signed
Make pictures of an AI character named 0_1.webp
· Playwright website read, tools not yet checked
Web automation and testing for apps, scripts, and AI agents
radar-get-dns-as112-summary · Cloudflare API verified and signed
Get AS112 summary by dimension
clawchain-rpc-client · clawchain-rpc-client verified and signed
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
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.