The request names a specific fine-tuned model (FortranCodeGen-3B-SynthData-onlysft), which is not among the candidate products, so no product here hosts or serves that model directly. The candidates that offer fine-tuning or model hosting for a custom model are OpenAI's fine-tuning API 17 and Cloudflare's Workers AI finetune creation 14; Mistral 1 and NVIDIA's synthetic data tooling 13 are also relevant to training or customizing open-weight models.
A question back: Which platform or infrastructure is the FortranCodeGen-3B-SynthData-onlysft model stored on, and do you need to run it for inference or to fine-tune further?
- 1
OpenAI APIopenai.comverified and signed
The fine-tuning API creates a job that fine-tunes a specified model from a given dataset, and it also lets you retrieve job status and delete fine-tuned models 17.
official:API · OpenAI APISDK · openailibrary · OpenAIskill · babysit-prSDK · openai+163 community tools built for it
for agents: createFineTune · retrieveFineTune · deleteModel
- 2
Cloudflare Workers AIcloudflare.comverified and signed
The Workers AI finetune action creates a new finetune, and model search helps find models to run on the platform 14.
official:MCP server · @cloudflare/mcp-server-cloudflareCLI · cloudflaredskill · cloudflareskill · durable-objects+259 community tools built for it
for agents: workers-ai-create-finetune · workers-ai-search-model · stream-subtitles/-captions-generate-caption-or-subtitle-for-language
- 3
Mistralmistral.aiverified and signed
Open-weight models that can be customized with Forge, deployed with Studio, and run on-prem, in your VPC, or in Mistral's cloud 1.
+297 community tools built for it
for agents: coding-assistant · llm · ai
- 4
NVIDIA NeMo Data Designernvidia.comverified and signed
The new-sdg action implements a synthetic data generator using NeMo Data Designer, which suits building the synthetic training data behind a model like this 13.
+81 community tools built for it
for agents: new-sdg · nv-generate-vae-finetune · nemo-data-designer-plugin
Sources
- 1Mistral | #1 in Sovereign AI: Frontier Open Models You Ownmistral.ai · read 2026-10-30
- 3Brev.dev Consolebrev.nvidia.com · read 2026-10-29
- 4Cloudflare: Build for the agent eracloudflare.com · read 2026-10-29
- 13new-sdg: declares "new-sdg" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14Cloudflare API: declares "workers-ai-create-finetune" (the record we read and signed)unfragile.ai · read 2026-10-24
- 17OpenAI API: declares "createFineTune" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
coding-assistant · mistral-vibe verified and signed
code-exemplars-blueprint-generator · code-exemplars-blueprint-generator verified and signed
Technology-agnostic prompt generator that creates customizable AI prompts for scanning codebases and identifying high-quality code exemplars. Supports multiple programming languages (.NET, Java, JavaScript, TypeScript, React, Angular, Python) with configurable analysis depth, categorization methods,
new-sdg · new-sdg verified and signed
Implement a new synthetic data generator using NeMo Data Designer by defining its configuration and executing a preview job.
workers-ai-create-finetune · Cloudflare API verified and signed
Create a new Finetune
ask-ai · Groq (Activepieces) verified and signed
Ask AI — Send a question or instruction to a Groq model and get a text reply.
openapi-generator · @daytonaio/api-client verified and signed
createFineTune · OpenAI API verified and signed
Creates a job that fine-tunes a specified model from a given dataset. Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete. [Learn m
pr-review · pr-review verified and signed
Review Github pull requests
pydantic · pydantic verified and signed
Pydantic is a Python data validation and serialization library, based on type hints. Use this skill whenever you need to do relatively complex data modeling using Pydantic, e.g. when adding constraints, defining a model hierarchy with subclasses, etc.
data-science · lancedb verified and signed
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.