[Feature] Add FPT AI Factory as a provider
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 25/100
- Issue type
- Feature
- Clarity
- Clearly specified
- Activity status
- Stale
- Tech stack
- typescript
- Domain
- ai
Research direction
Review implementation #3735 and the proposed providers/fpt-ai-factory/ files first. Verify the provider.toml, square logo.svg, and eight model entries against the public GET /v1/models catalog, including costs, limits, and the empty reasoning_options setting; done means the provider is represented accurately and uses FPT_API_KEY.
Written by the indexing model from the issue text.
Description
Provider
FPT AI Factory — OpenAI-compatible gateway at https://mkp-api.fptcloud.com/v1, serving LLM/VLM models on NVIDIA GB300 nodes.
Why
FPT AI Factory is a first-party Vietnamese cloud AI marketplace not yet in models.dev. It exposes a public catalog endpoint (GET /v1/models) with pricing and limits, making it straightforward to keep in sync.
Scope
Add providers/fpt-ai-factory/ with provider.toml, a square logo.svg, and 8 model entries (DeepSeek-V4-Flash, Qwen3.6-27B, GLM-5.2, gpt-oss-120b/20b, gemma-4-26B/31B, Llama-3.3-70B). Costs/limits sourced from the live catalog; reasoning_options = [] (gateway exposes no reasoning control).
Implementation
Implemented in #3735.
Env
FPT_API_KEY — keys at https://marketplace.fptcloud.com/ · docs https://ai-docs.fptcloud.com/
- Dominant language
- TypeScript
- Stars
- 7.2k
- Forks
- 1.8k
- Avg merge
- 1h 12m
- Merged PRs (30d)
- 911
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from anomalyco/models.dev
-
Context limits for DeepSeek V4 models should be 1,048,576 instead of 1,000,000Possibly taken @github-actions claimed this 10 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
anomalyco/models.dev#8534 ·
Maintainers usually reply within 1 day
-
opencode[-go] muse-spark-1.3-contributor* max level tested working but shows null in models.devOpen
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
anomalyco/models.dev#8342 · 2 comments ·
Maintainers usually reply within 1 day
-
Amazon as Lab ?Open
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
anomalyco/models.dev#8163 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
anomalyco/models.dev#8058 · 1 comment ·
Maintainers usually reply within 1 day
-
Alibaba Token Plan providers point at the undocumented region-scoped hostsPossibly taken @oliver-mee claimed this 17 days ago. Open
Difficulty 1/5 Under an hour Newbie friendliness 85/100
anomalyco/models.dev#7974 ·
Maintainers usually reply within 1 day
All issues in anomalyco/models.dev
Similar issues
-
by: ai-assisted frontend good-for: new-member spike
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
Northeastern-Electric-Racing/Argos#847 ·
Maintainers usually reply within 4 days
-
Difficulty 1/5 1-3 hours Newbie friendliness 84/100
SignalK/freeboard-sk#990 ·
Maintainers usually reply within 1 day
-
[missing-inheritance] audit review (1 preset)Possibly taken @github-actions claimed this today. Open
Difficulty 1/5 Under an hour Newbie friendliness 82/100
osmberlin/tagging-schema-browser#363 · 1 comment ·
Maintainers usually reply within 1 day
-
enhancement
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
Albert-Weasker/niubigeo#205 ·
Maintainers usually reply within 1 day
-
area/frontend area/v2 kind/bug priority/needs-triage
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
kubeflow/notebooks#1498 · 1 comment ·
Maintainers usually reply within 1 day