SiteList review score
Clear developer guides and efficient navigation support API integrators. Mobile loading and public detail on cost, quotas, reliability, and model coverage need work.
Reviewed on Oct 7, 2026
Codexhot
codexhot.com
Unclaimed listingWhat it does
Codexhot is a web-based, usage-billed AI API aggregation service. It provides one API key for connected GPT models, routes requests through model groups with different default billing multipliers, and documents API, SDK, migration, pricing, and error-diagnosis workflows.
Two ratings
Verified user rating
—
No verified reviews yet — the evidence locker is empty.
Screenshots
Captured during our latest review on Oct 7, 2026
Pricing details
Usage pricing is based on model tokens and group multipliers. For gpt-6-luna, the site states approximately $0.002 per million input tokens and $0.01 per million output tokens in GO before the illustrated short-request calculation; GO, PLUS, and PRO default multipliers are 0.02, 0.07, and 0.10. Vouchers start at RMB 5. Billed usage.
| Plan | Price | Details |
|---|---|---|
| GPT GO | usage per 0.02 multiplier | Usage billing at the default 2% multiplier on the site's model base pricing. Listed models include gpt-6-luna, gpt-5.6-terra, and gpt-5.6-luna View source |
| GPT PLUS | usage per 0.07 multiplier | Usage billing at the default 7% multiplier on the site's model base pricing. The page lists eight currently available models View source |
| GPT PRO | usage per 0.10 multiplier | Usage billing at the default 10% multiplier on the site's model base pricing. The page lists gpt-6-luna as currently available View source |
Key features
Single API key
access
Provides one API key for calling connected AI models without separate applications.
Smart routing
routing
Routes requests across upstream accounts with automatic failover.
Usage-based billing
billing
Charges according to model usage with quota limits and team-consumption visibility.
Responses API support
API
The guide documents creating a key and sending a first request with the Responses API.
Python and Node.js examples
SDK
The guide documents Base URL and key configuration for Python and Node.js SDK requests.
Chat Completions migration
migration
The migration guide documents retaining the messages structure while replacing the Base URL, key, and model name.
Messages API and SSE examples
API
The guide documents basic text and SSE requests using the Messages API.
Error diagnosis guide
troubleshooting
The guide maps 401, 403, 404, 429, and 503 responses to checks for keys, groups, models, quotas, concurrency, and upstream limits.
Who it’s for
Calling multiple AI models
Use one API key to call connected AI models through an aggregation service.
Python or Node.js application integration
Configure a Base URL and key to send basic text requests from Python or Node.js applications.
Migrating an existing Chat Completions project
Retain an existing messages request structure while changing the Base URL, key, and model name.
Diagnosing API request failures
Use response codes and error content to investigate key, group, model, quota, concurrency, and upstream-limit issues.
Integrations
Python
developer tools
The documentation provides Python SDK setup examples for the GPT API.
Node.js
developer tools
The documentation provides Node.js SDK setup examples for the GPT API.
GitHub
developer tools
The homepage links to a GitHub repository for the project.
Buyer questions
Questions buyers actually ask
Is the GO 2% multiplier a fixed price per request?
No. It is a default group multiplier; the actual charge depends on model pricing, input and output tokens, cache use, and the billing rules for the request.
How can I confirm that my key can call a target model?
Check the key's selected group in the console, then send a small request using the integration guide. A model outside that group's whitelist should not be treated as available.
Why can a health check succeed while inference fails?
A health check confirms that the service entry point responds. Key status, group whitelist, account balance, and concurrency limits are evaluated for the specific request.
What should I provide when contacting support?
Provide the request time, model, selected group, HTTP status, and error code; do not provide the complete API key.
Product FAQ information · View source
The expert review
Codexhot scores 66/100 as a pay-as-you-go AI API service for developers and API integrators, with strong usability fundamentals across the sampled public surface. Its most material weaknesses are slow mobile loading and incomplete public clarity around cost, quotas, reliability, and model coverage.
66/100: fair product with strong usability and clear next fixes
Verified user reviews
0 verifiedNo reviews yet. The evidence locker is empty.
Reviews from verified users appear here once approved.
Reviews are from the SiteList community. Some reviewers received incentives — disclosed in the review, always. The verdict is never for sale.
Scores across 13 dimensions
Brand & experience
Performance
Content & editorial
Trust & decision surfaces
Search & discoverability
Docs & measurement
- Domain
- codexhot.com
- Category
- Model APIs & aggregators
- Pricing
- Usage-based · $0–$0.01
- Platforms
- web, api
- Founded
- 2026
- Last checked
- Oct 7, 2026
- Public dimensions
- 13
Compared on SiteList
Similar tools
Home
Pendra screenshot 1 of 4: Home
Pendra
Score 87 out of 100 — Strongpendra.ai
Pendra is a managed inference platform providing chat, embeddings, image generation, and audio transcription for open-weight models on sovereign infrastructure.
Home
Llmwise screenshot 1 of 4: Home
Llmwise
Score 86 out of 100 — Strongllmwise.ai
Auto-first AI routing platform that routes prompts across multiple models (GPT, Claude, Gemini, DeepSeek) to cheaper defaults, with transparent per-response costs, Compare/Blend/Judge workflows, and an OpenAI-compatible API.
Home
Lettib screenshot 1 of 4: Home
Lettib
Score 85 out of 100 — Stronglettib.com
LettiB is a web AI workspace that compares ChatGPT, Claude, Gemini, and other model answers side by side, then synthesizes them into one merged response.
Home
Assemblyai screenshot 1 of 4: Home
Assemblyai
Score 82 out of 100 — Strongassemblyai.com
AssemblyAI provides speech AI models and APIs for transcribing speech to text and extracting insights from voice data.