Upstream Supply Network
Internal sourcing and routing view that powers our unified AI API service
O
OpenRouter
🇺🇸CommercialPaid
Unified API for 200+ AI models with competitive pricing and smart routing
Relay / aggregation layerProcurement guardedUse with guardrailsLive Verified
Operating model
Relay / aggregation layer
Procurement
Procurement guarded
Recommendation
Strong option for cross-model routing and experimentation, but do not collapse it into direct first-party procurement in production architecture.
overdue · 14d cadence
Live Verification
All required official source types are currently reachable from this verification environment.
4 verified · 0 blocked · 0 broken
official baseline
Models:
claude-3-opusclaude-3-sonnetclaude-3-haiku+5
C
ChatAnywhere
🇨🇳Public WelfareFree
Free GPT API service with rate limits
Relay / aggregation layerProcurement blockedNeeds verificationPartial
Operating model
Relay / aggregation layer
Procurement
Procurement blocked
Recommendation
Useful for testing and lightweight internal usage, but the official user agreement and public project notes are too restrictive for formal production procurement. Current live verification is degraded because required official source types are missing or broken: terms.
overdue · 7d cadence
Live Verification
Some required official source types are live-verified, while others are blocked or broken and need follow-up.
3 verified · 0 blocked · 0 broken
Blocking factors
Required official source types are currently broken or missing in live verification: terms.
official baseline
Quick Start
$npx ccjk -p chatanywhere
DeepSeek is a Chinese AI company that has developed powerful language models with exceptional coding capabilities and highly competitive pricing. The DeepSeek-V3 chat model and DeepSeek-Coder series offer performance comparable to GPT-4 at a fraction of the cost, making them attractive alternatives for developers and businesses prioritizing cost-efficiency. DeepSeek models excel at code generation, mathematical reasoning, and Chinese language understanding, with official APIs supporting both Chinese and English. The platform's aggressive pricing strategy positions it as one of the most cost-effective solutions for production AI deployments.
Direct model providerProcurement readyFirst-party preferredLive Verified
Operating model
Direct model provider
Procurement
Procurement ready
Recommendation
Use DeepSeek directly when you want the simplest path to DeepSeek models without a relay layer sitting in front of them.
overdue · 30d cadence
Live Verification
All required official source types are currently reachable from this verification environment.
3 verified · 0 blocked · 0 broken
official baseline
Models:
deepseek-chatdeepseek-coderdeepseek-r1+1
Groq is an ultra-fast AI inference platform that leverages custom-designed LPU (Language Processing Unit) hardware to deliver unprecedented inference speeds for open-source LLMs. The platform provides free access to popular models like Llama 2, Mixtral, and Gemma through an OpenAI-compatible API, making it easy for developers to integrate blazing-fast AI capabilities into their applications. Groq's custom hardware enables token generation speeds up to 10x faster than traditional GPUs, with a generous free tier and competitive pay-per-use pricing for production workloads requiring maximum performance.
Cloud platform accessProcurement guardedRecommendedPartial
Operating model
Cloud platform access
Procurement
Procurement guarded
Recommendation
Good production candidate when low-latency managed inference on GroqCloud matters more than direct control over every open model host. Live verification is currently partial because some required official source types are blocked from this environment: documentation, pricing.
overdue · 21d cadence
Live Verification
Some required official source types are live-verified, while others are blocked or broken and need follow-up.
2 verified · 2 blocked · 0 broken
official baseline
Models:
llama-3.3-70bmixtral-8x7bgemma-7b
Leading AI research company offering GPT-4, GPT-3.5, DALL-E, and Whisper APIs
Direct model providerProcurement guardedFirst-party preferredBlocked
Operating model
Direct model provider
Procurement
Procurement guarded
Recommendation
Use OpenAI directly when model quality, roadmap alignment, and first-party support matter more than multi-vendor convenience. Live verification is currently partial because some required official source types are blocked from this environment: documentation, pricing, support.
overdue · 30d cadence
Live Verification
Required official source types exist, but live verification is currently blocked from this environment or region.
0 verified · 3 blocked · 0 broken
official baseline
Models:
gpt-4gpt-4-turbogpt-3.5-turbo+2
A
Anthropic
🇺🇸CommercialPaid
AI safety company offering Claude 3 family with extended context windows
Direct model providerProcurement guardedFirst-party preferredPartial
Operating model
Direct model provider
Procurement
Procurement guarded
Recommendation
Use Anthropic directly when Claude is strategic and you want first-party support, pricing, and model policy alignment. Live verification is currently partial because some required official source types are blocked from this environment: documentation, support.
overdue · 30d cadence
Live Verification
Some required official source types are live-verified, while others are blocked or broken and need follow-up.
1 verified · 2 blocked · 0 broken
official baseline
Models:
claude-3-opusclaude-3-sonnetclaude-3-haiku
M
MiniMax
🇨🇳Public WelfareFree
Chinese AI startup offering competitive language and multimodal models
Direct model providerProcurement blockedNeeds verificationPartial
Operating model
Direct model provider
Procurement
Procurement blocked
Recommendation
Use MiniMax directly when its model family is core to your workload and you want first-party commercial alignment. Current live verification is degraded because required official source types are missing or broken: pricing, terms.
overdue · 7d cadence
Live Verification
Some required official source types are live-verified, while others are blocked or broken and need follow-up.
2 verified · 0 blocked · 0 broken
Blocking factors
Required official source types are currently broken or missing in live verification: pricing, terms.
official baseline
Models:
abab5.5-chatabab5-chat
S
SiliconFlow (Silicon Cloud)
🇨🇳Public WelfareFree
SiliconFlow (Silicon Cloud) is a Chinese AI infrastructure platform specializing in fast inference for open-source large language models. The platform provides optimized access to popular Chinese and international models including Qwen, ChatGLM, Baichuan, Yi, and DeepSeek with latency-optimized inference endpoints. SiliconFlow offers competitive pricing with a free tier for testing, making advanced AI models accessible to Chinese developers and businesses. The service features high-performance inference infrastructure, Chinese language optimization, and seamless integration capabilities for enterprises requiring reliable AI model deployment.
Cloud platform accessProcurement guardedUse with guardrailsLive Verified
Operating model
Cloud platform access
Procurement
Procurement guarded
Recommendation
Useful when you need China-friendly access to many mainstream models from one managed platform, but enterprise rollout should still verify support and billing maturity.
overdue · 14d cadence
Live Verification
All required official source types are currently reachable from this verification environment.
4 verified · 0 blocked · 0 broken
official baseline
Models:
qwenchatglmbaichuan+3
A
AIMLAPI
🇨🇳Public WelfareFree
AIMLAPI is a comprehensive AI model aggregation platform that provides access to over 300 different AI models through a single unified API. The service supports models from multiple providers including OpenAI, Anthropic, Meta, Google, and various open-source projects, enabling developers to access cutting-edge AI capabilities without managing multiple API keys and subscriptions. AIMLAPI features developer-friendly documentation, flexible pricing options with a free tier for testing, and support for various model types including text generation, image creation, and code generation. The platform is designed to simplify AI integration for businesses and developers seeking diverse AI capabilities.
Relay / aggregation layerProcurement guardedUse with guardrailsLive Verified
Operating model
Relay / aggregation layer
Procurement
Procurement guarded
Recommendation
Suitable when one API for many models is more valuable than direct first-party alignment, especially for fast-moving product teams.
overdue · 14d cadence
Live Verification
All required official source types are currently reachable from this verification environment.
4 verified · 0 blocked · 0 broken
official baseline
Models:
gpt-4claudellama+2
AI service platform with API relay capabilities
Relay / aggregation layerProcurement blockedNeeds verificationBlocked
Operating model
Relay / aggregation layer
Procurement
Procurement blocked
Recommendation
Reasonable when you need broad model access and China-friendly delivery, but do not treat it as identical to direct first-party procurement. Live verification is currently partial because some required official source types are blocked from this environment: documentation, pricing, support, terms.
overdue · 7d cadence
Live Verification
Required official source types exist, but live verification is currently blocked from this environment or region.
0 verified · 4 blocked · 0 broken
Blocking factors
Required official source types are currently blocked from this verification environment: documentation, pricing, support, terms.
official baseline
Google's AI platform offering Gemini models. Multimodal capabilities with competitive pricing and integration with Google Cloud.
Direct model providerProcurement guardedFirst-party preferredPartial
Operating model
Direct model provider
Procurement
Procurement guarded
Recommendation
Use Google AI directly when Gemini is a target model family and you want first-party docs, pricing, and support ownership. Live verification is currently partial because some required official source types are blocked from this environment: documentation, pricing.
overdue · 30d cadence
Live Verification
Some required official source types are live-verified, while others are blocked or broken and need follow-up.
1 verified · 2 blocked · 0 broken
official baseline
Kimi by Moonshot is a long-context LLM API with excellent reasoning.
Direct model providerProcurement blockedNeeds verificationPartial
Operating model
Direct model provider
Procurement
Procurement blocked
Recommendation
Use Moonshot directly when Kimi is a target model family and you want first-party pricing and support alignment. Current live verification is degraded because required official source types are missing or broken: documentation, terms.
overdue · 7d cadence
Live Verification
Some required official source types are live-verified, while others are blocked or broken and need follow-up.
2 verified · 0 blocked · 1 broken
Blocking factors
Required official source types are currently broken or missing in live verification: documentation, terms.
official baseline