Docs/ Reference

Channel capability matrix

Check credential types, client protocols, operations, route modes, model discovery, and managed proxy support by channel.

Scope and version §

This page describes route capabilities declared by GPT-Load. It does not mean that every model or upstream supports each capability.

The matrix comes from the GPT-Load v2.0.0-rc.2 channel descriptors and was reviewed on 2026-09-01. For later releases, use the descriptors from that release.

How to read the matrix

N means Native execution in the target protocol; C means the gateway converts the request; N/C is model-dependent; — means the route is not currently declared.

Credentials and core protocols §

Channel Credential Chat CompletionsResponses CreateAnthropic MessagesGemini Generate
OpenAI API Key NNCC
CodexOAuth / OAuth JSONCNCC
ClaudeOAuth / OAuth JSONCCNC
AntigravityOAuth / OAuth JSONCCCN
Grok Device authorization / OAuth JSON CNCC
Anthropic API Key CCNC
Google Gemini API Key CCCN
Azure OpenAI API key / Entra CCCC
AWS Bedrock Bedrock API key / AWS credentials CCCC
Google Vertex AI Service account JSON CCCN/C
DeepSeek API Key NNNC
Moonshot AI API Key NCCC
SiliconFlow API Key NCCC
Zhipu AI API Key NCCC
Alibaba Cloud Bailian API Key NCCC
Volcengine Ark API Key NCCC
OpenRouter API Key NNCC
Groq API Key NCCC
xAI API Key NNCC
OpenAI Compatible API key + custom endpoint NCCC

Route modes are declared per protocol and operation. One channel can contain both Native and Converted routes.

Additional operations §

Channel Image generation/editing EmbeddingsAnthropic CountTokensGemini CountTokensResponses Input Tokens Responses resource APIs Model discovery Managed proxy
OpenAINNCCNN
CodexNCCN
ClaudeNCC
AntigravityCNC
GrokCCN
AnthropicNCC
Google GeminiCNC
Azure OpenAI
AWS Bedrock
Google Vertex AI
DeepSeek
Moonshot AI
SiliconFlow
Zhipu AI
Alibaba Cloud Bailian
Volcengine Ark
OpenRouterN
Groq
xAI
OpenAI CompatibleNN

Images covers both generation and editing. Responses resource APIs include retrieve, delete, cancel, input items, compact, and namespace pass-through.

Model discovery means the management plane uses a credential to discover upstream models. Data-plane model lists return configured models visible to the current AccessKey and do not query upstream in real time.

Managed proxy means a proxy injected by GPT-Load at credential, Group, or global scope. Provider SDK behavior that reads environment variables is outside this contract.

Validation levels §

Level Meaning Current public evidence
Automated contract Channel declarations, RouteMode values, adapter capabilities, and automated tests agree Covers the route contracts for all 20 channels listed here
Artifact smoke A released binary or image traverses the full product path, while the upstream may be a controlled substitute The release image covers OpenAI Compatible Chat through to a fake upstream
Live upstream verified A specific version, channel, operation, and model are verified with a real credential There is currently no centrally published, per-item traceable Live E2E record for all 20 channels
Implementation support does not equal live upstream verification

Upstreams change APIs, models, and account policies. A verification record without a version, date, operation, model, and evidence link is not marked Live upstream verified.

Known limitations §

  • The actual capabilities of OpenAI Compatible depend on the relay you configure. The matrix only states which requests GPT-Load can construct and accept.
  • Google Vertex AI chooses Native or Converted Gemini routing by model.
  • A protocol route does not guarantee that a model supports tools, reasoning, vision, or other model-level features.
  • Azure OpenAI, AWS Bedrock, and Google Vertex AI do not support GPT-Load managed proxies.
Channel capability matrix - GPT-Load