Check key scope
Claude-only, OpenAI-only, combined, Gemini, Grok, Qwen, Local Models, API-credit, and exact-model keys can return different catalogs.
ScaleMax models
Human-readable model names and copyable API IDs are not the same thing.
Use the display name to compare models, then copy the exact API ID from the live authenticated catalog. Availability follows the key’s scope and active production routes.
Catalog rules
Three checks before selecting a model.
Copy the API ID
Client configuration uses the exact machine-readable ID, including punctuation and version suffixes.
Check capabilities
Tools, images, reasoning controls, context limits, and output limits are model- and route-specific.
Reference names
Models represented in the shared ScaleMax catalog.
This reference explains names and IDs. Local Models lists every id in the live family roster. It is not an availability guarantee; the live catalog filters models to currently active routes for the requesting key.
Anthropic
7 reference IDs
Claude Haiku 4.5
claude-haiku-4-5-20251001Fast Anthropic model for low-latency chat and everyday work
Claude Opus 4.6
claude-opus-4-6High-capability Anthropic reasoning model for complex work
Claude Opus 4.7
claude-opus-4-7High-capability Anthropic model for advanced coding and reasoning
Claude Opus 4.8
claude-opus-4-8Premium Anthropic model for deep analysis and demanding tasks
Claude Opus 5
claude-opus-5Latest premium Anthropic model for advanced coding, agents, and deep reasoning
Claude Sonnet 5
claude-sonnet-5Balanced Anthropic model for strong reasoning and production workflows
Fable 5
fable-5Anthropic-family Fable model through ScaleMax
ScaleMax
9 reference IDs
Codex Auto Review
codex-auto-reviewScaleMax-optimized automated code review and PR analysis
GPT-5.3 Codex
gpt-5.3-codexBudget-friendly coding assistant
GPT-5.4
gpt-5.4Advanced long-context coding and analysis
GPT-5.4 mini
gpt-5.4-miniFast low-cost everyday development
GPT-5.5
gpt-5.5Premium reasoning and agentic coding
GPT-5.6 Sol
gpt-5.6-solAvailable through ScaleMax
GPT-5.6 Terra
gpt-5.6-terraAvailable through ScaleMax
GPT-6 astra
gpt-6-astraAvailable through ScaleMax
GPT-5.6 Luna
gpt-5.6-lunaAvailable through ScaleMax
Gemini
5 reference IDs
Gemini 3 Flash Preview
gemini-3-flash-previewPreview Google Gemini 3 model tuned for fast responses
Gemini 3 Pro Preview
gemini-3-pro-previewPreview Google Gemini 3 model for advanced reasoning and long context
Gemini 3.1 Flash Lite Preview
gemini-3.1-flash-lite-previewPreview lightweight Google Gemini model for high-volume work
Gemini 3.1 Pro Preview
gemini-3.1-pro-previewPreview Google Gemini model for demanding reasoning and agentic work
Gemini 3.6 Flash
gemini-3.6-flashLatest fast Google Gemini model for everyday coding and chat
Grok
2 reference IDs
Grok 4.5
grok-4.5xAI Grok model for reasoning, coding, and general assistance
Grok Build
grok-buildxAI Grok model for coding and agentic work
Qwen
2 reference IDs
Qwen 3.6 Plus
qwen3.6-plusAlibaba Qwen model for general reasoning and coding
Qwen 3.7 Plus
qwen3.7-plusLatest Alibaba Qwen model for general reasoning and coding
Local Models
51 reference IDs
DeepSeek V4 Flash
deepseek-v4-flashFast general-purpose model for everyday coding and chat
DeepSeek V4 Flash New
deepseek-v4-flash-newNewer DeepSeek V4 Flash generation with a 1M-token context window
DeepSeek V4 Flash 0731 Unlimited
dsv4-flash-0731-unlimitedDeepSeek V4 Flash 0731 build with tool calling, sold in the Local Models pack
Sonnet 4.6
claude-sonnet-4-6Fast general-purpose model with tool calling, sold in the Local Models pack
DeepSeek V4 Flash 1M
deepseek-v4-flash-1mLong-context general-purpose model for large codebases and documents
DeepSeek V4 Pro
deepseek-v4-proHigh-capability general-purpose model for demanding reasoning and coding
deepseek-v4-pro-0813
deepseek-v4-pro-0813DeepSeek · Local Models pack
DeepSeek V3.2
deepseek-v3.2General-purpose model for reasoning and coding
deepseek-v4-pro-v3
deepseek-v4-pro-v3DeepSeek · Local Models pack
deepseek-v4-flash-v3
deepseek-v4-flash-v3DeepSeek · Local Models pack
Gemini 3 Flash Preview
gemini-3-flash-previewPreview general-purpose model tuned for fast responses
Gemini 3 Pro Preview
gemini-3-pro-previewPreview general-purpose model for advanced reasoning and long context
Gemini 3.1 Flash Lite Preview
gemini-3.1-flash-lite-previewPreview lightweight general-purpose model for high-volume work
Gemini 3.1 Pro Preview
gemini-3.1-pro-previewPreview general-purpose model for demanding reasoning and agentic work
Gemini 3.6 Flash
gemini-3.6-flashLatest fast general-purpose model for everyday coding and chat
gemini-3.7-flash
gemini-3.7-flashGemini · Local Models pack
Gemini 3.8 Flash
gemini-3.8-flashFast general-purpose model with tool calling, sold in the Local Models pack
Grok 4.5
grok-4.5General-purpose model for reasoning, coding, and everyday assistance
Grok 4.6
grok-4.6Latest general-purpose model for reasoning, coding, and everyday assistance
Grok Build
grok-buildGrok model for coding and agentic work
glm-5
glm-5GLM · Local Models pack
glm-5.1
glm-5.1GLM · Local Models pack
GLM 5.2
glm-5.2Balanced general-purpose model for production workflows
glm-5.3
glm-5.3GLM · coming soon (priced, not yet routed)
glm-5.3-flash
glm-5.3-flashGLM · Local Models pack
glm-5.2-v2
glm-5.2-v2GLM · Local Models pack
glm-5.3-v2
glm-5.3-v2GLM · Local Models pack
glm-5.3-flash-v2
glm-5.3-flash-v2GLM · Local Models pack
glm-5.3-flash-v3
glm-5.3-flash-v3GLM · Local Models pack
MiniMax M2.5
minimax-m2.5General-purpose model for reasoning and coding
MiniMax M2.7
minimax-m2.7Latest general-purpose model for reasoning and coding
minimax-m3
minimax-m3MiniMax · Local Models pack
Kimi K2.6
kimi-k2.6Long-context general-purpose model for extended conversations and large codebases
kimi-k2.7-code
kimi-k2.7-codeKimi · Local Models pack
kimi-k3
kimi-k3Kimi · Local Models pack
Hunyuan 3
hunyuan-3General-purpose model for reasoning and everyday coding
Hunyuan 4
hy4Reasoning model with tool calling, sold in the Local Models pack
hy4-preview
hy4-previewHunyuan · Local Models pack
MiMo V2.5
mimo-v2.5Lightweight general-purpose model for fast, low-cost work
mimo-v2.5-pro
mimo-v2.5-proMiMo · Local Models pack
mistral-large-3
mistral-large-3Mistral · Local Models pack
nemotron-lightning-3.5
nemotron-lightning-3.5Nemotron · Local Models pack
qwen-3.7-flash
qwen-3.7-flashQwen · Local Models pack
qwen-3.7-max
qwen-3.7-maxQwen · Local Models pack
qwen-3.8-27b
qwen-3.8-27bQwen · Local Models pack
qwen3.8
qwen3.8Qwen · Local Models pack
qwen3.8-max-v2
qwen3.8-max-v2Qwen · Local Models pack
muse-spark-1.2
muse-spark-1.2Muse · Local Models pack
step-3.5-flash
step-3.5-flashStepFun · Local Models pack
LongCat 2.0
longcat-2.0Free reasoning model with tool calling, sold in the Local Models pack
gpt-oss-120b
gpt-oss-120bOpenAI · Local Models pack
The authenticated response wins.
Before a production request, fetch the catalog with the same key and base URL the client will use.