Skip to content

Models

These are the main public model IDs you should use in clients, SDKs, and editor integrations.

ModelModel IDMax inputMax outputThinkingVisionBest for
Claude Opus 4.7claude-opus-4.71M32KNoYesHard code, long reasoning, agents
Claude Opus 4.8claude-opus-4.81M32KYesYesHard code, long reasoning, agents
Claude Opus 5claude-opus-51M32KYesYesHard code, long reasoning, agents
Claude Sonnet 5claude-sonnet-51M32KYesYesEveryday development, balance of price and quality
GPT-5.6 Lunagpt-5.6-luna1M32KYesYesBulk processing, cheap repetitive tasks
GPT-5.6 Solgpt-5.6-sol1M32KYesYesBulk processing, cheap repetitive tasks
GPT-5.6 Terragpt-5.6-terra1M32KYesYesBulk processing, cheap repetitive tasks
Qwen 3.5 Flashqwen3.5-flash1M32KYesYesBulk processing, cheap repetitive tasks
Qwen 3.7 Maxqwen3.7-max1M32KYesYesBulk processing, cheap repetitive tasks
Qwen 3.7 Plusqwen3.7-plus1M32KYesYesBulk processing, cheap repetitive tasks
Qwen 3.8 Maxqwen3.8-max-preview1M32KYesYesBulk processing, cheap repetitive tasks
Claude Opus 4.6claude-opus-4.61M32KYesYesHard code, long reasoning, agents

Per-model rates

Claudexia uses pay-as-you-go billing — you pay per 1M tokens for each model. Prices are fetched from

ModelInput / 1MOutput / 1M
Claude Opus 4.7$0.3$0.3
Claude Opus 4.8$0.3$0.3
Claude Opus 5$0.3$0.3
Claude Sonnet 5$0.3$0.3
GPT-5.6 Luna$0.1$0.1
GPT-5.6 Sol$0.3$0.3
GPT-5.6 Terra$0.2$0.2
Qwen 3.5 Flash$0.1$0.1
Qwen 3.7 Max$0.2$0.2
Qwen 3.7 Plus$0.16$0.16
Qwen 3.8 Max$0.2$0.2
Claude Opus 4.6$0.3$0.3

How to choose a model

  • For coding and developmentstart with claude-sonnet-4.6. It offers the best balance of speed, quality, and cost for everyday coding tasks.
  • For complex reasoning use claude-opus-4.8 or claude-opus-4.8 when you need deep analysis, multi-step reasoning, or large codebase understanding.
  • For fast automation use gpt-5.6-luna for classification, extraction, and high-volume tasks where speed and cost matter most.
  • For latest capabilitiesclaude-opus-4.8 and claude-sonnet-4.6 have 1M context window and the newest model improvements.

Notes

  • Prefer these stable IDs for new integrations
  • Legacy dated Anthropic IDs and some aliases can still resolve, but they are less clear in shared configs
  • Use Opus for the heaviest reasoning, Sonnet for general development, and Haiku for fast low-cost work