Qwen / qwen/qwen3.7-max

Qwen3.7-Max - access through LLMTR

Qwen3.7-Max is a new top-tier text model in the Qwen family. Thinking is enabled by default, while latency-sensitive requests can disable it with the model suffix or request body. It is a strong fit for coding, research, tool use, and multi-step instruction following.

Technical specifications

Canonical IDqwen/qwen3.7-max
ProviderQwen
Context window256,000 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext

Pricing

A 6% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$2.50
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$7.50

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.7-max","messages":[{"role":"user","content":"Hello"}]}'

Related models