Qwen3.6 27B
Qwen3.6 27B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.
Explore Qwen3.6 27B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses through the unified API. Supported interfaces and current availability are shown below.
- OpenAI-style Chat Completions
- Anthropic-style Messages
- OpenAI-style Responses
Model details
- Context window
- 16K tokens
- Max output
- 8K tokens
- Input
- Text
- Output
- Text
- Capabilities
- Tool calling, Streaming, JSON output
- Interfaces
- OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses
Pricing
Prices use the units shown below. No gateway fees. Usage, size and model options may affect the total.
| Metric | Price |
|---|---|
| Per generation | Price not published |
Why teams pick it
- Qwen3.6 27B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.
API availability
Availability for this model has not yet been verified. You can compare its features and pricing; request examples will appear once availability is confirmed.
/v1/chat/completionsOpenAI-style Chat Completions · openai SDK or plain HTTP
Availability not yet verified
/v1/messagesAnthropic-style Messages · @anthropic-ai/sdk SDK or plain HTTP
Availability not yet verified
/v1/responsesOpenAI-style Responses · openai SDK or plain HTTP
Availability not yet verified
More from Alibaba
Qwen3.8 MaxAlibaba's flagship MoE, built for coding and long-horizon agents.$2 / 1M input tokens · $6 / 1M output tokens · See all rates on the model pageQwen-Audio-3.0-TTS FlashQwen-Audio-3.0-TTS Flash for Speech generation.$15 / 1M charactersQwen-Audio-3.0-TTS PlusQwen-Audio-3.0-TTS Plus for Speech generation.$20 / 1M characters
Questions about this model
- Is there a free tier for Qwen3.6 27B?
- No. You add credit and pay Qwen3.6 27B's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.
- Am I charged for failed requests?
- No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.
- Is Qwen3.6 27B included in Token Plans?
- No. Qwen3.6 27B is pay-as-you-go only; Token Plans cover the other text models in the catalog.
- Can I use Qwen3.6 27B in Claude Code?
- Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to qwen3.6-27b. The same key works in Codex, opencode, Cline, and other agents.
- Does Qwen3.6 27B support tool calling and vision?
- Qwen3.6 27B supports tool calling, JSON output and streaming on Inferray. It does not take image input.
- Is it the real Qwen3.6 27B?
- Yes. A request for qwen3.6-27b is answered by Qwen3.6 27B from Alibaba, billed at its published list price. Inferray never substitutes a different or smaller model.