# Qwen3.8 27B > Text and vision chat with tools and reasoning. Tested in Arabic by BroadNet. Call it as `broadnet/qwen3.8-27b` on BroadNet Inference, an OpenAI-compatible API at https://inference.broadnet.ai/v1. Prices synced from https://inference.broadnet.ai/pricing.json on 2026-11-14. BroadRouter is BroadNet's own site. BroadNet Inference is a single provider, not a router. ## Key facts - Model ID: `broadnet/qwen3.8-27b` - Type: chat - Base URL: https://inference.broadnet.ai/v1 - Endpoint: POST https://inference.broadnet.ai/v1/chat/completions - Input: text and image; output: text - Context window: 262,144 tokens - Capabilities: reasoning, tool calling, structured output - Data retention: none. Inference content is not retained or used for training (https://broadrouter.com/zero-data-retention/) ## Pricing (USD, synced 2026-11-14) - Input: $0.175 per 1M tokens - Cached input: $0.0435 per 1M tokens - Output: $2.17 per 1M tokens - Starting credit: not covered. New accounts get $5 of starting credit, but Qwen3.8 27B needs a top-up first. ## Limits - Pay-as-you-go: 30 requests a minute and 4 concurrent requests per key. A key lasts one year; an account holds up to 10 live keys. ## Authentication Create a key in the BroadNet console (https://inference.broadnet.ai/) and send it only in the `Authorization: Bearer` header. Inference keys call `/v1/*` model routes only; portal credentials manage keys, allowed IPs and purchases and carry full account authority. Any OpenAI SDK works by changing base_url, API key and model ID. ## Minimal request (curl) ```bash curl https://inference.broadnet.ai/v1/chat/completions \ -H "Authorization: Bearer $BROADNET_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "broadnet/qwen3.8-27b", "max_tokens": 2000, "messages": [{"role": "user", "content": "Reply with one short sentence."}] }' ``` The answer is in `choices[0].message.content`; `usage` holds the billed token counts. ## Minimal request (OpenAI Python SDK) ```python from openai import OpenAI import os client = OpenAI( base_url="https://inference.broadnet.ai/v1", api_key=os.environ["BROADNET_API_KEY"], ) response = client.chat.completions.create( model="broadnet/qwen3.8-27b", max_tokens=2000, messages=[{"role": "user", "content": "Reply with one short sentence."}], ) print(response.choices[0].message.content) ``` Qwen3.8 27B reasons before it answers, and the reasoning counts toward `max_tokens`. Give it 1,000 tokens or more; an empty `content` with `finish_reason` `length` means the budget ran out during reasoning. See https://broadrouter.com/guides/reasoning-tokens-empty-response/ ## Links - [Qwen3.8 27B on BroadRouter](https://broadrouter.com/models/qwen3.8-27b/) (Markdown: https://broadrouter.com/models/qwen3.8-27b/index.md) - [Pricing](https://broadrouter.com/pricing/) - [Developer quickstart](https://broadrouter.com/developers/) - [First request to BroadNet Inference with curl](https://broadrouter.com/guides/curl-quickstart/) - [Use the OpenAI Python SDK with BroadNet Inference](https://broadrouter.com/guides/openai-python-sdk/) - [BroadNet Inference error codes and when to retry](https://broadrouter.com/guides/errors-and-retries/) - [Lock API keys to your servers with IP allow-lists](https://broadrouter.com/guides/api-keys-ip-allow-lists/) - [Use the OpenAI Node.js SDK with BroadNet Inference](https://broadrouter.com/guides/openai-node-sdk/) - [Stream chat completions and handle dropped connections](https://broadrouter.com/guides/streaming-chat-completions/) - [Why a reasoning model returns an empty answer](https://broadrouter.com/guides/reasoning-tokens-empty-response/) - [Use LangChain with BroadNet Inference](https://broadrouter.com/guides/langchain-openai-base-url/) - [Use Cline with BroadNet Inference (OpenAI Compatible provider)](https://broadrouter.com/guides/cline-openai-compatible/) - [Use Roo Code with BroadNet Inference (OpenAI Compatible)](https://broadrouter.com/guides/roo-code-openai-compatible/) - [Use Continue with BroadNet Inference (config.yaml and apiBase)](https://broadrouter.com/guides/continue-dev-openai-compatible/) - [Add BroadNet Inference to opencode as a custom provider](https://broadrouter.com/guides/opencode-custom-provider/) - [Connect Open WebUI to BroadNet Inference](https://broadrouter.com/guides/open-webui-openai-api/) - [Add BroadNet Inference to LibreChat as a custom endpoint](https://broadrouter.com/guides/librechat-custom-endpoint/) - [Use BroadNet Inference in n8n (OpenAI credential, Base URL)](https://broadrouter.com/guides/n8n-openai-compatible/) - [Use the Vercel AI SDK with BroadNet Inference](https://broadrouter.com/guides/vercel-ai-sdk-openai-compatible/) - [Route LiteLLM to BroadNet Inference (SDK and proxy)](https://broadrouter.com/guides/litellm-proxy-custom-provider/) - [Run the OpenAI Agents SDK on BroadNet Inference](https://broadrouter.com/guides/openai-agents-sdk-custom-provider/) - [Read Arabic invoices and receipts with a vision model](https://broadrouter.com/guides/read-arabic-invoices-with-vision/) - [Use Zed with BroadNet Inference as an OpenAI-compatible provider](https://broadrouter.com/guides/zed-openai-compatible-provider/) - [Use Kilo Code with BroadNet Inference (OpenAI Compatible provider)](https://broadrouter.com/guides/kilo-code-openai-compatible/) - [Add BroadNet Inference to goose as a custom provider](https://broadrouter.com/guides/goose-custom-provider/) - [Use Pydantic AI with BroadNet Inference (OpenAICompatibleProvider)](https://broadrouter.com/guides/pydantic-ai-openai-compatible/) - [Use CrewAI with BroadNet Inference as a custom OpenAI endpoint](https://broadrouter.com/guides/crewai-custom-openai-endpoint/) - [Use LlamaIndex with BroadNet Inference through OpenAILike](https://broadrouter.com/guides/llamaindex-openailike/) - [Add BroadNet Inference to Dify with the OpenAI-API-compatible plugin](https://broadrouter.com/guides/dify-openai-api-compatible/) - [Use Jan with BroadNet Inference as a custom OpenAI-compatible provider](https://broadrouter.com/guides/jan-custom-endpoint/) - [Connect SillyTavern to BroadNet Inference (Custom OpenAI-compatible)](https://broadrouter.com/guides/sillytavern-custom-openai-endpoint/) - [Use Spring AI with BroadNet Inference (OpenAI base-url)](https://broadrouter.com/guides/spring-ai-openai-base-url/) - [Call BroadNet Inference from Go with the openai-go SDK](https://broadrouter.com/guides/openai-go-sdk/) - [Build LangGraph agents on BroadNet Inference](https://broadrouter.com/guides/langgraph-openai-compatible/) - [Use Haystack pipelines and agents with BroadNet Inference](https://broadrouter.com/guides/haystack-openai-compatible/) - [Use Semantic Kernel with BroadNet Inference](https://broadrouter.com/guides/semantic-kernel-openai-compatible/) - [Use Mastra agents with BroadNet Inference](https://broadrouter.com/guides/mastra-openai-compatible/) - [Get structured output with Instructor on BroadNet Inference](https://broadrouter.com/guides/instructor-structured-output/) - [Use DSPy with BroadNet Inference (set model_type="chat")](https://broadrouter.com/guides/dspy-openai-compatible/) - [Evaluate BroadNet models with promptfoo](https://broadrouter.com/guides/promptfoo-openai-compatible/) - [Run smolagents on BroadNet Inference with OpenAIModel](https://broadrouter.com/guides/smolagents-openai-compatible/) - [Connect Flowise to BroadNet Inference (OpenAI Custom Model)](https://broadrouter.com/guides/flowise-openai-compatible/) - [Connect Langflow to BroadNet Inference](https://broadrouter.com/guides/langflow-openai-compatible/) - [DeepSeek V4.1 Flash vs Qwen3.8 27B](https://broadrouter.com/compare/deepseek-v4.1-flash-vs-qwen3.8-27b/) - [GLM 5.3 vs Qwen3.8 27B](https://broadrouter.com/compare/glm-5.3-vs-qwen3.8-27b/) - [BroadNet Gemma 4 VL 26B vs Qwen3.8 27B](https://broadrouter.com/compare/gemma-4-vl-26b-vs-qwen3.8-27b/) - [All models as JSON](https://broadrouter.com/models.json) - [Site map for agents](https://broadrouter.com/llms.txt) - [BroadNet API reference](https://inference.broadnet.ai/docs) - [Official machine-readable prices](https://inference.broadnet.ai/pricing.json)