Qwen (Alibaba) · OpenAI-compatible
Qwen3 Coder 30B API
Coding model for agents and editors. $0.0675 in, $0.27 out per 1M tokens. Free up to 100,000 tokens a day.
| Model id | qwen3-coder-30b |
| Input | $0.0675 per 1M tokens |
| Output | $0.27 per 1M tokens |
| Context | 98,304 tokens |
| Input types | Text |
| Tool calling | Yes — tool_choice auto, required |
| JSON output | Yes — json_object and json_schema |
| Data | Served only on dedicated GPUs we operate. Not stored, not used for training. If no GPU is online the request fails (503), never rerouted. |
| Free tier | 100,000 tokens and 50 requests a day with Google sign-in. Terms |
Lower on input and output than all 2 provider endpoints listing it there; the lowest, SiliconFlow, is $0.07 / $0.28 per 1M tokens on OpenRouter. Checked 2026-10-31 22:40 UTC · source
Good for
- Coding agents and editor chat: Cline, Kilo Code, Continue, Aider
- Writing, refactoring and explaining code, and writing tests
- Tool calling and JSON output
Call it
curl https://synap.linkrra.com/v1/chat/completions \
-H "Authorization: Bearer $SYNAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "qwen3-coder-30b", "messages": [{"role": "user", "content": "Hello"}]}'from openai import OpenAI
client = OpenAI(base_url="https://synap.linkrra.com/v1", api_key="sk-pool-...")
r = client.chat.completions.create(
model="qwen3-coder-30b",
messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)Any OpenAI SDK works: change base_url to https://synap.linkrra.com/v1. Tool setup: guides.