Qwen3-Coder is the code version of Qwen3.
Schema d'entrée
Les paramètres suivants sont acceptés dans le corps de la requête.
Total: 9Requis: 2Optionnel: 7
modelstringrequired
The model ID to use for the completion.
messagesarray[object]required
A list of messages comprising the conversation so far.
rolestringrequired
The role of the message author. One of "system", "user", or "assistant".
systemuserassistant
contentstringrequired
The content of the message.
max_tokensinteger
The maximum number of tokens to generate in the completion.
temperaturenumber
Sampling temperature between 0 and 2. Higher values make output more random, lower values more focused and deterministic.
top_pnumber
Nucleus sampling parameter. The model considers the tokens with top_p probability mass.
streamboolean
If set to true, partial message deltas will be sent as server-sent events.
stoparray[string]
Up to 4 sequences where the API will stop generating further tokens.
frequency_penaltynumber
Penalizes new tokens based on their existing frequency in the text so far. Between -2.0 and 2.0.
presence_penaltynumber
Penalizes new tokens based on whether they appear in the text so far. Between -2.0 and 2.0.
Exemple de corps de requête
json
{
"model": "Qwen/Qwen3-Coder",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 1024,
"temperature": 0.7,
"stream": false
}Qwen3-Coder-480B-A35B-Instruct
Highlights
Qwen3-Coder-480B-A35B-Instruct. featuring the following key enhancements:
- Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks, achieving results comparable to Claude Sonnet.
- Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding.
- Agentic Coding supporting for most platform such as Qwen Code, CLINE, featuring a specially designed function call format.
Model Overview
Qwen3-480B-A35B-Instruct has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining & Post-training
- Number of Parameters: 480B in total and 35B activated
- Number of Layers: 62
- Number of Attention Heads (GQA): 96 for Q and 8 for KV
- Number of Experts: 160
- Number of Activated Experts: 8
- Context Length: 262,144 natively.
NOTE: This model supports only non-thinking mode and does not generate <think></think> blocks in its output. Meanwhile, specifying enable_thinking=False is no longer required.
