Qwen: Qwen3 235B A22B Thinking 2507
Fiabilité
20%
qwen/qwen3-235b-a22b-thinking-2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances struct...
🧠 Intelligence & Données
Knowledge Cutoff:
2025-06-30
Tokenizer:
Qwen3
Moderation:
✅ Non
📅 Cycle de vie
Ajouté le:
25/07/2025
Spécifications
-
Provider & Modalité qwen text->text
-
Fenêtre de contexte 131,072 tokens
-
Max Output Tokens 0
-
Support des Outils (Tools) ✔️ Fonction Calling
🔍 Modèles similaires
| Modèle | Provider | Input | Output | Contexte | |
|---|---|---|---|---|---|
|
Qwen: Qwen3.6 Plus (free)
qwen/qwen3.6-plus:free
|
qwen | $0.0000 | $0.0000 | 1,000,000 | → |
|
Qwen: Qwen3.5-9B
qwen/qwen3.5-9b
|
qwen | $0.0500 | $0.1500 | 256,000 | → |
|
Inception: Mercury 2
inception/mercury-2
|
inception | $0.2500 | $0.7500 | 128,000 | → |
|
OpenAI: GPT-5.3 Chat
openai/gpt-5.3-chat
|
openai | $1.7500 | $14.0000 | 128,000 | → |
|
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
google/gemini-3.1-flash-i...
|
$0.5000 | $3.0000 | 65,536 | → |