Models/Qwen 3 235B-A22B
QwenQwen / Qwen 3 235B-A22B
Released: 4/29/2025
texttext
Input: $0.10 / Output: $0.10

Qwen 3 235B-A22B is a Mixture-of-Experts (MoE) LLM. It excels in complex reasoning, mathematics, coding, and multilingual capabilities, offering a unique "thinking" mode for complex tasks and a "non-thinking" mode for general conversational efficiency.

Some other noteworthy features of Qwen 3 235B-A22B include advanced instruction-following capability, agent tool-calling functionality, and support for over 100 languages and dialects.

MetricValue
Parameter Count235 billion
Mixture of ExpertsYes
Active Parameter Count22 billion
Context Length32K tokens (extendable to 131K)
MultilingualYes
Quantized*Unknown

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

Qwen models available on Oxen.ai
ModalityPrice (1M tokens)
ModelInference providerInputOutputInputOutput
Fireworks AI
texttext$0.90$0.90
Together.ai
texttext$0.80$0.80
Fireworks AI
texttext$0.10$0.10
Fireworks AI
texttext$0.90$0.90
Fireworks AI
imagetext$0.90$0.90
Bytez
texttextN/AN/A
Fireworks AI
texttext$0.90$0.90
Fireworks AI
texttext$0.90$0.90
Together.ai
texttext$1.20$1.20
Together.ai
texttext$1.20$1.20
Fireworks AI
texttext$0.90$0.90
See all models available on Oxen.ai