Run Qwen 3 235B-A22B on your data

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.

Metric	Value
Parameter Count	235 billion
Mixture of Experts	Yes
Active Parameter Count	22 billion
Context Length	32K tokens (extendable to 131K)
Multilingual	Yes
Quantized*	Unknown

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

	Modality	Price (1M tokens)
Qwen 2.5 Coder 32B Instruct	Fireworks AI	text	text	$0.90	$0.90
Qwen 2.5 Coder 32B Instruct	Together.ai	text	text	$0.80	$0.80
Qwen 3 235B-A22B	Fireworks AI	text	text	$0.10	$0.10
Qwen 3 30B-A3B	Fireworks AI	text	text	$0.90	$0.90
Qwen2 VL 72B Instruct	Fireworks AI	image	text	$0.90	$0.90
Qwen2.5 1.5B Instruct	Bytez	text	text	N/A	N/A
Qwen2.5 72B Instruct	Fireworks AI	text	text	$0.90	$0.90
QwQ 32B	Fireworks AI	text	text	$0.90	$0.90
QwQ 32B	Together.ai	text	text	$1.20	$1.20
QwQ 32B Preview	Together.ai	text	text	$1.20	$1.20
QwQ 32B Preview	Fireworks AI	text	text	$0.90	$0.90

Modality

Price (1M tokens)

Model

Inference provider

Input

Output

Input

Output

Qwen 2.5 Coder 32B Instruct

Fireworks AI