qwen3-coder-30b-a3b-instruct pricing

Chat

qwen3-coder-30b-a3b-instruct · Alibaba Qwen · context —

Price per 1M tokens

In effect since Oct 15, 2026

qwen3-coder-30b-a3b-instruct token prices
Input (uncached)	$0.45
OutputIncludes reasoning tokens	$2.25

Above 32K prompt tokens: $0.75 in / $3.75 out; Above 128K prompt tokens: $1.20 in / $6.00 out. The whole request uses these rates.

1 version since Oct 15, 2026

Show data as table

qwen3-coder-30b-a3b-instruct price history per 1M tokens
Effective from	Input / 1M	Output / 1M
Oct 15, 2026	$0.45	$2.25
Oct 16, 2026	$0.45	$2.25

Calculated with the same function that AI Cost Map uses for your real events.

Uncached input tokens per call

Output tokens per call

Includes reasoning tokens.

Calls per month

Cost per call

$0.0020

Cost per month

$202.50

Same model type, nearest blended price (3 input : 1 output).

Similar models compared with qwen3-coder-30b-a3b-instruct
Model	Input	Output	Context	Blended vs this
qwen3-coder-30b-a3b-instruct (this model) Alibaba Qwen	$0.45	$2.25	—	—
qwen3.5-plus Alibaba Qwen	$0.40	$2.40	—	× 1.0
moonshotai/kimi-k2.5 DeepInfra	$0.45	$2.25	—	× 1.0
accounts/fireworks/models/code-llama-34b Fireworks AI	$0.90	$0.90	—	× 1.0
accounts/fireworks/models/code-llama-34b-instruct Fireworks AI	$0.90	$0.90	—	× 1.0
accounts/fireworks/models/code-llama-34b-python Fireworks AI	$0.90	$0.90	—	× 1.0
accounts/fireworks/models/code-llama-70b Fireworks AI	$0.90	$0.90	—	× 1.0