Qwen3-Max

Context

262K

Input price

$0.359/1M tokens

Output price

$1.434/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

ProviderQwen

CreatorQwen

Familyqwen3

Status—

Input modalities—

Output modalities—

Knowledge cutoff—

Release date—

Deprecation date—

Type—

Reasoning tokens—

Max input—

Sourceofficial

Last updated2026-03-21

Pricing

Input

$0.359

Output

$1.434

Cache write

—

Cache read

—

Batch in

—

Batch out

—

qwen3 family

Model	Perf	Speed	Context	Max out	Input	Output
qwen3-235b-a22b-instructTS	—	—	—	—	—	—
qwen3-235b-a22b-thinkingTS	—	—	—	—	—	—
qwen3-235b-a22bTS	—	—	—	—	—	—
qwen3-30b-a3b-instructTS	—	—	—	—	—	—
qwen3-30b-a3b-thinkingTS	—	—	—	—	—	—
qwen3-30b-a3bTS	—	—	—	—	—	—
qwen3-coder-30b-a3b-instructTS	—	—	—	—	—	—
qwen3-coder-480b-a35b-instructTS	—	—	—	—	—	—
qwen3-coder-flashTS	—	—	—	—	—	—
qwen3-coder-plusTS	—	—	—	—	—	—
qwen3-max-previewTS	—	—	—	—	—	—
qwen3-next-80b-a3b-instructTS	—	—	—	—	—	—
qwen3-next-80b-a3b-thinkingTS	—	—	—	—	—	—
qwen3-omni-flash-0915TS	—	—	—	—	—	—
qwen3-omni-flash-realtimeTS	—	—	—	—	—	—
qwen3-omni-flashTS	—	—	—	—	—	—
qwen3-omni-realtime-flashTS	—	—	—	—	—	—
qwen3TS	—	—	—	—	—	—
Qwen3-MaxRTS	—	—	262K	—	$0.359	$1.434

API

GET/v1/models/qwen/qwen3-max