Model Catalog › qwen

Qwen3.8 Max

qwen3.8-max

CHAT High tier ReasoningMultimodal Proprietary (API-only)

Qwen3.8 Max (qwen3.8-max) is a chat model from qwen with a 991.8K-token context window; proprietary (API-only); capabilities tools, vision, reasoning; input image, pdf, text, video; output text.

991.8KContext
131.1KMax output
$2$ / 1M in
33.7Intelligence
37.55tok / s

Pricing

Input
$2 / 1M tokens
Output
$6 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.

Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-10-30.

Benchmarks

Intelligence index
33.7

Cited from a public third-party leaderboard — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-11-05.

Performance

Throughput
37.55 tokens/s
Latency (TTFT)
3.15 s

Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-11-05.

Specifications

Context window
991,808 tokens (991.8K)
Max output
131,072 tokens
Weights
Proprietary (API-only)
Input modalities
image pdf text video
Output modalities
text
Release date
2026-08-03

Capabilities

tools vision reasoning

Provenance

artificial-analysislitellmmodels-dev
Last verified: 2026-11-05

Related models

Qwen-Turbo
qwen-turbo
qwen · CHAT · 129.0K ctx
GLM-5.2
glm-5.2
qwen · CHAT · 1.0M ctx
Kimi K3
kimi-k3
qwen · CHAT · 1.0M ctx
DeepSeek V4 Flash 0731
deepseek-v4-flash-0731
qwen · CHAT · 1M ctx
Qwen-Coder
qwen-coder
qwen · CHAT · 1M ctx
Qwen3.5 Flash
qwen3.5-flash
qwen · CHAT · 1M ctx