modelrelay_
Navigate ModelRelay
Get started
Sign in
← All models

Qwen 3.8 Max

qwen3p8-max

Frontier model for coding, research, and long-horizon agentic tasks

Intelligence
40.2
Context
262K
Training cutoff
--
Added
2026-08-27
Inputs
Vision

Providers

One route serves Qwen 3.8 Max, and every figure below is measured on it. Where the selected window has too little traffic, the figure names what it is based on instead.

Fireworks AI only route

accounts/fireworks/models/qwen3p8-max

Uptime 100.0%
Input / 1M
$2.00
Output / 1M
$6.00
TTFT
0.72s fixed prompt · n=8
Output rate
127.6 tok/s fixed prompt · n=8
262K context 131,072 max output cache $0.25 read / $2.00 write per 1M Vision ZDR Retention None Training No Provider terms, reviewed 2026-10-13warming · 30m
Prompt caching Automatic reuse Eligible Cache key Affinity hint Caller breakpoints None advertised

TTFT is the median time to the first visible answer token over real ModelRelay requests, with a fixed prompt standing in for models that have no traffic yet. Speed ranks by it. Intelligence is the Artificial Analysis Intelligence Index.