Models/Qwen3.8 Max (0902)

Qwen3.8 Max (0902)Ready

qwen3-8-max

Serverless APILLMReasoningVisionPrompt cachingClosed

A flagship Qwen release with a long multilingual and agentic track record. It ranks #11 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 45.4. Released September 2, 2026.

984K

Context

—

Parameters

#11

Intelligence rank · 45.4

Closed

Weights

View full spec

ReleasedSep 2, 2026

Knowledge cutoff—

Size classlarge

Input modalitiestext, image

Output modalitiestext

Median output speed38 tok/s

Median time to first token3.1s

Usage guide

1. Choose how you'd like to use Qwen3.8 Max (0902)

☁️ Serverless

Use with pay-per-token pricing. Zero setup, no cold starts, automatic failover between upstream routes.

Usage tiers · Standard • Priority

Try it — sign in

curl https://tokenhub.coality.io/v1/chat/completions \
  -H "Authorization: Bearer $TOKEN_HUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-8-max",
    "messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
  }'

Pricing

Bucket	Price	Notes
Input tokens	$2.50	per 1M tokens
Output tokens	$7.50	per 1M tokens
Cache read	$0.3125	cached input · 88% off
Cache write	—	per 1M tokens

Billed per token with micro-dollar precision · effective Oct 27, 2026 · default key limits 600 req/min · 200K tokens/min

Benchmarks

GPQA Diamond

92.8

Humanity's Last Exam

43.1

MMMU-Pro

82.8

SciCode

52.1

Terminal-Bench 4.0

38.9

Long Context Reasoning

80.3

Frontier Code

43.2

Scores from the Artificial Analysis evaluation suite (0–100 scale).

About this model

Closed model, with a 984K context window, native image input, visible reasoning traces, prompt caching at a 88% discount on cached input, 38 output tokens/s median serving speed and 3.1s to first token.