qwen/qwen3-max-preview

qwen/qwen3-max-preview
by qwen · text in · text out · 262.1K ctx

Qwen3 Max preview — proprietary chat preview, 256k context, thinking mode + function calling.

Endpoints:/v1/chat/completions
INPUT$0.86/ 1M tokens
OUTPUT$3.44/ 1M tokens
p50 TTFT1.00 s7d
p95 TTFT2.30 s7d
TRAFFIC91.7Ktokens / 7d
▶ Try in playground</> Use via API
Code samples
from openai import OpenAI

client = OpenAI(
    base_url="https://orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="qwen/qwen3-max-preview",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
Pricing
TierInput / 1M tokensOutput / 1M tokens
≤ 32K$0.861$3.44
≤ 128K$1.43$5.74
≤ 256K$2.15$8.60
Tier selected by input token count of each request
Performancelast 7 days
TTFT p50
1.00 s
Output speed
14.1 tok/s
TTFT p95
2.30 s
Error rate
3.1%
Public benchmarksLast evaluated 2025-09-05
AA Coding
25.5
AA Intelligence
26.1
AA Math
75.0
AIME 2025
75.0
GPQA Diamond
76.4
Humanity's Last Exam
9.3
IFBench
48.0
LiveCodeBench
65.1
Long-Context Recall
39.7
MMLU-Pro
83.8
SciCode
37.0
TerminalBench Hard
19.7
τ²-Bench
32.7
Source: artificialanalysis.ai
More from qwenSee all models from qwen →
Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b
$0.17 in · $1.03 out / 1M
32.8K ctx· quality 8/10
qwen/qwen3.5-plusCheapest
qwen/qwen3.5-plus
$0.12 in · $0.69 out / 1M
1.05M ctx· quality 8/10
Qwen3.6 35B A3BNew
qwen/qwen3.6-35b-a3b
$0.25 in · $1.49 out / 1M
262.1K ctx· quality 8/10
FAQ
How much does qwen/qwen3-max-preview cost on OrcaRouter?
qwen/qwen3-max-preview is priced at $0.86 per 1M input tokens and $3.44 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
What is qwen/qwen3-max-preview's context window?
qwen/qwen3-max-preview supports a context window of 262K tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call qwen/qwen3-max-preview via the OpenAI SDK?
Set OpenAI base_url to https://orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="qwen/qwen3-max-preview" in the chat.completions.create call.
Does OrcaRouter rate-limit qwen/qwen3-max-preview?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.
Embed this badgePaste into your blog post
qwen/qwen3-max-preview•$0.86/M in•1000ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/qwen/qwen3-max-preview" target="_blank"> <img src="https://www.orcarouter.ai/embed/qwen/qwen3-max-preview.svg" alt="qwen/qwen3-max-preview on OrcaRouter" /> </a>
Markdown [![qwen/qwen3-max-preview](https://www.orcarouter.ai/embed/qwen/qwen3-max-preview.svg)](https://www.orcarouter.ai/models/qwen/qwen3-max-preview)