ModelBench
Alibaba Qwen logo
Models/Alibaba Qwen

Alibaba Qwen: Qwen3 Max

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

Source-linked qwen Closed weights Released 2025-09-23
API record Report
InputT
OutputT
Input price$1.2/M
Output price$6/M
Context262.144K
Max output65.536K
Providers21
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Qwen3 Max
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Alibaba Coding Plan qwen3-max-2026-01-23 262.144K 32.768K — — — Tools Docs ↗
Alibaba Coding Plan (China) qwen3-max-2026-01-23 262.144K 32.768K — — — Tools Docs ↗
OrcaRouter qwen/qwen3-max 262.144K 65.536K $0.359 $1.434 — Tools Docs ↗
Merge Gateway qwen/qwen3-max 262.144K 65.536K $0.359 $1.434 $0.072 ToolsJSON Docs ↗
Ofox bailian/qwen3-max 262.144K 65.536K $0.36 $1.43 $0.072 ReasoningTools Docs ↗
Ofox qwen/qwen3-max 256K 64K $0.36 $1.43 $0.072 ReasoningTools Docs ↗
OpenRouter qwen/qwen3-max 262.144K 65.536K $0.78 $3.9 $0.156 ToolsJSON Docs ↗
Kilo Gateway qwen/qwen3-max 262.144K 65.536K $0.78 $3.9 $0.156 ToolsJSON Docs ↗
DevPass (LLM Gateway) qwen3-max 262.144K 65.536K $0.845 $3.38 $0.6 Tools Docs ↗
Alibaba (China) qwen3-max 262.144K 65.536K $0.861 $3.441 — Tools Docs ↗
EmpirioLabs AI qwen3-max 256K 65.536K $1.08 $5.52 $1.08 ReasoningToolsJSON Docs ↗
Deep Infra Qwen/Qwen3-Max 256K 65.536K $1.2 $6 $0.24 ToolsJSON Docs ↗
LLMTR qwen/qwen3-max 256K 65.536K $1.2 $6 — ReasoningTools Docs ↗
Eden AI qwen/qwen3-max 262.144K 65.536K $1.2 $6 $0.24 ToolsJSON Docs ↗
Alibaba qwen3-max 262.144K 65.536K $1.2 $6 — Tools Docs ↗
Cloudflare AI Gateway alibaba/qwen3-max 262.144K 65.536K $1.2 $6 — Tools Docs ↗
LLM Gateway alibaba/qwen3-max 256K 32.8K $1.2 $6 $0.24 ReasoningTools Docs ↗
Vercel AI Gateway alibaba/qwen3-max 262.144K 32.768K $1.2 $6 $0.24 Tools Docs ↗
Abacus qwen3-max 131.072K 16.384K $1.2 $6 — ReasoningTools Docs ↗
NanoGPT qwen/qwen3-max 256K 32.768K $1.2 $6.001 $0.6 Not listed Docs ↗
NovitaAI qwen/qwen3-max 262.144K 65.536K $2.11 $8.45 — ToolsJSON Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.359/M

Across 19 priced providers

Median input $1.2/M

Midpoint of listed rates

Highest input $2.11/M

5.9× the lowest listed rate

Output range $1.43 – $8.45

Per million output tokens

OrcaRouter $0.359/M
Merge Gateway $0.359/M
Ofox $0.36/M
Ofox $0.36/M
OpenRouter $0.78/M
Kilo Gateway $0.78/M
DevPass (LLM Gateway) $0.845/M
Alibaba (China) $0.861/M
EmpirioLabs AI $1.08/M
Deep Infra $1.2/M
LLMTR $1.2/M
Eden AI $1.2/M
Alibaba $1.2/M
Cloudflare AI Gateway $1.2/M
LLM Gateway $1.2/M
Vercel AI Gateway $1.2/M
Abacus $1.2/M
NanoGPT $1.2/M
NovitaAI $2.11/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

2 providers list the identical $0.359 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 131.072K to 262.144K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
× Tool calling No
× Structured output No
× Attachments No
× Vision input No
× Open weights No
Model family
qwen
Knowledge cutoff
2025-04
License
Not documented
Release date
2025-09-23
Model ID
alibaba/qwen3-max
Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
Benchmark profile
SciCodeSciCode AA Coding IndexArtificial Analysis Coding Index Terminal-Bench…Terminal-Bench Hard This model — SciCode: 38.3 percent correct (72.2th percentile) This model — Artificial Analysis Coding Index: 26.4 index (75.0th percentile) This model — Terminal-Bench Hard: 20.5 success rate (63.6th percentile)

Each axis is this model's percentile among the 3 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

SciCode percent correct · 2026-05-30 Source ↗
SciCode #8 of 27
Artificial Analysis Coding Index index · 2026-05-30 Source ↗
Artificial Analysis Coding Index #7 of 26
Terminal-Bench Hard success rate · 2026-05-30 Source ↗
Terminal-Bench Hard #8 of 22

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against SciCode, the benchmark with the widest published coverage that this model appears in.

0 23 45 $0.1 $1 $10 Qwen3-Coder 30B-A3B Instruct — $0.45/M, score 27.8 Qwen3 Max — $1.2/M, score 38.3 DeepSeek-R1 — $0.7/M, score 35.7 Gemini 2.5 Flash — $0.3/M, score 39.4 Gemini 2.5 Flash-Lite — $0.1/M, score 19.3 Gemini 2.5 Pro — $1.25/M, score 42.8 Llama-3.3-70B-Instruct — $0.1/M, score 26.0 Devstral 2 — $0.4/M, score 33.1 Mistral Large 2.1 — $2/M, score 29.2 Mistral Large 3 — $0.5/M, score 36.2 Mistral Medium 3 — $0.4/M, score 33.1 Mistral Small 4 — $0.15/M, score 38.0 GPT-4 Turbo — $10/M, score 31.9 GPT-4o (2024-05-13) — $5/M, score 30.9 GPT-4o (2024-08-06) — $2.5/M, score 33.1 GPT-4o (2024-11-20) — $2.5/M, score 33.3 GPT-4o mini — $0.15/M, score 22.9 GPT-5-Codex — $1.1/M, score 40.9 Sonar — $1/M, score 22.9 Sonar Pro — $3/M, score 22.6 Step 3.5 Flash — $0.1/M, score 40.4 Step 3.5 Flash 2603 — $0.1/M, score 38.5 Step 3.7 Flash — $0.185/M, score 40.0 GLM-4.5 — $0.6/M, score 34.8 GLM-4.5-Air — $0.2/M, score 30.6 GLM-4.5V — $0.6/M, score 22.1 GLM-4.6 — $0.6/M, score 38.4 Qwen3 Max Input price per million tokens (log scale) Percent correct

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Price Completion1.434 → 6.0
Price Prompt0.359 → 1.2
Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology
Last verified
Sep 11, 2026
Status
Source-linked
Confidence
Medium
Catalog source
Models.dev
Models.devcatalog ↗Alibaba Coding Plan documentationprovider documentation ↗Alibaba Coding Plan (China) documentationprovider documentation ↗OrcaRouter documentationprovider documentation ↗Merge Gateway documentationprovider documentation ↗Ofox documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗Kilo Gateway documentationprovider documentation ↗LLM Gateway documentationprovider documentation ↗Alibaba documentationprovider documentation ↗EmpirioLabs AI documentationprovider documentation ↗Deep Infra documentationprovider documentation ↗
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/alibaba/qwen3-max
curl
curl "https://model.kyssta.lol/api/v1/models/alibaba/qwen3-max"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Qwen3 Max?

Flagship Qwen3 model for coding agents, complex reasoning, and tool use. It is published by Alibaba Qwen and catalogued here from Models.dev.

How much does Qwen3 Max cost?

Listed input pricing starts at $0.359 per million tokens from OrcaRouter, rising to $2.11 across 19 listed providers.

What is the context length of Qwen3 Max?

Qwen3 Max accepts up to 262.144K tokens of context and returns up to 65.536K output tokens.

Which providers serve Qwen3 Max?

20 providers list this model: Alibaba Coding Plan, Alibaba Coding Plan (China), OrcaRouter, Merge Gateway, Ofox, OpenRouter and 14 more.

Are the weights for Qwen3 Max open?

No. This model is served through hosted APIs only.

When was Qwen3 Max released?

The catalog records a release date of 2025-09-23, last verified Sep 11, 2026.

More models from Alibaba Qwen

View all →
QwQ 32B

Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving

131.072K ctx $0.287/M in Qwen3.6 Max Preview

Flagship Qwen model for complex reasoning, coding, and agentic workflows

262.144K ctx $1.3/M in Qwen/Qwen3.8-27B

No provider description available.

Not documented ctx Qwen3 235B-A22B Instruct 2507

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

262.144K ctx $0.069/M in