What this model supports
ReasoningNo
Tool callingYes
Structured outputNo
AttachmentsNo
Temperature controlYes
Open weightsNo
- Creator
- Alibaba Qwen
- Family
- qwen
- Modalities
- Text
- License
- Not documented
- Release date
- 2025-09-23
- Model ID
alibaba/qwen3-max
Qwen3 Max
alibaba/qwen3-maxFlagship Qwen3 model for coding agents, complex reasoning, and tool use
Input modalities
Output modalities
Source-linkedqwenClosed weightsReleased 2025-09-23
Context window262.144K
Maximum output65.536K
Provider offers12
Knowledge cutoff2025-04
Market availability
Report price →Provider pricing
| Provider | Provider model ID | Context | Input / 1M | Output / 1M | Cached / 1M | Features | All pricing |
|---|---|---|---|---|---|---|---|
 Alibaba Coding Plan (China) | qwen3-max-2026-01-23 | 262.144K | $0 if offer.cost.input is defined else '—'}} | $0 if offer.cost.output is defined else '—'}} | $0 if offer.cost.cache_read is defined else '—'}} | · T · | View{
"cache_read": 0,
"cache_write": 0,
"input": 0,
"output": 0
} |
 Alibaba Coding Plan | qwen3-max-2026-01-23 | 262.144K | $0 if offer.cost.input is defined else '—'}} | $0 if offer.cost.output is defined else '—'}} | $0 if offer.cost.cache_read is defined else '—'}} | · T · | View{
"cache_read": 0,
"cache_write": 0,
"input": 0,
"output": 0
} |
 OrcaRouter | qwen/qwen3-max | 262.144K | $0.359 if offer.cost.input is defined else '—'}} | $1.434 if offer.cost.output is defined else '—'}} | $0 if offer.cost.cache_read is defined else '—'}} | · T · | View{
"input": 0.359,
"output": 1.434
} |
 OpenRouter | qwen/qwen3-max | 262.144K | $0.78 if offer.cost.input is defined else '—'}} | $3.9 if offer.cost.output is defined else '—'}} | $0.156 if offer.cost.cache_read is defined else '—'}} | · T S | View{
"cache_read": 0.156,
"cache_write": 0.975,
"input": 0.78,
"output": 3.9
} |
 LLM Gateway | qwen3-max | 262.144K | $0.845 if offer.cost.input is defined else '—'}} | $3.38 if offer.cost.output is defined else '—'}} | $0.6 if offer.cost.cache_read is defined else '—'}} | · T · | View{
"cache_read": 0.6,
"cache_write": 3.75,
"input": 0.845,
"output": 3.38
} |
 Alibaba (China) | qwen3-max | 262.144K | $0.861 if offer.cost.input is defined else '—'}} | $3.441 if offer.cost.output is defined else '—'}} | $0 if offer.cost.cache_read is defined else '—'}} | · T · | View{
"input": 0.861,
"output": 3.441
} |
 EmpirioLabs AI | qwen3-max | 256K | $1.08 if offer.cost.input is defined else '—'}} | $5.52 if offer.cost.output is defined else '—'}} | $0 if offer.cost.cache_read is defined else '—'}} | R T S | View{
"input": 1.08,
"output": 5.52,
"tiers": [
{
"input": 2.7,
"output": 13.8,
"tier": {
"size": 128000,
"type": "context"
}
}
]
} |
 Vercel AI Gateway | alibaba/qwen3-max | 262.144K | $1.2 if offer.cost.input is defined else '—'}} | $6 if offer.cost.output is defined else '—'}} | $0.24 if offer.cost.cache_read is defined else '—'}} | · T · | View{
"cache_read": 0.24,
"input": 1.2,
"output": 6
} |
 Abacus | qwen3-max | 131.072K | $1.2 if offer.cost.input is defined else '—'}} | $6 if offer.cost.output is defined else '—'}} | $0 if offer.cost.cache_read is defined else '—'}} | R T · | View{
"input": 1.2,
"output": 6
} |
 Alibaba | qwen3-max | 262.144K | $1.2 if offer.cost.input is defined else '—'}} | $6 if offer.cost.output is defined else '—'}} | $0 if offer.cost.cache_read is defined else '—'}} | · T · | View{
"input": 1.2,
"output": 6
} |
 Deep Infra | Qwen/Qwen3-Max | 256K | $1.2 if offer.cost.input is defined else '—'}} | $6 if offer.cost.output is defined else '—'}} | $0.24 if offer.cost.cache_read is defined else '—'}} | · T S | View{
"cache_read": 0.24,
"input": 1.2,
"output": 6,
"tiers": [
{
"cache_read": 0.48,
"input": 2.4,
"output": 12,
"tier": {
"size": 32000,
"type": "context"
}
},
{
"cache_read": 0.6,
"input": 3,
"output": 15,
"tier": {
"size": 128000,
"type": "context"
}
}
]
} |
 NovitaAI | qwen/qwen3-max | 262.144K | $2.11 if offer.cost.input is defined else '—'}} | $8.45 if offer.cost.output is defined else '—'}} | $0 if offer.cost.cache_read is defined else '—'}} | · T S | View{
"input": 2.11,
"output": 8.45
} |
Published benchmark results
Artificial Analysis Coding Index
vs top 8 models
SciCode
vs top 8 models
Terminal-Bench Hard
vs top 8 models