← Model list
Qwen3.7 Max
alibaba·alibaba/qwen3.7-max·GA·Closed·qwen series
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
At a glance
Official price$2.50 / $7.50 per 1M
Cache read $0.50 · Alibaba (China)
Lowest paid$0.825 / $2.48
Merge Gateway Gateway · 3.6× spread
2 more $0 channels
Context1,000,000
⚠ Providers report 256,000–1,048,576; the table below is authoritative
Output limit65,536
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Knowledge cutoff—
Released / updated2026-05-21 / 2026-05-21
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence46.7
Value38
Coding66
Agentic30.9
Output speed201 tok/s
TTFT2.26 s
Cost per task$0.5413
Value formulaIQ 46.7 ÷ min blended $1.238 = 38
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 30 providers28 with public prices · 2 subscription-covered
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Alibaba Token Plan | Gateway | Subscription | $0 | $0 | 1,000,000 | 131,072 | ||
| Alibaba Token Plan (China) | Gateway | Subscription | $0 | $0 | 1,000,000 | 131,072 | ||
| Merge Gateway | Gateway | $0.825 | $2.48 | $0.165 | — | 1,000,000 | 250,000 | |
| Together AI Qwen/Qwen3.7-Max | Cloud | $1.25 | $3.75 | $0.125 | — | 1,000,000 | 500,000 | |
| NovitaAI | Gateway | $1.25 | $3.75 | $0.25 | $1.56 | 1,000,000 | 65,536 | |
| DevPass (LLM Gateway) | Gateway | $1.25 | $3.75 | $0.25 | $3.13 | 1,000,000 | 65,536 | |
| Kilo Gateway | Gateway | $1.25 | $3.75 | $0.125 | $1.56 | 1,000,000 | 131,072 | |
| Pioneer | Gateway | $1.25 | $3.75 | $0.25 | $1.56 | 991,000 ⚠ | 64,000 | |
| OpenRouter | Gateway | $1.48 | $4.42 | $0.295 | $1.84 | 1,000,000 | 131,072 | |
| CrossModel | Gateway | $1.50 | $4.50 | $0.30 | $1.88 | 1,000,000 | 65,536 | |
| Alibaba (China)Official | First-party | $2.50 | $7.50 | $0.50 | $3.13 | 1,000,000 | 65,536 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1Merge Gateway$209.58
2Together AI$302.50
3Kilo Gateway$302.50
4NovitaAI$317.50
5DevPass (LLM Gateway)$317.50
6Pioneer$317.50
15Alibaba (China) · Official$635.00
2 more channels offer $0 (Alibaba Token Plan, Alibaba Token Plan (China)); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to Merge Gateway to save $425.43/mo (67%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark9 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 80.4 | resolved | Source ↗ |
| SWE-Bench Pro | — | 60.6 | resolve rate | Source ↗ |
| SWE-Bench Multilingual | — | 78.3 | resolve rate | Source ↗ |
| Terminal-Bench | harness: Terminus-2 · v2.0 | 69.7 | success rate | Source ↗ |
| GPQA Diamond | — | 92.4 | accuracy | Source ↗ |
| Humanity's Last Exam | — | 41.4 | accuracy | Source ↗ |
| SciCode | — | 53.5 | — | Source ↗ |
| MCP Atlas | — | 76.4 | success rate | Source ↗ |
| NL2Repo | harness: Claude Code | 47.2 | — | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
Toggle (on / off)budget_tokenseffort = noneeffort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = max
4 / 30 providers expose no reasoning control (reasoning_options: []).
Related models
Qwen3.5 0.8Bsame series$0.06 / $0.12Qwen3.5 4Bsame series$0.10 / $0.20Qwen3.8 27B TEEsame series$0.40 / $3.00GLM-5.2cheaper alternative$1.40 / $4.40DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44
Price historyone sample accumulated per data sync
Input listOutput listMin blended