Qwen3.7-Max vs DeepSeek V4 Pro
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
Qwen3.7-MaxIntro price
by Alibaba
2 providers:
Alibaba $2.50/$7.50
Together $1.25/$3.75
|
by DeepSeek
3 providers:
DeepSeek $0.435/$0.870
Fireworks $1.74/$3.48
Together $1.74/$3.48
|
|---|---|---|
| Overview | ||
| Status | Current flagship | Current mid tier |
| Released | May 20, 2026 | Apr 24, 2026 |
| Pricing per million tokens | ||
| Input | $2.50/Mtok | $0.435/Mtok |
| Output | $7.50/Mtok | $0.870/Mtok |
| Blended avg | $5.00/Mtok | $0.652/Mtok |
| Cached input | $0.250/Mtok | $0.004/Mtok |
| Specifications | ||
| Context window | 1M tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks sources: Artificial Analysis, Alibaba, Qwen model card / Vellum LLM Leaderboard | ||
| GPQA Diamond | 68 vendor | 90.1 |
| SWE-Bench Verified | 45 vendor | 50 |
| Humanity's Last Exam | 25 vendor | 48.2 |
| ARC-AGI 2 | 28 vendor | 30 |
| AIME 2025 | 70 vendor | 75 |
| MMMLU | 80 vendor | 82 |
| BFCL | 68 vendor | 72 |
| HumanEval | 84 vendor | 80.6 |
| MATH 500 | 76 vendor | 80 |
| Avg benchmark score | — | 71.5 |
| Perf / dollar | — | 109.6 |
| LiveCodeBench | — | 93.5 |
| MCP Atlas | — | 73.6 |
| BrowseComp | — | 83.4 |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 46 | 44.3 |
| AA Agentic Index | 30.6 | 36.4 |
| AA-Omniscience Index (−100–100) | 14.1 | -10 |
| GDPval-AA v2 | 1271.8 ELO | 1305.9 ELO |
| LMSYS Chatbot Arena | — | 1457.1 ELO |
| Providers | ||
| Available from |
Alibaba — $2.50/$7.50/Mtok
Together — $1.25/$3.75/Mtok
|
DeepSeek — $0.435/$0.870/Mtok
Fireworks — $1.74/$3.48/Mtok
Together — $1.74/$3.48/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Qwen3.7-Max | DeepSeek V4 Pro | Savings |
|---|---|---|---|
| 1M tokens | $5 | $0.65 | $4.35 (87%) |
| 10M tokens | $50 | $6.53 | $43.48 (87%) |
| 100M tokens | $500 | $65.25 | $434.75 (87%) |
| 1000M tokens | $5000 | $652.5 | $4347.5 (87%) |
The cheaper option here — DeepSeek V4 Pro costs $0.652/Mtok blended on DeepSeek.
Summary
Qwen3.7-Max by Alibaba costs $2.50/Mtok input and $7.50/Mtok output, with a 1M-token context window. It supports text input and is available from 2 providers.
DeepSeek V4 Pro by DeepSeek costs $0.435/Mtok input and $0.870/Mtok output, with a 1M-token context window. It supports text input and is available from 3 providers.
On a blended cost basis, DeepSeek V4 Pro is 86.9% cheaper than Qwen3.7-Max.
The two aren't directly comparable on average benchmark score: DeepSeek V4 Pro has published per-benchmark results, while Qwen3.7-Max does not yet — it is measured today on independent composites (see the table above).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.