Today's price · per 1M tokens
Input
$0.400
per 1M tokens
Output
$1.60
per 1M tokens
Blended
$0.700
blended $/1M — 3:1 weighted input:output
Overview
Alibaba's current-generation Qwen3.7 mid tier on Model Studio. $0.40/$1.60 per 1M tokens up to 256K context; the 256K–1M tier is billed at $1.20/$4.80. Thinking and non-thinking modes bill at the same output rate. 1M-token context, text-only.
Capabilities
struck through = not supportedBenchmark performance
accuracy % · higher is betterWe hold no per-benchmark accuracy scores for this model yet, so it has no accuracy average. That is a gap in our coverage, not a sign the model is untested — independent evaluators often publish a composite index for a new model long before releasing its per-benchmark numbers. The percentile above is its standing across the independent composites below.
- AA Intelligence Index: 39.4 (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA Agentic Index: 20.7 (Tool use, planning, autonomy)
- AA-Omniscience Index: 1.1 (−100–100)
- LMSYS Chatbot Arena: 1457.8 ELO (Human preference)
- Ranks #57 of 150 comparably-measured models by percentile score, across 4 independent measurements
- Ranks #29 of 150 comparably-tested models by normalized performance per dollar
Source: Artificial Analysis · updated Aug 6, 2026 · See full rankings →
Specifications
- Provider
- Alibaba
- Context window
- 1M tokens
- Modality
- text
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- May 26, 2026
- Status
- Current
- Last updated
- Aug 6, 2026
- Tags
Availability verified: Aug 6, 2026 — listed on Alibaba's own page