Context
1M
Max output
131K
Serving providers
10
Cheapest input
$1.65 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
41 t/s
tokens / second
Time to first token
2.57s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| Automation Bench | 0.5 | default | — | |
| CritPt | 20% | default | — | |
| GDPval (normalized)Frozen Aug 18, 2026 | 55% | default | — | |
| GPQA Diamond | 93% | default | — | |
| Humanity's Last Exam | 43% | default | — | |
| Long-Context Reasoning | 78% | default | — | |
| MMMU-Pro | 82% | default | — | |
| Omniscience | 3.4 | default | — | |
| Omniscience Accuracy | 0.3 | default | — | |
| Omniscience Non Hallucination | 0.6 | default | — | |
| SciCode | 53% | default | — | |
| Terminal Bench40 | 0.2 | default | — | |
| TerminalBench v2.1 | 81% | default | — | |
| τ-bench Banking | 51% | default | — |
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $1.65 to $2.00 per 1M tokens across 10 providers, so the dearest route costs 21% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $1.65 | $4.95 | 1 | ||||||||||||||||
Standarddeepinfra/Qwen/Qwen3.8-Max
| |||||||||||||||||||
| Scx AI | $1.65 | $4.99 | 1 | ||||||||||||||||
Standardscx-ai/Qwen3.8-Max
| |||||||||||||||||||
| Aihubmix | $1.69 | $5.07 | 1 | ||||||||||||||||
Standardaihubmix/qwen3.8-max
| |||||||||||||||||||
| Dashscope | $2.00 | $6.00 | 1 | ||||||||||||||||
Standarddashscope/qwen3.8-max
| |||||||||||||||||||
| Fireworks AI | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardfireworks_ai/accounts/fireworks/models/qwen3p8-max
| |||||||||||||||||||
| Novita | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardnovita/qwen/qwen3.8-max
| |||||||||||||||||||
| OpenRouter | $2.00 | $6.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Qwen AI Platform | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardqwen_ai_platform/qwen3.8-max
| |||||||||||||||||||
| Dashscope is dearest at $2.00 / $6.00 | |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 18% since first tracked
Cost calculator
estimate your monthly spend on this model$729
estimated / month
Model IDs
copy the exact identifier for your platformscx-ai/Qwen3.8-Maxdeepinfra/Qwen/Qwen3.8-Maxaihubmix/qwen3.8-maxqwen/qwen3.8-maxdashscope/qwen3.8-maxfireworks_ai/accounts/fireworks/models/qwen3p8-maxnovita/qwen/qwen3.8-maxqwencloud/qwen3.8-maxqwen_ai_platform/qwen3.8-maxalibaba/qwen3.8-max
Frequently asked questions
Qwen3.8 Max pricing, context and availabilityHow much does Qwen3.8 Max cost?
Qwen3.8 Max costs $1.65 per 1M input tokens from DeepInfra, and $4.95 per 1M output tokens from DeepInfra. Across 10 serving providers, input prices range from $1.65 to $2.00 per 1M tokens.
What is the context window of Qwen3.8 Max?
Qwen3.8 Max accepts up to 1M tokens of context and can return up to 131K output tokens.
Which providers serve Qwen3.8 Max?
Qwen3.8 Max is available from 10 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can Qwen3.8 Max do?
Qwen3.8 Max supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other Alibaba models
compare pricing across the Alibaba lineupQwen3 Next 80B A3B Instruct$0.09/1M · 11 providersQwen3 32B$0.08/1M · 10 providersQwen3 Next 80B A3B Thinking$0.14/1M · 10 providersQwen3.6 35B A3B$0.05/1M · 9 providersQwen3 VL 235B A22B Instruct$0.20/1M · 9 providersQwen2.5 Coder 32B Instruct$0.05/1M · 8 providersQwen3 235B A22b Instruct 2507$0.09/1M · 8 providersQwen3.6 27B$0.15/1M · 8 providers
Popular comparisons
head-to-head pages featuring Qwen3.8 Max
Qwen3.8 Max vs Claude Fable 5.1side-by-side pricing & benchmarks Qwen3.8 Max vs Claude Opus 5side-by-side pricing & benchmarks
Qwen3.8 Max vs DeepSeek V4.1 Flashside-by-side pricing & benchmarks Qwen3.8 Max vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
Qwen3.8 Max vs Gemini 3.7 Flashside-by-side pricing & benchmarks Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI