QVQ Max API Pricing
Alibaba · released Mar 25, 2025 · 131K context · API model ID qvq-max
QVQ Max by Alibaba API pricing: $1.20 per 1M input tokens and $4.80 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).
Prices
| Price | USD per 1M tokens |
|---|---|
| Input | $1.20 |
| Output | $4.80 |
| Cache read | Not published |
| Cache write | Not published |
Alibaba's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation
Estimated monthly cost
$1,080
per month
- per day
- $36.00
- per request
- $0.0036
Cannot estimate: a needed price is not published.
Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.
Monthly cost by workload
| Workload | Per month |
|---|---|
| Chatbot1,000 in / 500 out tokens, 10,000 requests a day | $1,080/mo |
| RAG8,000 in / 500 out tokens, 5,000 requests a day | $1,800/mo |
| Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input | $2,088/mo |
Context and capabilities
- Context
- 131,072 tokens
- Max output
- 8,192 tokens
- Input
- text, image
- Output
- text
- Knowledge cutoff
- April 2024
- Open weights
- No
- Tool calling
- Yes
- Reasoning
- Yes
- Structured outputs
- No
Capabilities and limits as listed by models.dev.
Similarly priced models
- Muse Spark 1.3 · $1.25 in / $4.25 out
- DeepSeek V4 Pro · $1.32 in / $3.96 out
- Gemini 3.8 Flash · $0.75 in / $3.75 out
- Qwen3.8 Max · $2.00 in / $6.00 out
Price history
No price changes since we started tracking on Oct 8, 2026.
Questions
- How much does QVQ Max cost per month?
- For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, QVQ Max costs about $1,080 per month at Alibaba's list prices ($1.20 per 1M input tokens, $4.80 per 1M output tokens).
- Does QVQ Max support prompt caching?
- No cache read price is published for QVQ Max.
- How long is QVQ Max's context window?
- QVQ Max accepts up to 131,072 tokens (131K) of context and returns up to 8,192 tokens per response.