Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / Qwen3.7

Qwen3.7-Max

Text-only proprietary model for coding, tool use and extended agent workflows.

availableClosed weightsText generationCodingAgents
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
17 of 21 specification fields collected
Input token limit991.8K991,808 tokens
Maximum output131.1K131,072 tokens
Input / 1M tokens$2.50Alibaba Model Studio · Singapore · International
Output / 1M tokens$7.50USD · observed 12 Oct 2026

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
1,000,000 tokensSource for Context / input limit (opens in a new tab)
Tool calling
SupportedSource for Tool calling (opens in a new tab)

Available on at least one reviewed endpoint when true. Regional differences appear under access and pricing.

Structured output
SupportedSource for Structured output (opens in a new tab)

Available on at least one reviewed endpoint when true. Regional differences appear under access and pricing.

Streaming
SupportedSource for Streaming (opens in a new tab)

OpenAI-compatible Chat Completions streaming; endpoint-specific availability should be checked before deployment.

Batch processing
SupportedSource for Batch processing (opens in a new tab)

Available on at least one reviewed endpoint when true. Regional differences appear under access and pricing.

Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)

Available on at least one reviewed endpoint when true. Regional differences appear under access and pricing.

Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
SupportedSource for Context caching (opens in a new tab)

Available on at least one reviewed endpoint when true. Regional differences appear under access and pricing.

API aliases
qwen3.7-max, qwen3.7-max-2026-05-20Source for API aliases (opens in a new tab)
Search grounding
SupportedSource for Search grounding (opens in a new tab)

Available on at least one reviewed endpoint when true. Regional differences appear under access and pricing.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Alibaba Model Studio · Singapore · International

Provider source (opens in a new tab)
API model ID
qwen3.7-max
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
Singapore / International deployment scope
Published request quota
600 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
1,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$2.50
OUTPUT / 1M TOKENS$7.50

USD list rates for Singapore / International. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: $0.50 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$3.1251M tokens
Explicit cacheExplicit cache read1$0.251M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · China (Beijing)

Provider source (opens in a new tab)
API model ID
qwen3.7-max
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
China (Beijing)
Published request quota
30000 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
5,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for China (Beijing). Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: $0.33 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
BatchInput(Batch File)1$0.8251M tokens
BatchOutput(Batch File)1$2.4751M tokens
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens
BatchInput(Batch Chat)1$1.651M tokens
BatchOutput(Batch Chat)1$4.9511M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · Germany (Frankfurt) · Global

Provider source (opens in a new tab)
API model ID
qwen3.7-max
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
Germany (Frankfurt) / Global deployment scope
Published request quota
30000 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
5,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for Germany (Frankfurt) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: $0.33 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · US (Virginia) · Global

Provider source (opens in a new tab)
API model ID
qwen3.7-max
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
US (Virginia) / Global deployment scope
Published request quota
30000 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
10,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for US (Virginia) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: $0.33 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · US (Virginia) · US

Provider source (opens in a new tab)
API model ID
qwen3.7-max
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
US (Virginia) / US deployment scope
Published request quota
600 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
1,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$2.50
OUTPUT / 1M TOKENS$7.50

USD list rates for US (Virginia) / US. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: $0.50 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$3.1251M tokens
Explicit cacheExplicit cache read1$0.251M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · Japan (Tokyo) · Global

Provider source (opens in a new tab)
API model ID
qwen3.7-max
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
Japan (Tokyo) / Global deployment scope
Published request quota
600 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
1,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for Japan (Tokyo) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: $0.33 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · Hong Kong (China) · Global

Provider source (opens in a new tab)
API model ID
qwen3.7-max
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
Hong Kong (China) / Global deployment scope
Published request quota
30000 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
5,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for Hong Kong (China) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: $0.33 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · Singapore · International

Provider source (opens in a new tab)
API model ID
qwen3.7-max-2026-05-20
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
Singapore / International deployment scope
Published request quota
60 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
1,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$2.50
OUTPUT / 1M TOKENS$7.50

USD list rates for Singapore / International. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: not collected.

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$3.1251M tokens
Explicit cacheExplicit cache read1$0.251M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · China (Beijing)

Provider source (opens in a new tab)
API model ID
qwen3.7-max-2026-05-20
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
China (Beijing)
Published request quota
600 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
1,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for China (Beijing). Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: not collected.

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · Germany (Frankfurt) · Global

Provider source (opens in a new tab)
API model ID
qwen3.7-max-2026-05-20
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
Germany (Frankfurt) / Global deployment scope
Published request quota
600 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
1,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for Germany (Frankfurt) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: not collected.

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · US (Virginia) · Global

Provider source (opens in a new tab)
API model ID
qwen3.7-max-2026-05-20
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
US (Virginia) / Global deployment scope
Published request quota
600 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
1,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for US (Virginia) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: not collected.

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · Japan (Tokyo) · Global

Provider source (opens in a new tab)
API model ID
qwen3.7-max-2026-05-20
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
Japan (Tokyo) / Global deployment scope
Published request quota
60 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
1,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for Japan (Tokyo) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: not collected.

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Alibaba Model Studio · Hong Kong (China) · Global

Provider source (opens in a new tab)
API model ID
qwen3.7-max-2026-05-20
Access
OpenAI-compatible Chat Completions or DashScope, with a regional workspace API key. Listed scope describes this price/capability configuration; account eligibility must be checked.
Regions
Hong Kong (China) / Global deployment scope
Published request quota
600 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
1,000,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.65
OUTPUT / 1M TOKENS$4.951

USD list rates for Hong Kong (China) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion. Cached input price: not collected.

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Explicit cacheExplicit cache write1$2.0631M tokens
Explicit cacheExplicit cache read1$0.1651M tokens

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Alibaba Model Studio · Singapore · International

qwen3.7-max
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache + automatic implicit cacheSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.50 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache write2Explicit cache$3.125 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read2Explicit cache$0.25 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. USD list rates for Singapore / International. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion.
  2. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · China (Beijing)

qwen3.7-max
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache + automatic implicit cacheSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.33 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache write2Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read2Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. USD list rates for China (Beijing). Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion.
  2. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · Germany (Frankfurt) · Global

qwen3.7-max
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache + automatic implicit cacheSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.33 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache write2Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read2Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. USD list rates for Germany (Frankfurt) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion.
  2. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · US (Virginia) · Global

qwen3.7-max
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache + automatic implicit cacheSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.33 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache write2Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read2Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. USD list rates for US (Virginia) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion.
  2. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · US (Virginia) · US

qwen3.7-max
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache + automatic implicit cacheSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.50 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache write2Explicit cache$3.125 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read2Explicit cache$0.25 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. USD list rates for US (Virginia) / US. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion.
  2. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · Japan (Tokyo) · Global

qwen3.7-max
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache + automatic implicit cacheSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.33 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache write2Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read2Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. USD list rates for Japan (Tokyo) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion.
  2. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · Hong Kong (China) · Global

qwen3.7-max
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache + automatic implicit cacheSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.33 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache write2Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read2Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. USD list rates for Hong Kong (China) / Global. Cached input means implicit cache reads. Separate explicit-cache and batch charges are listed below. Published card prices are retained without currency conversion.
  2. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · Singapore · International

qwen3.7-max-2026-05-20
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache; implicit rate not collectedSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Explicit cache write1Explicit cache$3.125 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read1Explicit cache$0.25 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · China (Beijing)

qwen3.7-max-2026-05-20
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache; implicit rate not collectedSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Explicit cache write1Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read1Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · Germany (Frankfurt) · Global

qwen3.7-max-2026-05-20
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache; implicit rate not collectedSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Explicit cache write1Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read1Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · US (Virginia) · Global

qwen3.7-max-2026-05-20
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache; implicit rate not collectedSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Explicit cache write1Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read1Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · Japan (Tokyo) · Global

qwen3.7-max-2026-05-20
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache; implicit rate not collectedSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Explicit cache write1Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read1Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Alibaba Model Studio · Hong Kong (China) · Global

qwen3.7-max-2026-05-20
Documented
Support evidence (opens in a new tab)
How it works
Explicit cache; implicit rate not collectedSource for How it works (opens in a new tab)
Lifetime & refresh
Explicit: 5 minutes, renewed on hit. Implicit: no fixed guaranteed lifetime.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Explicit: cache_control type ephemeral, up to four markers. Wait for the creation request to finish. Implicit caching is automatic.Source for How to enable it (opens in a new tab)
Usage fields
Inspect the API usage cache fields; field names depend on API, region and model.Source for Usage fields (opens in a new tab)
Billing rules
Implicit reads, explicit reads and explicit creation have separate published rates. Output remains charged.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Explicit and implicit modes are mutually exclusive. Batch and cache discounts do not stack. Identical prefixes and eligible deployment scope are required.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Explicit cache write1Explicit cache$2.063 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache read1Explicit cache$0.165 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Alternative billing mode for this same endpoint. Explicit creation replaces normal input billing for written tokens; explicit reads replace input billing for matching tokens. Batch prices are separate and do not stack with cache discounts.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

The Qwen team explicitly describes Qwen3.7-Max as proprietary. The model card documents these release IDs and aliases; this classification does not extend to later open-weight Qwen3.8 releases.

Classification evidence (opens in a new tab)

Lifecycle dates

Released20 May 2026Source (opens in a new tab)

Sources reviewed