At least one reviewed endpoint supports this feature when true.
Data retention
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.Source for Data retention (opens in a new tab)
Cards also publish batch prices for larger input tiers. Those rates do not establish accepted request limits; confirm the deployed batch contract before relying on them.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.08 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.50
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.04
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.50
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.12
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Batch · Input<=256k
Input(Batch File)1
$0.143
1M tokens
Batch · Input<=256k
Output(Batch File)1
$0.574
1M tokens
Explicit cache · Input<=256k
Explicit Cache Creation2
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read2
$0.028
1M tokens
Batch · Input<=256k
Input(Batch Chat)1
$0.287
1M tokens
Batch · Input<=256k
Output(Batch Chat)1
$1.147
1M tokens
Batch · 256k<Input<=1m
Input(Batch File)3
$0.43
1M tokens
Batch · 256k<Input<=1m
Output(Batch File)3
$1.72
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation4
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read4
$0.083
1M tokens
Batch · 256k<Input<=1m
Input(Batch Chat)3
$0.86
1M tokens
Batch · 256k<Input<=1m
Output(Batch Chat)3
$3.44
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. The batch guide caps context at 256K; larger published price tiers are not verified usable limits. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. The batch guide caps context at 256K; larger published price tiers are not verified usable limits. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.028
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.083
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.028
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.083
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.08 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.50
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.04
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.50
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.12
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.028
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.083
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.028
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.083
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.08 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.50
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.04
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.50
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.12
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.028
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.083
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.028
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.083
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.028
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.083
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.028
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.083
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate. Cached input price: $0.056 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=256k
Explicit Cache Creation1
$0.344
1M tokens
Explicit cache · Input<=256k
Explicit Cache Read1
$0.028
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation2
$1.032
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read2
$0.083
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. Qwen3.7-Plus is included in the published ZDR roster, subject to enterprise approval, an enabled workspace, eligible non-mainland region, and covered APIs/features. It is not enabled by default.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Caching reviewed 14 Oct 2026
Alibaba Model Studio · Germany (Frankfurt) · Global
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Caching reviewed 14 Oct 2026
Alibaba Model Studio · Germany (Frankfurt) · Global
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Reuse identical prefixes for implicit caching. For explicit caching, set cache_control type ephemeral; up to four markers. Modes do not combine.Source for How to enable it (opens in a new tab)
Implicit reads, explicit reads and explicit writes have separate published prices. Output remains billed; batch and caching discounts do not stack.Source for Billing rules (opens in a new tab)
Published regional list rates, excluding promotions. K=1,000 and M=1,000,000. Total input length selects the rate for the whole request. Cached input is implicit-cache reads. Explicit cache and batch charges are separate.
Alternative billing mode for this endpoint. Whole-request input tier: Input<=256k. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Alternative billing mode for this endpoint. Whole-request input tier: 256k<Input<=1m. Explicit cache writes and reads replace the corresponding input-token charge. Batch and cache discounts do not stack; published rounded rates are preserved.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Caching reviewed 14 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
Inference from release-specific Alibaba-managed API documentation and the reviewed official Qwen public-weight inventory. No matching weights are published for this named hosted release in that inventory. Public Qwen3.8-Flash-Next, Qwen3.8-2.4T-A95B and older Qwen-Omni checkpoints are separate identities and are excluded; this is not a blanket classification of the Qwen family.
