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. This release is not named in the current ZDR roster; do not assume zero retention.Source for Data retention (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. Cached input price: $0.006 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=32k
Explicit Cache Creation1
$0.038
1M tokens
Explicit cache · Input<=32k
Explicit Cache Read1
$0.003
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Creation2
$0.125
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Read2
$0.01
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation3
$0.25
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read3
$0.02
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=32k. 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: 32k<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. This release is not named in the current ZDR roster; do not assume zero retention.
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: $0.006 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=32k
Explicit Cache Creation1
$0.034
1M tokens
Explicit cache · Input<=32k
Explicit Cache Read1
$0.003
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Creation2
$0.103
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Read2
$0.008
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation3
$0.206
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read3
$0.017
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=32k. 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: 32k<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. This release is not named in the current ZDR roster; do not assume zero retention.
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: $0.006 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=32k
Explicit Cache Creation1
$0.034
1M tokens
Explicit cache · Input<=32k
Explicit Cache Read1
$0.003
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Creation2
$0.103
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Read2
$0.008
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation3
$0.206
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read3
$0.017
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=32k. 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: 32k<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. This release is not named in the current ZDR roster; do not assume zero retention.
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: $0.006 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=32k
Explicit Cache Creation1
$0.034
1M tokens
Explicit cache · Input<=32k
Explicit Cache Read1
$0.003
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Creation2
$0.103
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Read2
$0.008
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation3
$0.206
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read3
$0.017
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=32k. 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: 32k<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. This release is not named in the current ZDR roster; do not assume zero retention.
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: $0.006 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=32k
Explicit Cache Creation1
$0.034
1M tokens
Explicit cache · Input<=32k
Explicit Cache Read1
$0.003
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Creation2
$0.103
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Read2
$0.008
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation3
$0.206
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read3
$0.017
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=32k. 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: 32k<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. This release is not named in the current ZDR roster; do not assume zero retention.
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: $0.006 / 1M tokens (base tier).
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Explicit cache · Input<=32k
Explicit Cache Creation1
$0.034
1M tokens
Explicit cache · Input<=32k
Explicit Cache Read1
$0.003
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Creation2
$0.103
1M tokens
Explicit cache · 32k<Input<=256k
Explicit Cache Read2
$0.008
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Creation3
$0.206
1M tokens
Explicit cache · 256k<Input<=1m
Explicit Cache Read3
$0.017
1M tokens
Rate conditions
Alternative billing mode for this endpoint. Whole-request input tier: Input<=32k. 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: 32k<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. This release is not named in the current ZDR roster; do not assume zero retention.
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<=32k. 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: 32k<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<=32k. 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: 32k<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<=32k. 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: 32k<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<=32k. 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: 32k<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<=32k. 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: 32k<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<=32k. 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: 32k<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.
