API Pricing

Official API rates, context windows, reasoning features, and prompt cache discounts across mainstream LLMs with verified timestamps

By Provider Table View

搜索模型厂商币种

Provider

Sort

16 records · Billing Unit: Per 1M Tokens · Grouped by Provider (Newest First)

Model & API ID					Official Source
Alibaba
Qwen3.7-MaxCNYReleased N/A CN-BEIJING·`qwen3.7-max` View notes Standard real-time text API; Beijing endpoint; per 1M tokens. Displayed price is the first input band below. 0<Token≤1M, thinking and non-thinking: input CNY 12, output CNY 36. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	¥ 12.00 Cached Input: Not Cataloged	¥ 36.00	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen-MaxCNYReleased N/A CN-BEIJING·`qwen-max` View notes Standard real-time text API; Beijing endpoint; per 1M tokens. Displayed price is the first input band below. no tiered pricing, non-thinking: input CNY 2.4, output CNY 9.6. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	¥ 2.40 Cached Input: Not Cataloged	¥ 9.60	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen3.7-FlashCNYReleased N/A CN-BEIJING·`qwen3.7-flash` View notes Standard real-time text API; Beijing endpoint; per 1M tokens. Displayed price is the first input band below. 0<Token≤32K, thinking and non-thinking: input CNY 0.2, output CNY 0.8; 32K<Token≤256K, thinking and non-thinking: input CNY 0.6, output CNY 2.4; 256K<Token≤1M, thinking and non-thinking: input CNY 1.2, output CNY 4.8. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	¥ 0.20 Cached Input: Not Cataloged	¥ 0.80	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen-PlusUSDReleased N/A SINGAPORE·`qwen-plus` View notes Standard real-time text API; Singapore endpoint, international deployment; per 1M tokens. Displayed price is the first input band below. 0<Token≤256K, non-thinking: input $0.4, output $1.2; 0<Token≤256K, thinking: input $0.4, output $4; 256K<Token≤1M, non-thinking: input $1.2, output $3.6; 256K<Token≤1M, thinking: input $1.2, output $12. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	US$ 0.40 Cached Input: Not Cataloged	US$ 1.20	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen3.8-MaxUSDReleased N/A SINGAPORE·`qwen3.8-max` View notes Standard real-time text API; Singapore endpoint, international deployment; per 1M tokens. Displayed price is the first input band below. 0<Token≤1M, thinking and non-thinking: input $2, output $6. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	US$ 2.00 Cached Input: Not Cataloged	US$ 6.00	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen3.7-FlashUSDReleased N/A SINGAPORE·`qwen3.7-flash` View notes Standard real-time text API; Singapore endpoint, international deployment; per 1M tokens. Displayed price is the first input band below. 0<Token≤32K, thinking and non-thinking: input $0.030, output $0.130; 32K<Token≤256K, thinking and non-thinking: input $0.100, output $0.400; 256K<Token≤1M, thinking and non-thinking: input $0.200, output $0.800. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	US$ 0.03 Cached Input: Not Cataloged	US$ 0.13	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen3.7-PlusUSDReleased N/A SINGAPORE·`qwen3.7-plus` View notes Standard real-time text API; Singapore endpoint, international deployment; per 1M tokens. Displayed price is the first input band below. 0<Token≤256K, thinking and non-thinking: input $0.4, output $1.6; 256K<Token≤1M, thinking and non-thinking: input $1.2, output $4.8. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate. Published list price; the official page currently advertises a limited-time 20% discount separately.	—	US$ 0.40 Cached Input: Not Cataloged	US$ 1.60	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen-MaxUSDReleased N/A SINGAPORE·`qwen-max` View notes Standard real-time text API; Singapore endpoint, international deployment; per 1M tokens. Displayed price is the first input band below. no tiered pricing, non-thinking: input $1.6, output $6.4. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	US$ 1.60 Cached Input: Not Cataloged	US$ 6.40	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen3.8-MaxCNYReleased N/A CN-BEIJING·`qwen3.8-max` View notes Standard real-time text API; Beijing endpoint; per 1M tokens. Displayed price is the first input band below. 0<Token≤1M, thinking and non-thinking: input CNY 12, output CNY 36. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	¥ 12.00 Cached Input: Not Cataloged	¥ 36.00	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen3.8-FlashCNYReleased N/A CN-BEIJING·`qwen3.8-flash` View notes Standard real-time text API; Beijing endpoint; per 1M tokens. Displayed price is the first input band below. 0<Token≤1M, thinking and non-thinking: input CNY 0.8, output CNY 2.7. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	¥ 0.80 Cached Input: Not Cataloged	¥ 2.70	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen-FlashUSDReleased N/A SINGAPORE·`qwen-flash` View notes Standard real-time text API; Singapore endpoint, international deployment; per 1M tokens. Displayed price is the first input band below. 0<Token≤256K, thinking and non-thinking: input $0.05, output $0.4; 256K<Token≤1M, thinking and non-thinking: input $0.25, output $2. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	US$ 0.05 Cached Input: Not Cataloged	US$ 0.40	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen3.8-FlashUSDReleased N/A SINGAPORE·`qwen3.8-flash` View notes Standard real-time text API; Singapore endpoint, international deployment; per 1M tokens. Displayed price is the first input band below. 0<Token≤1M, thinking and non-thinking: input $0.15, output $0.47. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	US$ 0.15 Cached Input: Not Cataloged	US$ 0.47	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen3.7-PlusCNYReleased N/A CN-BEIJING·`qwen3.7-plus` View notes Standard real-time text API; Beijing endpoint; per 1M tokens. Displayed price is the first input band below. 0<Token≤256K, thinking and non-thinking: input CNY 2, output CNY 8; 256K<Token≤1M, thinking and non-thinking: input CNY 6, output CNY 24. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate. Published list price; the official page currently advertises a limited-time 20% discount separately.	—	¥ 2.00 Cached Input: Not Cataloged	¥ 8.00	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen-FlashCNYReleased N/A CN-BEIJING·`qwen-flash` View notes Standard real-time text API; Beijing endpoint; per 1M tokens. Displayed price is the first input band below. 0<Token≤128K, thinking and non-thinking: input CNY 0.15, output CNY 1.5; 128K<Token≤256K, thinking and non-thinking: input CNY 0.6, output CNY 6; 256K<Token≤1M, thinking and non-thinking: input CNY 1.2, output CNY 12. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	¥ 0.15 Cached Input: Not Cataloged	¥ 1.50	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen-PlusCNYReleased N/A CN-BEIJING·`qwen-plus` View notes Standard real-time text API; Beijing endpoint; per 1M tokens. Displayed price is the first input band below. 0<Token≤128K, non-thinking: input CNY 0.8, output CNY 2; 0<Token≤128K, thinking: input CNY 0.8, output CNY 8; 128K<Token≤256K, non-thinking: input CNY 2.4, output CNY 20; 128K<Token≤256K, thinking: input CNY 2.4, output CNY 24; 256K<Token≤1M, non-thinking: input CNY 4.8, output CNY 48; 256K<Token≤1M, thinking: input CNY 4.8, output CNY 64. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	¥ 0.80 Cached Input: Not Cataloged	¥ 2.00	2026/11/01 10:45	Official Source(opens in a new tab)
Qwen3.7-MaxUSDReleased N/A SINGAPORE·`qwen3.7-max` View notes Standard real-time text API; Singapore endpoint, international deployment; per 1M tokens. Displayed price is the first input band below. 0<Token≤1M, thinking and non-thinking: input $2.5, output $7.5. Cache-read price is not independently verified; consult the official context-caching documentation. Batch rates and free quotas are separate.	—	US$ 2.50 Cached Input: Not Cataloged	US$ 7.50	2026/11/01 10:45	Official Source(opens in a new tab)

How to read pricing and model specs?

Grouped by provider by default, sorted newest to oldest by public release date. Release date is not price verification date; uncataloged dates appear at the end. Click column headers to sort by price, context window, or verification date across providers. All token prices are standardized per 1M tokens without currency conversion. Context windows not independently audited are marked as unverified. Actual billing is determined by vendor documentation and timestamps.

Price Changes →