PRICING

Pricing

Transparent pricing, pay as you go. Every model shares a unified API and unified billing with no hidden fees.

Bytedance

Bytedance AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
Doubao-Seed-1.8
Default
256000 $0.00011429 / 1000 tokens $0.00028571 / 1000 tokens Integration docs
input <=32k,output>200k
256000 $0 / 1000 tokens $0 / 1000 tokens
32k<token<=128K
256000 $0 / 1000 tokens $0 / 1000 tokens
token>128k
256000 $0 / 1000 tokens $0 / 1000 tokens
Cache Hit
256000 $0 / 1000 tokens -

Qwen

Qwen AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
qwen3.5-plus
0<Token<=128K
10000000 $0.000115 / 1000 tokens $0.000688 / 1000 tokens Integration docs
256K<Token<=1M
10000000 $0.000573 / 1000 tokens $0.00344 / 1000 tokens
128K<Token<=256K
10000000 $0.000287 / 1000 tokens $0.00172 / 1000 tokens
qwen3-max
0<Token<=32K
256000 $0.000359 / 1000 tokens $0.001434 / 1000 tokens Integration docs
32K<Token<=128K
256000 $0.000574 / 1000 tokens $0.002294 / 1000 tokens
128K<Token<=256K
256000 $0.001004 / 1000 tokens $0.004014 / 1000 tokens
qwen3-235b-a22b
Default
256000 $0.000287 / 1000 tokens $0.002868 / 1000 tokens Integration docs
qwen3.5-flash
0<Token<=128K
1000000 $2.9E-5 / 1000 tokens $0.000287 / 1000 tokens Integration docs
128K<Token<=256K
1000000 $0.000115 / 1000 tokens $0.001147 / 1000 tokens
256K<Token<=1M
1000000 $0.000172 / 1000 tokens $0.00172 / 1000 tokens
qwen-flash
0<Token<=128K
1000000 $2.2E-5 / 1000 tokens $0.000216 / 1000 tokens Integration docs
256K<Token<=1M
1000000 $0.000173 / 1000 tokens $0.001721 / 1000 tokens
128K<Token<=256K
1000000 $8.7E-5 / 1000 tokens $0.000861 / 1000 tokens
qwen3.5-27b
0<Token<=128K
256000 $8.6E-5 / 1000 tokens $0.000688 / 1000 tokens Integration docs
128K <Token<=256K
256000 $0.000258 / 1000 tokens $0.002064 / 1000 tokens
qwen3.5-35b-a3b
0<Token<=128K
256000 $5.7E-5 / 1000 tokens $0.000459 / 1000 tokens Integration docs
128K <Token<=256K
256000 $0.000229 / 1000 tokens $0.001835 / 1000 tokens
qwen3.6-plus
0<Token<=256K
1000000 $0.000276 / 1000 tokens $0.001651 / 1000 tokens Integration docs
256K<Token<=1M
1000000 $0.001101 / 1000 tokens $0.006602 / 1000 tokens
qwen3-max-preview
0<Token<=32K
256000 $0.000861 / 1000 tokens $0.003441 / 1000 tokens Integration docs
32K<Token<=128K
256000 $0.001434 / 1000 tokens $0.005735 / 1000 tokens
128K<Token<=256K
256000 $0.002151 / 1000 tokens $0.008602 / 1000 tokens
qwen-plus
0<Token<=128K
1000000 $0.000115 / 1000 tokens $0.000287 / 1000 tokens Integration docs
256K<Token<=1M
1000000 $0.000689 / 1000 tokens $0.006881 / 1000 tokens
128K<Token<=256K
1000000 $0.000345 / 1000 tokens $0.002868 / 1000 tokens
qwen-plus-latest
0<Token<=128K
1000000 $0.000115 / 1000 tokens $0.000287 / 1000 tokens Integration docs
256K<Token<=1M
1000000 $0.000689 / 1000 tokens $0.006881 / 1000 tokens
128K<Token<=256K
1000000 $0.000345 / 1000 tokens $0.002868 / 1000 tokens
qwen3-coder-plus
0<Token<=32K
1000000 $0.000574 / 1000 tokens $0.002294 / 1000 tokens Integration docs
32K<Token<=128K
1000000 $0.000861 / 1000 tokens $0.003441 / 1000 tokens
128K<Token<=256K
1000000 $0.001434 / 1000 tokens $0.005735 / 1000 tokens
256K<Token<=1M
1000000 $0.002868 / 1000 tokens $0.028671 / 1000 tokens
qwen-plus-character
Default
32000 $0.000115 / 1000 tokens $0.000287 / 1000 tokens Integration docs
qwen3-coder-next
0<Token<=32K
256000 $0.00014335 / 1000 tokens $0.00057341 / 1000 tokens Integration docs
32K<Token<=128K
256000 $0.00021503 / 1000 tokens $0.00086011 / 1000 tokens
128K<Token<=256K
256000 $0.00035838 / 1000 tokens $0.00143352 / 1000 tokens
qwen3-vl-32b-instruct
Default
128000 $0.000287 / 1000 tokens $0.001147 / 1000 tokens Integration docs
qwen3-vl-32b-thinking
Default
128000 $0.000287 / 1000 tokens $0.002868 / 1000 tokens Integration docs
qwen3-vl-30b-a3b-instruct
Default
128000 $0.000108 / 1000 tokens $0.00043 / 1000 tokens Integration docs
qwen3-vl-30b-a3b-thinking
Default
128000 $0.000108 / 1000 tokens $0.001075 / 1000 tokens Integration docs
qwen3.6-flash
0<Token<=256K
1000000 $0.000165 / 1000 tokens $0.00099 / 1000 tokens Integration docs
256K<Token<=1M
1000000 $0.00066 / 1000 tokens $0.003961 / 1000 tokens
qwen3.6-35b-a3b
Default
256000 $0.000248 / 1000 tokens $0.001485 / 1000 tokens Integration docs
qwen3.5-122b-a10b
0<Token<=128K
256000 $0.000115 / 1000 tokens $0.000917 / 1000 tokens Integration docs
128K <Token<=256K
256000 $0.000287 / 1000 tokens $0.002294 / 1000 tokens
qwen3.5-397b-a17b
0<Token<=128K
256000 $0.000172 / 1000 tokens $0.001032 / 1000 tokens Integration docs
128K <Token<=256K
256000 $0.00043 / 1000 tokens $0.00258 / 1000 tokens
qwen3-coder-flash
0<Token<32K
1000000 $0.000144 / 1000 tokens $0.000574 / 1000 tokens Integration docs
32K<Token<128K
1000000 $0.000574 / 1000 tokens $0.000861 / 1000 tokens
128K<Token<256K
1000000 $0.000359 / 1000 tokens $0.001434 / 1000 tokens
256K<Token<1M
1000000 $0.000717 / 1000 tokens $0.003584 / 1000 tokens
qwen-flash-character
Default
8000 $3.4E-5 / 1000 tokens $0.000203 / 1000 tokens Integration docs
Cache Hit
8000 $7.0E-6 / 1000 tokens -
qwen3.7-max
0<Token≤1M
1000000 $0.000825 / 1000 tokens $0.0024755 / 1000 tokens Integration docs
Input Cache Hit
1000000 $0.00033 / 1000 tokens -
Explicit Cache Creation
1000000 $0.002063 / 1000 tokens -
Explicit Cache Hit
1000000 $0.000165 / 1000 tokens -
code_interpreter
1000000 - $0 / 次
web_extractor
1000000 - $0 / 次
web_search
1000000 - $0.573411 / 次
qwen3.7-plus
Token≤256k
1000000 $0.000276 / 1000 tokens $0.001101 / 1000 tokens Integration docs
256k<Token<1M
1000000 $0.000826 / 1000 tokens $0.003301 / 1000 tokens
Token≤256k Cache Hit
1000000 $5.6E-5 / 1000 tokens -
256k<Token<1M Cache Hit
1000000 $0.000166 / 1000 tokens -
Token≤256k Explicit Cache Creation
1000000 $5.6E-5 / 1000 tokens -
256k<Token<1M Explicit Cache Creation
1000000 $0.001032 / 1000 tokens -
Token≤256k Explicit Cache Hit
1000000 $2.8E-5 / 1000 tokens -
256k<Token<1M Explicit Cache Hit
1000000 $8.3E-5 / 1000 tokens -
code_interpreter
1000000 - $0 / 次
i2i_search
1000000 - $6.881 / 次
t2i_search
1000000 - $3.44 / 次
web_search
1000000 - $0.573411 / 次
qwen3.8-max
Default
1000000 $0.00171429 / 1000 tokens $0.00514286 / 1000 tokens Integration docs
Input Cache Hit
1000000 $0.00021429 / 1000 tokens -
Explicit Cache Creation
1000000 $0.00214286 / 1000 tokens -
Explicit Cache Hit
1000000 $0.00014286 / 1000 tokens -
code_interpreter
1000000 - $0 / 次
web_extractor
1000000 - $0 / 次
web_search
1000000 - $0.57142857 / 次
i2i_search
1000000 - $6.85714286 / 次
t2i_search
1000000 - $3.42857143 / 次
qwen3.7-flash
32k<Token≤256k
1000000 $3.943E-5 / 1000 tokens $0.00015729 / 1000 tokens Integration docs
256k<Token<1M
1000000 $0.000118 / 1000 tokens $0.00047157 / 1000 tokens
32k<Token≤256k Cache Hit
1000000 $8.0E-6 / 1000 tokens -
256k<Token<1M Cache Hit
1000000 $2.371E-5 / 1000 tokens -
32k<Token≤256k Explicit Cache Creation
1000000 $8.0E-6 / 1000 tokens -
256k<Token<1M Explicit Cache Creation
1000000 $0.00014743 / 1000 tokens -
32k<Token≤256k Explicit Cache Hit
1000000 $4.0E-6 / 1000 tokens -
256k<Token<1M Explicit Cache Hit
1000000 $1.186E-5 / 1000 tokens -
code_interpreter
1000000 - $0 / 次
i2i_search
1000000 - $0.983 / 次
t2i_search
1000000 - $0.49142857 / 次
web_search
1000000 - $0.08191586 / 次
Token≤32k
1000000 $3.943E-5 / 1000 tokens $0.00015729 / 1000 tokens
Token≤32k Cache Hit
1000000 $8.0E-6 / 1000 tokens -
Token≤32k Explicit Cache Creation
1000000 $8.0E-6 / 1000 tokens -
Token≤32k Explicit Cache Hit
1000000 $4.0E-6 / 1000 tokens -
qwen3.8-flash
Default
1000000 $0.00023571 / 1000 tokens $0.00070729 / 1000 tokens Integration docs
Cache Hit
1000000 $4.714E-5 / 1000 tokens -
Explicit Cache Creation
1000000 $0.00029471 / 1000 tokens -
Explicit Cache Hit
1000000 $2.357E-5 / 1000 tokens -
code_interpreter
1000000 - $0 / 次
web_extractor
1000000 - $0 / 次
web_search
1000000 - $0.08191586 / 次
i2i_search
1000000 - $0.08191586 / 次
t2i_search
1000000 - $0.08191586 / 次

Deepseek

Deepseek AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
deepseek-v3.2
Default
128000 $7.534E-5 / 1000 tokens $0.00011314 / 1000 tokens Integration docs
Cache Hit
128000 $0.00030135 / 1000 tokens -
Explicit Cache Hit
128000 $0.00030135 / 1000 tokens -
deepseek-v4-flash
Default Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $0.00021429 / 1000 tokens $0.00064286 / 1000 tokens Integration docs
Cache Hit Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $7.14E-6 / 1000 tokens -
Default Peak
09:00-12:00 14:00-18:00
1000000 $0.00042858 / 1000 tokens $0.00128572 / 1000 tokens
Cache Hit Peak
09:00-12:00 14:00-18:00
1000000 $1.428E-5 / 1000 tokens -
Explicit Cache Hit Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $7.14E-6 / 1000 tokens -
Explicit Cache Hit Peak
09:00-12:00 14:00-18:00
1000000 $1.428E-5 / 1000 tokens -
Default Holiday
1000000 $0.00021429 / 1000 tokens $0.00064286 / 1000 tokens
Cache Hit Holiday
1000000 $7.14E-6 / 1000 tokens -
Explicit Cache Hit Holiday
1000000 $7.14E-6 / 1000 tokens -
deepseek-v4-pro
Default Standard
12:00-14:00 00:00-09:00 18:00-00:00
1000000 $0.00064286 / 1000 tokens $0.00192857 / 1000 tokens Integration docs
Cache Hit Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $2.143E-5 / 1000 tokens -
Default Peak
09:00-12:00 14:00-18:00
1000000 $0.00128572 / 1000 tokens $0.00385714 / 1000 tokens
Cache Hit Peak
09:00-12:00 14:00-18:00
1000000 $4.286E-5 / 1000 tokens -
Explicit Cache Hit Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $2.143E-5 / 1000 tokens -
Explicit Cache Hit Peak
09:00-12:00 14:00-18:00
1000000 $4.286E-5 / 1000 tokens -
Default Holiday
1000000 $0.00064286 / 1000 tokens $0.00192857 / 1000 tokens
Cache Hit Holiday
1000000 $2.143E-5 / 1000 tokens -
Explicit Cache Hit Holiday
1000000 $2.143E-5 / 1000 tokens -
deepseek-flash
Default Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $0.00014286 / 1000 tokens $0.00057143 / 1000 tokens Integration docs
Cache Hit Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $2.86E-6 / 1000 tokens -
Default Peak
09:00-12:00 14:00-18:00
1000000 $0.00028572 / 1000 tokens $0.00114286 / 1000 tokens
Cache Hit Peak
09:00-12:00 14:00-18:00
1000000 $5.72E-6 / 1000 tokens -
Explicit Cache Hit Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $2.86E-6 / 1000 tokens -
Explicit Cache Hit Peak
09:00-12:00 14:00-18:00
1000000 $5.72E-6 / 1000 tokens -
Default Holiday
1000000 $0.00014286 / 1000 tokens $0.00057143 / 1000 tokens
Cache Hit Holiday
1000000 $2.86E-6 / 1000 tokens -
Explicit Cache Hit Holiday
1000000 $2.86E-6 / 1000 tokens -
deepseek-v4.1-flash
Default Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $0.00014286 / 1000 tokens $0.00057143 / 1000 tokens Integration docs
Cache hit Standard
00:00-09:00 18:00-00:00 12:00-14:00
1000000 $2.86E-6 / 1000 tokens -

Zhipu

Zhipu AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
glm-4.7
0<Token<=32K
198000 $0.000431 / 1000 tokens $0.002007 / 1000 tokens Integration docs
32K<Token<=200K
198000 $0.000574 / 1000 tokens $0.002294 / 1000 tokens
0<Token<=32K Cache Hit
198000 $8.6E-5 / 1000 tokens -
32K<Token<=200K Cache Hit
198000 $0.000115 / 1000 tokens -
0<Token<=32K Explicit Cache Hit
198000 $8.6E-5 / 1000 tokens -
32K<Token<=200K Explicit Cache Hit
198000 $0.000115 / 1000 tokens -
glm-5
0<Token<=32K
198000 $0.000573 / 1000 tokens $0.00258 / 1000 tokens Integration docs
32K<Token<=200K
198000 $0.00086 / 1000 tokens $0.003154 / 1000 tokens
0<Token<=32K Cache Hit
198000 $0.000115 / 1000 tokens -
32K<Token<=200K Cache Hit
198000 $0.000172 / 1000 tokens -
0<Token<=32K Explicit Cache Hit
198000 $0.000115 / 1000 tokens -
32K<Token<=200K Explicit Cache Hit
198000 $0.000172 / 1000 tokens -
glm-5.1
0<Token<=32K
202000 $0.000825 / 1000 tokens $0.003301 / 1000 tokens Integration docs
32K<Token<=200K
202000 $0.0011 / 1000 tokens $0.003851 / 1000 tokens
0<Token<=32K Cache Hit
202000 $0.000165 / 1000 tokens -
0<Token<=32K Explicit Cache Creation
202000 $0.001031 / 1000 tokens -
0<Token<=32K Explicit Cache Hit
202000 $8.3E-5 / 1000 tokens -
32K<Token<=200K Cache Hit
202000 $0.00022 / 1000 tokens -
32K<Token<=200K Explicit Cache Creation
202000 $0.001375 / 1000 tokens -
32K<Token<=200K Explicit Cache Hit
202000 $0.00011 / 1000 tokens -
glm-5.2
Default
1000000 $0.00114286 / 1000 tokens $0.004 / 1000 tokens Integration docs
Cache Hit
1000000 $0.00028571 / 1000 tokens -
Explicit Cache Hit
1000000 $0.00028571 / 1000 tokens -

Kimi

Kimi AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
kimi-k2.6
Default
256000 $0.0008939 / 1000 tokens $0.0037131 / 1000 tokens Integration docs
Cache Hit
256000 $0.0001788 / 1000 tokens -
Explicit Cache Creation
256000 $0.0011174 / 1000 tokens -
Explicit Cache Hit
256000 $8.94E-5 / 1000 tokens -
kimi-k2.5
Default
256000 $0.000574 / 1000 tokens $0.003011 / 1000 tokens Integration docs
Cache Hit
256000 $0.000115 / 1000 tokens -
Explicit Cache Creation
256000 $0.000718 / 1000 tokens -
Explicit Cache Hit
256000 $5.7E-5 / 1000 tokens -
kimi-k3
Default
1000000 $0.00285714 / 1000 tokens $0.01428571 / 1000 tokens Integration docs
Cache Hit
1000000 $0.00028571 / 1000 tokens -
Explicit Cache Hit
1000000 $0.00028571 / 1000 tokens -
kimi-k2.7-code
Default
256000 $0.00092857 / 1000 tokens $0.00385714 / 1000 tokens Integration docs
Cache Hit
256000 $0.00018571 / 1000 tokens -
Explicit Cache Hit
256000 $8.94E-5 / 1000 tokens -
kimi-k2.7-code-highspeed
Default
256000 $0.00185714 / 1000 tokens $0.00771429 / 1000 tokens Integration docs
Cache Hit
256000 $0.00037143 / 1000 tokens -
Explicit Cache Hit
256000 $0.00037143 / 1000 tokens -

OpenAI

A world-leading AI research organization; the GPT series is the industry benchmark with comprehensive multimodal capabilities.

Model Billing type Context Input price (/kt) Output price (/kt) Action
GPT 5.3 Chat
Default
400000 $0.00175 / 1000 tokens $0.014 / 1000 tokens Integration docs
Cache Hit
400000 $0.00018 / 1000 tokens -
GPT 5.3 Codex
Default
400000 $0.00175 / 1000 tokens $0.014 / 1000 tokens Integration docs
Cache Hit
400000 $0.00018 / 1000 tokens -
GPT 5.4
Token≤272k
1050000 $0.0025 / 1000 tokens $0.015 / 1000 tokens Integration docs
Token>272k
1050000 $0.005 / 1000 tokens $0.0225 / 1000 tokens
Token≤272k cache hit
1050000 $0.00025 / 1000 tokens -
Token>272k cache hit
1050000 $0.0005 / 1000 tokens -
GPT 5.5
Token≤272k
1050000 $0.005 / 1000 tokens $0.03 / 1000 tokens Integration docs
Token≤272k Cache Hit
1050000 $0.0005 / 1000 tokens -
Token>272k
1050000 $0.01 / 1000 tokens $0.045 / 1000 tokens
Token>272k Cache Hit
1050000 $0.001 / 1000 tokens -
GPT 5.4 Mini
Default
400000 $0.00075 / 1000 tokens $0.0045 / 1000 tokens Integration docs
Cache Hit
400000 $8.0E-5 / 1000 tokens -
gpt-5.6-sol
Token≤272k
1050000 $0.005 / 1000 tokens $0.03 / 1000 tokens Integration docs
Token≤272k Cache Hit
1050000 $0.0005 / 1000 tokens -
Token>272k
1050000 $0.01 / 1000 tokens $0.045 / 1000 tokens
Token>272k Cache Hit
1050000 $0.001 / 1000 tokens -
Token≤272k Cache Creation
1050000 $0.00625 / 1000 tokens -
Token>272k Cache Creation
1050000 $0.0125 / 1000 tokens -
gpt-5.6-terra
Token ≤ 272k
1050000 $0.002 / 1000 tokens $0.012 / 1000 tokens Integration docs
Token ≤ 272k cache hit
1050000 $0.0002 / 1000 tokens -
Token > 272k
1050000 $0.004 / 1000 tokens $0.018 / 1000 tokens
Token > 272k cache hit
1050000 $0.0004 / 1000 tokens -
Token ≤ 272k cache creation
1050000 $0.0025 / 1000 tokens -
Token > 272k cache creation
1050000 $0.005 / 1000 tokens -
gpt-5.6-luna
Token≤272k
1050000 $0.0002 / 1000 tokens $0.0012 / 1000 tokens Integration docs
Token≤272k cache hit
1050000 $2.0E-5 / 1000 tokens -
Token>272k
1050000 $0.0004 / 1000 tokens $0.0018 / 1000 tokens
Token>272k cache hit
1050000 $4.0E-5 / 1000 tokens -
Token≤272k cache creation
1050000 $0.00025 / 1000 tokens -
Token>272k cache creation
1050000 $0.0005 / 1000 tokens -
gpt-6-astra
Token≤272k
1050000 $0.01 / 1000 tokens $0.05 / 1000 tokens Integration docs
Token≤272k Cache Hit
1050000 $0.001 / 1000 tokens -
Token>272k
1050000 $0.02 / 1000 tokens $0.075 / 1000 tokens
Token>272k Cache Hit
1050000 $0.002 / 1000 tokens -
Token≤272k Cache Creation
1050000 $0.0125 / 1000 tokens -
Token>272k Cache Creation
1050000 $0.025 / 1000 tokens -
gpt-6.1-sol
Token≤272k
1050000 $0.002 / 1000 tokens $0.01 / 1000 tokens Integration docs
Token≤272k Cache Hit
1050000 $0.0001 / 1000 tokens -
Token>272k
1050000 $0.004 / 1000 tokens $0.015 / 1000 tokens
Token>272k Cache Hit
1050000 $0.0002 / 1000 tokens -
Token≤272k Cache Creation
1050000 $0.0025 / 1000 tokens -
Token>272k Cache Creation
1050000 $0.005 / 1000 tokens -

Google

Google Gemini models feature million-token context windows and industry-leading multimodal capabilities.

Model Billing type Context Input price (/kt) Output price (/kt) Action
gemini-2.5-pro
0<Token<=200K
- $0.00125 / 1000 tokens $0.01 / 1000 tokens Integration docs
200K<Token<=1M
- $0.0025 / 1000 tokens $0.015 / 1000 tokens
gemini-2.5-flash
Default
-
Text$0.0003 / 1000 tokens Image$0.0003 / 1000 tokens Audio$0.001 / 1000 tokens Video$0.0003 / 1000 tokens
Text$0.0025 / 1000 tokens
Integration docs
Cache Hit
-
Text$3.0E-5 / 1000 tokens Image$3.0E-5 / 1000 tokens Video$3.0E-5 / 1000 tokens
Audio Cache Hit
-
Audio$0.0001 / 1000 tokens
gemini-2.5-flash-lite
Default
-
Text$0.0001 / 1000 tokens Image$0.0001 / 1000 tokens Audio$0.0003 / 1000 tokens Video$0.0001 / 1000 tokens
Text$0.0004 / 1000 tokens
Integration docs
Cache Hit
-
Text$1.0E-5 / 1000 tokens Image$1.0E-5 / 1000 tokens Video$1.0E-5 / 1000 tokens
Audio Cache Hit
-
Audio$3.0E-5 / 1000 tokens
gemini-3.1-pro-preview
0<Token<=200K
- $0.002 / 1000 tokens $0.012 / 1000 tokens Integration docs
200K<Token<=1M
- $0.004 / 1000 tokens $0.018 / 1000 tokens
gemini-3.1-flash-lite-preview
Default
-
Text$0.00025 / 1000 tokens Image$0.00025 / 1000 tokens Audio$0.0005 / 1000 tokens Video$0.00025 / 1000 tokens
Text$0.0015 / 1000 tokens
Integration docs
Cache Hit
-
Text$2.5E-5 / 1000 tokens Image$2.5E-5 / 1000 tokens Video$2.5E-5 / 1000 tokens
Audio Cache Hit
-
Audio$5.0E-5 / 1000 tokens
Gemini 3 Flash Preview
Default Mixed Tokens
-
Text$0.0005 / 1000 tokens Image$0.0005 / 1000 tokens Audio$0.001 / 1000 tokens Video$0.0005 / 1000 tokens
Text$0.003 / 1000 tokens
Integration docs
Audio Cache Hit
-
Audio$0.0001 / 1000 tokens
Cache Hit
-
Text$5.0E-5 / 1000 tokens Image$5.0E-5 / 1000 tokens Video$5.0E-5 / 1000 tokens
Text$0.003 / 1000 tokens
Gemini 3.1 Flash Image Preview
Default
-
Text$0.0005 / 1000 tokens Image$0.0005 / 1000 tokens Audio$0.001 / 1000 tokens Video$0.0005 / 1000 tokens
Text$0.003 / 1000 tokens
Integration docs
Gemini 3 Pro Image Preview
Default
-
Text$0.0005 / 1000 tokens Image$0.0005 / 1000 tokens Audio$0.001 / 1000 tokens Video$0.0005 / 1000 tokens
Text$0.003 / 1000 tokens
Integration docs
Gemini 3.5 Flash
Token<=200k
- $0.0015 / 1000 tokens $0.0015 / 1000 tokens Integration docs
Token>200k
- $0.0015 / 1000 tokens $0.0015 / 1000 tokens
Token<=200k Cache Hit
- $0.00015 / 1000 tokens -
Token>200k Cache Hit
- $0.00015 / 1000 tokens -

Anthropic

Anthropic is built around AI safety; the Claude series is widely praised for coding and analysis.

Model Billing type Context Input price (/kt) Output price (/kt) Action
claude-opus-4-6
Per Token
- $0.00514286 / 1000 tokens $0.02571429 / 1000 tokens Integration docs
5m Cache Creation
- $0.00642857 / 1000 tokens -
1h Cache Creation
- $0.01028571 / 1000 tokens -
Cache Hit
- $0.00051429 / 1000 tokens -
claude-opus-4-7
Per Token
- $0.00514286 / 1000 tokens $0.02571429 / 1000 tokens Integration docs
5m Cache Creation
- $0.00642857 / 1000 tokens -
1h Cache Creation
- $0.01028571 / 1000 tokens -
Cache Hit
- $0.00051429 / 1000 tokens -
claude-sonnet-4-6
Per Token
- $0.00308571 / 1000 tokens $0.01542857 / 1000 tokens Integration docs
5m Cache Creation
- $0.00385714 / 1000 tokens -
1h Cache Creation
- $0.00617143 / 1000 tokens -
Cache Hit
- $0.00030857 / 1000 tokens -
claude-opus-4-8
Per Token
- $0.00514286 / 1000 tokens $0.02571429 / 1000 tokens Integration docs
5m Cache Creation
- $0.00642857 / 1000 tokens -
1h Cache Creation
- $0.01028571 / 1000 tokens -
Cache Hit
- $0.00051429 / 1000 tokens -
claude-fable-5
Per Token
- $0.01028571 / 1000 tokens $0.05142857 / 1000 tokens Integration docs
5m Cache Creation
- $0.01285714 / 1000 tokens -
1h Cache Creation
- $0.02057143 / 1000 tokens -
Cache Hit
- $0.00102857 / 1000 tokens -
claude-opus-5-5
Per token
- $0.004 / 1000 tokens $0.02 / 1000 tokens Integration docs
5m cache creation
- $0.005 / 1000 tokens -
1h cache creation
- $0.008 / 1000 tokens -
Cache hit
- $0.0002 / 1000 tokens -
claude-sonnet-5-5
Per token
- $0.002 / 1000 tokens $0.01 / 1000 tokens Integration docs
5-minute cache creation
- $0.0025 / 1000 tokens -
1-hour cache creation
- $0.004 / 1000 tokens -
Cache hit
- $0.0001 / 1000 tokens -
claude-haiku-5-5
Per token < 1M
- $0.0001 / 1000 tokens $0.0005 / 1000 tokens Integration docs
5m cache creation < 1M
- $0.000125 / 1000 tokens -
1h cache creation < 1M
- $0.0002 / 1000 tokens -
Cache hit < 1M
- $1.0E-5 / 1000 tokens -
Per token > 1M
- $0.0005 / 1000 tokens $0.0025 / 1000 tokens
5m cache creation > 1M
- $0.000625 / 1000 tokens -
1h cache creation > 1M
- $0.001 / 1000 tokens -
Cache hit > 1M
- $5.0E-5 / 1000 tokens -

Tencent

Tencent AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
Hy3 preview
Token<16k
256000 $0.00017143 / 1000 tokens $0.00057143 / 1000 tokens Integration docs
Token<16k Cache Hit
256000 $5.714E-5 / 1000 tokens -
16k<=Token<32k
256000 $0.00022857 / 1000 tokens $0.00091429 / 1000 tokens
Token>=32k
256000 $0.00028571 / 1000 tokens $0.00114286 / 1000 tokens
16k<=Token<32k Cache Hit
256000 $8.571E-5 / 1000 tokens -
Token>=32k Cache Hit
256000 $0.00011429 / 1000 tokens -
Token<16k Explicit Cache Hit
256000 $5.714E-5 / 1000 tokens -
16k<=Token<32k Explicit Cache Hit
256000 $8.571E-5 / 1000 tokens -
Token>=32k Explicit Cache Hit
256000 $0.00011429 / 1000 tokens -
hy3
Default
256000 $0.00014286 / 1000 tokens $0.00057143 / 1000 tokens Integration docs
Cache Hit
256000 $3.571E-5 / 1000 tokens -
Explicit Cache Hit
256000 $3.571E-5 / 1000 tokens -

MiniMax

MiniMax is committed to general AI and stands out in text processing.

Model Billing type Context Input price (/kt) Output price (/kt) Action
MiniMax-M2.5
Default
200000 $0.000304 / 1000 tokens $0.001213 / 1000 tokens Integration docs
Cache Hit
200000 $6.1E-5 / 1000 tokens -
MiniMax-M2.5-highspeed
Default
200000 $0.0006 / 1000 tokens $0.0024 / 1000 tokens Integration docs
Cache Hit
200000 $3.0E-5 / 1000 tokens -
Explicit Cache Hit
200000 $3.0E-5 / 1000 tokens -
MiniMax-M2.7
Default
200000 $0.0003 / 1000 tokens $0.0012 / 1000 tokens Integration docs
Cache Hit
200000 $6.0E-5 / 1000 tokens -
Explicit Cache Hit
200000 $6.0E-5 / 1000 tokens -
MiniMax-M2.7-highspeed
Default
200000 $0.0006 / 1000 tokens $0.0024 / 1000 tokens Integration docs
Cache Hit
200000 $6.0E-5 / 1000 tokens -
Explicit Cache Hit
200000 $6.0E-5 / 1000 tokens -
MiniMax-M3
token <= 512k
1000000 $0.0003 / 1000 tokens $0.0012 / 1000 tokens Integration docs
token <= 512k Cache Hit
1000000 $6.0E-5 / 1000 tokens -
token <= 512k Explicit Cache Hit
1000000 $6.0E-5 / 1000 tokens -
token > 512k
1000000 $0.0006 / 1000 tokens $0.0024 / 1000 tokens
token > 512k Cache Hit
1000000 $0.00012 / 1000 tokens -
token > 512k Explicit Cache Hit
1000000 $0.00012 / 1000 tokens -

智谱

智谱 AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
glm-5.3
Default
1000000 $0.00015714 / 1000 tokens $0.00055014 / 1000 tokens Integration docs
Cache Hit
1000000 $3.929E-5 / 1000 tokens -
Explicit Cache Hit
1000000 $3.929E-5 / 1000 tokens -
glm-5.3-flash
Default
1000000 $0.00015714 / 1000 tokens $0.00055014 / 1000 tokens Integration docs
Cache Hit
1000000 $3.929E-5 / 1000 tokens -
Explicit Cache Hit
1000000 $3.929E-5 / 1000 tokens -

百度

百度 AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
ERNIE 5.1
Input ≤ 32k
119000 $0.00015714 / 1000 tokens $0.00055014 / 1000 tokens Integration docs
32k < Input ≤ 128k
119000 $0.00015714 / 1000 tokens $0.00055014 / 1000 tokens
ERNIE 5.0
Input ≤ 32k
119000 $0.00015714 / 1000 tokens $0.00055014 / 1000 tokens Integration docs
32k < Input ≤ 128k
119000 $0.00015714 / 1000 tokens $0.00055014 / 1000 tokens

腾讯云

腾讯云 AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
Hy4 preview
Default
1024000 $0.006 / 1000 tokens $0.018 / 1000 tokens Integration docs
Cache hit
1024000 $0.0003 / 1000 tokens -
Explicit cache hit
1024000 $0.0003 / 1000 tokens -

字节

字节 AI model Advanced language understanding, content generation and complex reasoning.

Model Billing type Context Input price (/kt) Output price (/kt) Action
Doubao-Seed-2.1-pro
Default
1024000 $0.00085714 / 1000 tokens $0.00428571 / 1000 tokens Integration docs
Cache Hit
1024000 $0.00017143 / 1000 tokens -

Need enterprise custom pricing?

High-volume customers can enjoy dedicated discounts and SLA guarantees. Feel free to contact our sales team.

Contact Sales