Model marketplace模型广场

Available models可用模型

Browse models by brand. All registered users have access, with normal usage billing.按品牌厂商浏览模型，所有注册用户均可调用，正常按量扣费。

All models, open to every registered user所有注册用户，畅享全部已上架模型

No top-up threshold for model access. Usage is billed normally. Eligible top-ups receive bonus credits.模型使用无充值门槛，调用正常按量扣费；符合活动条件的充值可获赠额外额度。

Model pricing模型计价

Text model rates are shown per 1 million input and output tokens. Image prices are per generated image; video prices are per generated second and may vary by resolution.文本模型按每百万输入/输出 Token 展示费率；图片按生成张数计费；视频按生成秒数计费，并按分辨率显示对应单价。

anthropic

anthropic/claude-fable-5

Anthropic

Model: anthropic/claude-fable-5

$9.5 / $47.5 per 1M tokens每百万 Token
Cache read: $9.5/1M · Cache write: $11.875/1M · 1h cache write: $19/1M缓存读取：$9.5/百万 Token · 缓存写入：$11.875/百万 Token · 1小时缓存写入：$19/百万 Token

anthropic/claude-haiku-4.5

Anthropic

Model: anthropic/claude-haiku-4.5

$0.95 / $4.75 per 1M tokens每百万 Token
Cache read: $0.95/1M · Cache write: $1.1875/1M · 1h cache write: $1.9/1M缓存读取：$0.95/百万 Token · 缓存写入：$1.1875/百万 Token · 1小时缓存写入：$1.9/百万 Token

anthropic/claude-opus-4.8

Anthropic

Model: anthropic/claude-opus-4.8

$4.75 / $23.75 per 1M tokens每百万 Token
Cache read: $4.75/1M · Cache write: $5.9375/1M · 1h cache write: $9.5/1M缓存读取：$4.75/百万 Token · 缓存写入：$5.9375/百万 Token · 1小时缓存写入：$9.5/百万 Token

anthropic/claude-opus-4.8-fast

Anthropic

Model: anthropic/claude-opus-4.8-fast

$9.5 / $47.5 per 1M tokens每百万 Token
Cache read: $9.5/1M · Cache write: $11.875/1M · 1h cache write: $19/1M缓存读取：$9.5/百万 Token · 缓存写入：$11.875/百万 Token · 1小时缓存写入：$19/百万 Token

anthropic/claude-sonnet-5

Anthropic

Model: anthropic/claude-sonnet-5

$1.9 / $9.5 per 1M tokens每百万 Token
Cache read: $1.9/1M · Cache write: $2.375/1M · 1h cache write: $3.8/1M缓存读取：$1.9/百万 Token · 缓存写入：$2.375/百万 Token · 1小时缓存写入：$3.8/百万 Token

anthropic/claude-fable-5.1

Anthropic

Model: anthropic/claude-fable-5.1

$9.5 / $47.5 per 1M tokens每百万 Token
Cache read: $9.5/1M · Cache write: $11.875/1M · 1h cache write: $19/1M缓存读取：$9.5/百万 Token · 缓存写入：$11.875/百万 Token · 1小时缓存写入：$19/百万 Token

DeepSeek

deepseek-ai/DeepSeek-OCR

DeepSeek

Model: deepseek-ai/DeepSeek-OCR

$0 / $0 per 1M tokens每百万 Token

deepseek-ai/DeepSeek-V4-Flash

DeepSeek

Model: deepseek-ai/DeepSeek-V4-Flash

$0.039767 / $0.079534 per 1M tokens每百万 Token
Cache read: $0.039767/1M缓存读取：$0.039767/百万 Token

deepseek-chat

DeepSeek

Model: deepseek-chat

$0.24453 / $0.977265 per 1M tokens每百万 Token
Cache read: $0.24453/1M缓存读取：$0.24453/百万 Token

DeepSeek-R1-0528

DeepSeek

DeepSeek R1 0528 reasoning model.

$0.475 / $2.04 per 1M tokens每百万 Token

deepseek-reasoner

DeepSeek

Model: deepseek-reasoner

$0.475 / $2.0425 per 1M tokens每百万 Token
Cache read: $0.475/1M缓存读取：$0.475/百万 Token

deepseek-v3.2

DeepSeek

Model: deepseek-v3.2

$0.266 / $0.399 per 1M tokens每百万 Token
Cache read: $0.266/1M缓存读取：$0.266/百万 Token

deepseek-v3.2-1222

DeepSeek

DeepSeek V3.2 1222 for chat and reasoning.

$0.266 / $0.399 per 1M tokens每百万 Token
Cache read: $0.266/1M缓存读取：$0.266/百万 Token

DeepSeek-V3.2-Pro

DeepSeek

Model: DeepSeek-V3.2-Pro

$0.266 / $0.399 per 1M tokens每百万 Token
Cache read: $0.266/1M缓存读取：$0.266/百万 Token

deepseek-v3.2-standard

DeepSeek

DeepSeek V3.2 Standard for chat and reasoning.

$0.266 / $0.399 per 1M tokens每百万 Token
Cache read: $0.266/1M缓存读取：$0.266/百万 Token

deepseek-v4-flash

DeepSeek

Model: deepseek-v4-flash

$0.039767 / $0.079534 per 1M tokens每百万 Token
Cache read: $0.039767/1M缓存读取：$0.039767/百万 Token

deepseek-v4-flash-0731

DeepSeek

DeepSeek V4 Flash 0731 for fast reasoning.

$0.0855 / $0.171 per 1M tokens每百万 Token

deepseek-v4-flash-0731-new

DeepSeek

DeepSeek V4 Flash 0731 New for fast reasoning.

$0.01026 / $1.216 per 1M tokens每百万 Token
Cache read: $0.01026/1M缓存读取：$0.01026/百万 Token

deepseek-v4-pro

DeepSeek

Model: deepseek-v4-pro

$0.19836 / $0.39672 per 1M tokens每百万 Token
Cache read: $0.19836/1M缓存读取：$0.19836/百万 Token

deepseek-v4-pro-0813

DeepSeek

DeepSeek V4 Pro 0813 for advanced reasoning.

$0.627 / $1.881 per 1M tokens每百万 Token
Cache read: $0.627/1M · saturday, sunday: $0.627/$1.881 per 1M input/output · cache read $0.627/1M · UTC 00:00–01:00 monday, tuesday, wednesday, thursday, friday: $0.627/$1.881 per 1M input/output · cache read $0.627/1M · UTC 01:00–04:00 monday, tuesday, wednesday, thursday, friday: $1.254/$3.762 per 1M input/output · cache read $1.254/1M · UTC 04:00–06:00 monday, tuesday, wednesday, thursday, friday: $0.627/$1.881 per 1M input/output · cache read $0.627/1M · UTC 06:00–10:00 monday, tuesday, wednesday, thursday, friday: $1.254/$3.762 per 1M input/output · cache read $1.254/1M · UTC 10:00–24:00 monday, tuesday, wednesday, thursday, friday: $0.627/$1.881 per 1M input/output · cache read $0.627/1M缓存读取：$0.627/百万 Token · saturday, sunday：输入/输出 $0.627/$1.881 每百万 Token · 缓存读取 $0.627/百万 Token · UTC 00:00–01:00 monday, tuesday, wednesday, thursday, friday：输入/输出 $0.627/$1.881 每百万 Token · 缓存读取 $0.627/百万 Token · UTC 01:00–04:00 monday, tuesday, wednesday, thursday, friday：输入/输出 $1.254/$3.762 每百万 Token · 缓存读取 $1.254/百万 Token · UTC 04:00–06:00 monday, tuesday, wednesday, thursday, friday：输入/输出 $0.627/$1.881 每百万 Token · 缓存读取 $0.627/百万 Token · UTC 06:00–10:00 monday, tuesday, wednesday, thursday, friday：输入/输出 $1.254/$3.762 每百万 Token · 缓存读取 $1.254/百万 Token · UTC 10:00–24:00 monday, tuesday, wednesday, thursday, friday：输入/输出 $0.627/$1.881 每百万 Token · 缓存读取 $0.627/百万 Token

deepseek-v4-pro-0817

DeepSeek

DeepSeek V4 Pro 0817 for advanced reasoning.

$0.413 / $0.827 per 1M tokens每百万 Token

Doubao

doubao-seedream-4.0

Doubao

Doubao Seedream 4.0 image generation; billed per image.

$0.07 per image每张
Gen Studio reference base price: $0.07/image. Same USD price for the same configuration.Gen Studio 创作参考基础价：$0.07/张；同规格美元基础价一致。

doubao-seedream-4.5

Doubao

Doubao Seedream 4.5 image generation; billed per image.

$0.08 per image每张
Gen Studio reference base price: $0.08/image. Same USD price for the same configuration.Gen Studio 创作参考基础价：$0.08/张；同规格美元基础价一致。

Doubao-seedream-5.0-lite

Doubao

Doubao Seedream 5.0 Lite image generation; billed per image.

$0.07 per image每张
Gen Studio reference base price: $0.07/image. Same USD price for the same configuration.Gen Studio 创作参考基础价：$0.07/张；同规格美元基础价一致。

doubao-seedream-5.0-pro

Doubao

Doubao Seedream 5.0 Pro image generation; billed per image.

$0.183 per image每张

flowbar

flowbar-free

Other / 其他

Model: flowbar-free

$0 / $0 per 1M tokens每百万 Token

GLM

glm-5

GLM / Z.ai

Model: glm-5

$0.57 / $1.824 per 1M tokens每百万 Token
Cache read: $0.57/1M缓存读取：$0.57/百万 Token

glm-5.1

GLM / Z.ai

Model: glm-5.1

$0.91637 / $2.88002 per 1M tokens每百万 Token
Cache read: $0.91637/1M缓存读取：$0.91637/百万 Token

glm-5.2

GLM / Z.ai

GLM 5.2 for chat and reasoning.

$0.3895 / $3.7905 per 1M tokens每百万 Token
Cache read: $0.3895/1M缓存读取：$0.3895/百万 Token

glm-5.3

GLM / Z.ai

GLM 5.3 for advanced chat and reasoning.

$0.210805 / $3.2205 per 1M tokens每百万 Token
Cache read: $0.210805/1M缓存读取：$0.210805/百万 Token

Pro/zai-org/GLM-5

GLM / Z.ai

Model: Pro/zai-org/GLM-5

$0.902 / $2.42 per 1M tokens每百万 Token

Pro/zai-org/GLM-5.1

GLM / Z.ai

Model: Pro/zai-org/GLM-5.1

$0.91637 / $2.88002 per 1M tokens每百万 Token
Cache read: $0.91637/1M缓存读取：$0.91637/百万 Token

z-ai/glm-5.2

GLM / Z.ai

Model: z-ai/glm-5.2

$0.3895 / $3.7905 per 1M tokens每百万 Token
Cache read: $0.3895/1M缓存读取：$0.3895/百万 Token

google

google/gemini-2.5-flash

Google

Model: google/gemini-2.5-flash

$0.285 / $2.375 per 1M tokens每百万 Token
Cache read: $0.285/1M · Cache write: $0.079166666666666635/1M缓存读取：$0.285/百万 Token · 缓存写入：$0.079166666666666635/百万 Token

google/gemini-2.5-pro

Google

Model: google/gemini-2.5-pro

$1.1875 / $9.5 per 1M tokens每百万 Token
Cache read: $1.1875/1M · Cache write: $0.35625/1M · Input context > 200,000: $2.375/$14.25 per 1M input/output · cache read $2.375/1M缓存读取：$1.1875/百万 Token · 缓存写入：$0.35625/百万 Token · 输入上下文超过 200,000 Token：输入/输出 $2.375/$14.25 每百万 Token · 缓存读取 $2.375/百万 Token

google/gemini-3.1-flash-lite

Google

Model: google/gemini-3.1-flash-lite

$0.2375 / $1.425 per 1M tokens每百万 Token
Cache read: $0.2375/1M · Cache write: $0.079166666666666635/1M缓存读取：$0.2375/百万 Token · 缓存写入：$0.079166666666666635/百万 Token

google/gemini-3.1-pro-preview

Google

Model: google/gemini-3.1-pro-preview

$1.9 / $11.4 per 1M tokens每百万 Token
Cache read: $1.9/1M · Cache write: $0.35625/1M · Input context > 200,000: $3.8/$17.1 per 1M input/output · cache read $3.8/1M缓存读取：$1.9/百万 Token · 缓存写入：$0.35625/百万 Token · 输入上下文超过 200,000 Token：输入/输出 $3.8/$17.1 每百万 Token · 缓存读取 $3.8/百万 Token

google/gemini-3.5-flash

Google

Model: google/gemini-3.5-flash

$1.425 / $8.55 per 1M tokens每百万 Token
Cache read: $1.425/1M · Cache write: $0.079166666666666635/1M缓存读取：$1.425/百万 Token · 缓存写入：$0.079166666666666635/百万 Token

google/gemini-3.8-flash

Google

Model: google/gemini-3.8-flash

$0.7125 / $3.5625 per 1M tokens每百万 Token
Cache read: $0.7125/1M · Cache write: $0.039583333333333365/1M缓存读取：$0.7125/百万 Token · 缓存写入：$0.039583333333333365/百万 Token

google/gemini-3.7-flash

Google

Model: google/gemini-3.7-flash

$0.7125 / $3.5625 per 1M tokens每百万 Token
Cache read: $0.7125/1M · Cache write: $0.039583333333333365/1M缓存读取：$0.7125/百万 Token · 缓存写入：$0.039583333333333365/百万 Token

Kimi / Moonshot

Kimi-K2

Kimi / Moonshot

Kimi K2 for long-context chat and reasoning.

$0.541 / $2.18 per 1M tokens每百万 Token

Kimi-K2-Thinking

Kimi / Moonshot

Kimi K2 Thinking for complex reasoning workloads.

$0.57 / $2.38 per 1M tokens每百万 Token

kimi-k2.5

Kimi / Moonshot

Model: kimi-k2.5

$0.4275 / $2.1375 per 1M tokens每百万 Token
Cache read: $0.4275/1M缓存读取：$0.4275/百万 Token

kimi-k2.6

Kimi / Moonshot

Model: kimi-k2.6

$0.4124425 / $1.7366 per 1M tokens每百万 Token
Cache read: $0.4124425/1M缓存读取：$0.4124425/百万 Token

kimi-k3

Kimi / Moonshot

Kimi K3 for long-context chat and reasoning.

$0.63061 / $9.5 per 1M tokens每百万 Token
Cache read: $0.63061/1M缓存读取：$0.63061/百万 Token

moonshotai/kimi-k3

Kimi / Moonshot

Model: moonshotai/kimi-k3

$0.63061 / $9.5 per 1M tokens每百万 Token
Cache read: $0.63061/1M缓存读取：$0.63061/百万 Token

Pro/moonshotai/Kimi-K2.6

Kimi / Moonshot

Model: Pro/moonshotai/Kimi-K2.6

$0.4124425 / $1.7366 per 1M tokens每百万 Token
Cache read: $0.4124425/1M缓存读取：$0.4124425/百万 Token

kwaipilot

kwaipilot/kat-coder-pro-v2.5

kwaipilot

Model: kwaipilot/kat-coder-pro-v2.5

$0.703 / $2.81 per 1M tokens每百万 Token

meta

meta-llama/llama-4-maverick

meta-llama

Model: meta-llama/llama-4-maverick

$0.178125 / $0.619875 per 1M tokens每百万 Token
Cache read: $0.178125/1M缓存读取：$0.178125/百万 Token

MiniMax

minimax-m2.5

MiniMax

Model: minimax-m2.5

$0.2565 / $1.026 per 1M tokens每百万 Token
Cache read: $0.2565/1M缓存读取：$0.2565/百万 Token

minimax-m2.7

MiniMax

Model: minimax-m2.7

$0.1995 / $0.798 per 1M tokens每百万 Token
Cache read: $0.1995/1M缓存读取：$0.1995/百万 Token

minimax-m3

MiniMax

MiniMax M3 for chat and reasoning.

$0.285 / $1.14 per 1M tokens每百万 Token
Cache read: $0.285/1M缓存读取：$0.285/百万 Token

minimax/minimax-m3

MiniMax

Model: minimax/minimax-m3

$0.285 / $1.14 per 1M tokens每百万 Token
Cache read: $0.285/1M缓存读取：$0.285/百万 Token

mistral

mistralai/mistral-large

mistralai

Model: mistralai/mistral-large

$1.9 / $5.7 per 1M tokens每百万 Token
Cache read: $1.9/1M缓存读取：$1.9/百万 Token

nvidia

nvidia/nemotron-3-ultra-550b-a55b

nvidia

Model: nvidia/nemotron-3-ultra-550b-a55b

$0.57 / $2.28 per 1M tokens每百万 Token
Cache read: $0.57/1M缓存读取：$0.57/百万 Token

openai

openai/gpt-3.5-turbo

OpenAI

Model: openai/gpt-3.5-turbo

$0.475 / $1.425 per 1M tokens每百万 Token
Cache read: $0.475/1M缓存读取：$0.475/百万 Token

openai/gpt-4.1-mini

OpenAI

Model: openai/gpt-4.1-mini

$0.38 / $1.52 per 1M tokens每百万 Token
Cache read: $0.38/1M缓存读取：$0.38/百万 Token

openai/gpt-4.1-nano

OpenAI

Model: openai/gpt-4.1-nano

$0.095 / $0.38 per 1M tokens每百万 Token
Cache read: $0.095/1M缓存读取：$0.095/百万 Token

openai/gpt-4o

OpenAI

Model: openai/gpt-4o

$2.375 / $9.5 per 1M tokens每百万 Token
Cache read: $2.375/1M缓存读取：$2.375/百万 Token

openai/gpt-4o-mini

OpenAI

Model: openai/gpt-4o-mini

$0.1425 / $0.57 per 1M tokens每百万 Token
Cache read: $0.1425/1M缓存读取：$0.1425/百万 Token

openai/gpt-5-image

OpenAI

Model: openai/gpt-5-image

$9.5 / $9.5 per 1M tokens每百万 Token
Cache read: $9.5/1M缓存读取：$9.5/百万 Token

openai/gpt-5-mini

OpenAI

Model: openai/gpt-5-mini

$0.2375 / $1.9 per 1M tokens每百万 Token
Cache read: $0.2375/1M缓存读取：$0.2375/百万 Token

openai/gpt-5-pro

OpenAI

Model: openai/gpt-5-pro

$14.25 / $114 per 1M tokens每百万 Token
Cache read: $14.25/1M缓存读取：$14.25/百万 Token

openai/gpt-5.1-chat

OpenAI

Model: openai/gpt-5.1-chat

$1.19 / $9.5 per 1M tokens每百万 Token

openai/gpt-5.5

OpenAI

Model: openai/gpt-5.5

$4.75 / $28.5 per 1M tokens每百万 Token
Cache read: $4.75/1M · Input context > 272,000: $9.5/$42.75 per 1M input/output · cache read $9.5/1M缓存读取：$4.75/百万 Token · 输入上下文超过 272,000 Token：输入/输出 $9.5/$42.75 每百万 Token · 缓存读取 $9.5/百万 Token

openai/gpt-5.5-pro

OpenAI

Model: openai/gpt-5.5-pro

$28.5 / $171 per 1M tokens每百万 Token
Cache read: $28.5/1M · Input context > 272,000: $57/$256.5 per 1M input/output缓存读取：$28.5/百万 Token · 输入上下文超过 272,000 Token：输入/输出 $57/$256.5 每百万 Token

openai/gpt-5.6-luna

OpenAI

Model: openai/gpt-5.6-luna

$0.19 / $1.14 per 1M tokens每百万 Token
Cache read: $0.19/1M · Cache write: $0.2375/1M · Input context > 272,000: $0.38/$1.71 per 1M input/output · cache read $0.38/1M; cache write $0.475/1M缓存读取：$0.19/百万 Token · 缓存写入：$0.2375/百万 Token · 输入上下文超过 272,000 Token：输入/输出 $0.38/$1.71 每百万 Token · 缓存读取 $0.38/百万 Token; 缓存写入 $0.475/百万 Token

openai/gpt-5.6-sol

OpenAI

Model: openai/gpt-5.6-sol

$1.9 / $9.5 per 1M tokens每百万 Token
Cache read: $1.9/1M · Cache write: $2.375/1M · Input context > 272,000: $3.8/$14.25 per 1M input/output · cache read $3.8/1M; cache write $4.75/1M缓存读取：$1.9/百万 Token · 缓存写入：$2.375/百万 Token · 输入上下文超过 272,000 Token：输入/输出 $3.8/$14.25 每百万 Token · 缓存读取 $3.8/百万 Token; 缓存写入 $4.75/百万 Token

openai/gpt-5.6-terra

OpenAI

Model: openai/gpt-5.6-terra

$1.9 / $11.4 per 1M tokens每百万 Token
Cache read: $1.9/1M · Cache write: $2.375/1M · Input context > 272,000: $3.8/$17.1 per 1M input/output · cache read $3.8/1M; cache write $4.75/1M缓存读取：$1.9/百万 Token · 缓存写入：$2.375/百万 Token · 输入上下文超过 272,000 Token：输入/输出 $3.8/$17.1 每百万 Token · 缓存读取 $3.8/百万 Token; 缓存写入 $4.75/百万 Token

openai/o1-pro

OpenAI

Model: openai/o1-pro

$142.5 / $570 per 1M tokens每百万 Token
Cache read: $142.5/1M缓存读取：$142.5/百万 Token

openai/o3-deep-research

OpenAI

Model: openai/o3-deep-research

$9.5 / $38 per 1M tokens每百万 Token

openai/o3-mini

OpenAI

Model: openai/o3-mini

$1.045 / $4.18 per 1M tokens每百万 Token
Cache read: $1.045/1M缓存读取：$1.045/百万 Token

openai/o3-pro

OpenAI

Model: openai/o3-pro

$19 / $76 per 1M tokens每百万 Token
Cache read: $19/1M缓存读取：$19/百万 Token

openai/gpt-6-astra

OpenAI

Model: openai/gpt-6-astra

$9.5 / $47.5 per 1M tokens每百万 Token
Cache read: $9.5/1M · Cache write: $11.875/1M · Input context > 272,000: $19/$71.25 per 1M input/output · cache read $19/1M; cache write $23.75/1M缓存读取：$9.5/百万 Token · 缓存写入：$11.875/百万 Token · 输入上下文超过 272,000 Token：输入/输出 $19/$71.25 每百万 Token · 缓存读取 $19/百万 Token; 缓存写入 $23.75/百万 Token

openai/gpt-6-astra-pro

OpenAI

Model: openai/gpt-6-astra-pro

$9.5 / $47.5 per 1M tokens每百万 Token
Cache read: $9.5/1M · Cache write: $11.875/1M · Input context > 272,000: $19/$71.25 per 1M input/output · cache read $19/1M; cache write $23.75/1M缓存读取：$9.5/百万 Token · 缓存写入：$11.875/百万 Token · 输入上下文超过 272,000 Token：输入/输出 $19/$71.25 每百万 Token · 缓存读取 $19/百万 Token; 缓存写入 $23.75/百万 Token

perplexity

perplexity/sonar

perplexity

Model: perplexity/sonar

$0.95 / $0.95 per 1M tokens每百万 Token
Cache read: $0.95/1M · Request fee: $0.00475缓存读取：$0.95/百万 Token · 每次请求费：$0.00475

perplexity/sonar-pro-search

perplexity

Model: perplexity/sonar-pro-search

$2.85 / $14.25 per 1M tokens每百万 Token
Cache read: $2.85/1M · Request fee: $0.0171缓存读取：$2.85/百万 Token · 每次请求费：$0.0171

Qwen / Alibaba Cloud

happyhorse-1.0-i2v

Qwen / Alibaba

HappyHorse 1.0 image-to-video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：720p $0.28 per second每秒
Gen Studio default example: 720p · 5 s · $1.4/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $1.4/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

happyhorse-1.0-r2v-20260618

Qwen / Alibaba

HappyHorse 1.0 reference-to-video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：720p $0.28 per second每秒
Gen Studio default example: 720p · 5 s · $1.4/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $1.4/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

happyhorse-1.0-t2v

Qwen / Alibaba

HappyHorse 1.0 text-to-video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：720p $0.28 per second每秒
Gen Studio default example: 720p · 5 s · $1.4/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $1.4/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

happyhorse-1.1-i2v

Qwen / Alibaba

HappyHorse 1.1 image-to-video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：720p $0.28 per second每秒
Gen Studio default example: 720p · 5 s · $1.4/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $1.4/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

happyhorse-1.1-r2v

Qwen / Alibaba

HappyHorse 1.1 reference-to-video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：720p $0.28 per second每秒
Gen Studio default example: 720p · 5 s · $1.4/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $1.4/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

happyhorse-1.1-t2v

Qwen / Alibaba

HappyHorse 1.1 text-to-video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：720p $0.28 per second每秒
Gen Studio default example: 720p · 5 s · $1.4/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $1.4/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

qwen-image-edit-max

Qwen / Alibaba

Qwen Image Edit Max; billed per edited image.

$0.16 per image每张
Gen Studio reference base price: $0.16/image. Same USD price for the same configuration.Gen Studio 创作参考基础价：$0.16/张；同规格美元基础价一致。

qwen-image-edit-plus

Qwen / Alibaba

Qwen Image Edit Plus; billed per edited image.

$0.07 per image每张
Gen Studio reference base price: $0.07/image. Same USD price for the same configuration.Gen Studio 创作参考基础价：$0.07/张；同规格美元基础价一致。

qwen-vl-chat

Qwen / Alibaba

Qwen VL Chat for visual conversation.

$0.215 / $0.646 per 1M tokens每百万 Token

Qwen/Qwen3-32B

Qwen / Alibaba

Model: Qwen/Qwen3-32B

$0.076 / $0.266 per 1M tokens每百万 Token
Cache read: $0.076/1M缓存读取：$0.076/百万 Token

qwen/qwen3-coder

Qwen / Alibaba

Model: qwen/qwen3-coder

$0.285 / $0.95 per 1M tokens每百万 Token
Cache read: $0.285/1M缓存读取：$0.285/百万 Token

Qwen/Qwen3-Coder-30B-A3B-Instruct

Qwen / Alibaba

Model: Qwen/Qwen3-Coder-30B-A3B-Instruct

$0.0665 / $0.266 per 1M tokens每百万 Token
Cache read: $0.0665/1M缓存读取：$0.0665/百万 Token

Qwen/Qwen3.6-27B

Qwen / Alibaba

Model: Qwen/Qwen3.6-27B

$0.304 / $3.04 per 1M tokens每百万 Token
Cache read: $0.304/1M缓存读取：$0.304/百万 Token

qwen/qwen3.7-max

Qwen / Alibaba

Model: qwen/qwen3.7-max

$1.4 / $4.2 per 1M tokens每百万 Token

qwen/qwen3.7-plus

Qwen / Alibaba

Model: qwen/qwen3.7-plus

$0.304 / $1.22 per 1M tokens每百万 Token

Qwen2.5-72B-Instruct

Qwen / Alibaba

Qwen2.5 72B Instruct model.

$0.342 / $0.38 per 1M tokens每百万 Token

qwen2.5-vl-72b-instruct

Qwen / Alibaba

Qwen2.5 VL 72B Instruct for visual understanding.

$0.76 / $0.95 per 1M tokens每百万 Token
Cache read: $0.76/1M缓存读取：$0.76/百万 Token

qwen3-235b-a22b-instruct-2507

Qwen / Alibaba

Qwen3 235B A22B Instruct 2507 model.

$0.142 / $0.568 per 1M tokens每百万 Token

qwen3-235b-a22b-thinking-2507

Qwen / Alibaba

Qwen3 235B A22B Thinking 2507 reasoning model.

$0.2185 / $2.185 per 1M tokens每百万 Token
Cache read: $0.2185/1M缓存读取：$0.2185/百万 Token

qwen3-30b-a3b

Qwen / Alibaba

Qwen3 30B A3B model.

$0.114 / $0.475 per 1M tokens每百万 Token
Cache read: $0.114/1M缓存读取：$0.114/百万 Token

qwen3-coder-480b-a35b-instruct

Qwen / Alibaba

Qwen3 Coder 480B A35B Instruct for advanced coding.

$0.285 / $0.95 per 1M tokens每百万 Token
Cache read: $0.285/1M缓存读取：$0.285/百万 Token

qwen3-max

Qwen / Alibaba

Qwen3 Max for advanced chat and reasoning.

$0.741 / $3.705 per 1M tokens每百万 Token
Cache read: $0.741/1M · Cache write: $0.92625/1M · Input context > 32,000: $1.482/$7.41 per 1M input/output · cache read $1.482/1M; cache write $1.8525/1M · Input context > 128,000: $1.8525/$9.2625 per 1M input/output · cache read $1.8525/1M; cache write $2.315625/1M缓存读取：$0.741/百万 Token · 缓存写入：$0.92625/百万 Token · 输入上下文超过 32,000 Token：输入/输出 $1.482/$7.41 每百万 Token · 缓存读取 $1.482/百万 Token; 缓存写入 $1.8525/百万 Token · 输入上下文超过 128,000 Token：输入/输出 $1.8525/$9.2625 每百万 Token · 缓存读取 $1.8525/百万 Token; 缓存写入 $2.315625/百万 Token

qwen3-vl-235b-a22b-instruct

Qwen / Alibaba

Qwen3 VL 235B A22B Instruct for multimodal understanding.

$0.1995 / $1.805 per 1M tokens每百万 Token
Cache read: $0.1995/1M缓存读取：$0.1995/百万 Token

qwen3-vl-30b-a3b-instruct

Qwen / Alibaba

Qwen3 VL 30B A3B Instruct multimodal model.

$0.1425 / $0.57 per 1M tokens每百万 Token
Cache read: $0.1425/1M缓存读取：$0.1425/百万 Token

Qwen3.5-35B-A3B

Qwen / Alibaba

Model: Qwen3.5-35B-A3B

$0.133 / $0.95 per 1M tokens每百万 Token

qwen3.5-35b-a3b

Qwen / Alibaba

Qwen 3.5 35B A3B model.

$0.154375 / $1.235 per 1M tokens每百万 Token
Cache read: $0.154375/1M缓存读取：$0.154375/百万 Token

Qwen3.5-397B-A17B-Pro

Qwen / Alibaba

Model: Qwen3.5-397B-A17B-Pro

$0.5225 / $3.325 per 1M tokens每百万 Token
Cache read: $0.5225/1M缓存读取：$0.5225/百万 Token

qwen3.6-35b-a3b

Qwen / Alibaba

Qwen3.6 35B A3B for chat and reasoning.

$0.1425 / $0.95 per 1M tokens每百万 Token
Cache read: $0.1425/1M缓存读取：$0.1425/百万 Token

qwen3.6-flash

Qwen / Alibaba

Model: qwen3.6-flash

$0.178125 / $1.06875 per 1M tokens每百万 Token
Cache read: $0.178125/1M · Cache write: $0.22265625/1M · Input context > 256,000: $0.7125/$2.85 per 1M input/output · cache write $0.890625/1M缓存读取：$0.178125/百万 Token · 缓存写入：$0.22265625/百万 Token · 输入上下文超过 256,000 Token：输入/输出 $0.7125/$2.85 每百万 Token · 缓存写入 $0.890625/百万 Token

qwen3.6-plus

Qwen / Alibaba

Model: qwen3.6-plus

$0.30875 / $1.8525 per 1M tokens每百万 Token
Cache read: $0.30875/1M · Cache write: $0.3859375/1M · Input context > 256,000: $1.235/$3.705 per 1M input/output · cache write $1.54375/1M缓存读取：$0.30875/百万 Token · 缓存写入：$0.3859375/百万 Token · 输入上下文超过 256,000 Token：输入/输出 $1.235/$3.705 每百万 Token · 缓存写入 $1.54375/百万 Token

qwen3.8-max

Qwen / Alibaba

Qwen 3.8 Max flagship model.

$1.9 / $5.7 per 1M tokens每百万 Token
Cache read: $1.9/1M缓存读取：$1.9/百万 Token

text-embedding-v3

Qwen / Alibaba

Text Embedding V3 multilingual vector model.

$0.0665 / $0 per 1M tokens每百万 Token
Cache read: $0.0665/1M缓存读取：$0.0665/百万 Token

text-embedding-v4

Qwen / Alibaba

Text Embedding V4 multilingual vector model.

$0.0665 / $0 per 1M tokens每百万 Token
Cache read: $0.0665/1M缓存读取：$0.0665/百万 Token

wan2.2-kf2v-flash

Qwen / Alibaba

Wan 2.2 keyframe-to-video Flash; billed per generated second.

480P $0.0304 · 720P $0.0609 · 1080P $0.146 per second每秒

wan2.6-r2v

Qwen / Alibaba

Wan 2.6 reference-to-video; billed per generated second.

720P $0.183 · 1080P $0.304 per second每秒

wan2.6-r2v-flash

Qwen / Alibaba

Wan 2.6 reference-to-video Flash with audio; billed per generated second.

720P $0.0913 · 1080P $0.152 per second每秒

wan2.7-i2v

Qwen / Alibaba

Wan 2.7 image-to-video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：720p $0.19 · 1080p $0.31 per second每秒
Gen Studio default example: 720p · 5 s · $0.95/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $0.95/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

wan2.7-image

Qwen / Alibaba

Wan 2.7 image generation and editing; billed per image.

$0.07 per image每张
Gen Studio reference base price: $0.07/image. Same USD price for the same configuration.Gen Studio 创作参考基础价：$0.07/张；同规格美元基础价一致。

wan2.7-image-pro

Qwen / Alibaba

Wan 2.7 Image Pro generation and editing; billed per image.

$0.16 per image每张
Gen Studio reference base price: $0.16/image. Same USD price for the same configuration.Gen Studio 创作参考基础价：$0.16/张；同规格美元基础价一致。

wan2.7-r2v

Qwen / Alibaba

Wan 2.7 reference-to-video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：720p $0.19 · 1080p $0.31 per second每秒
Gen Studio default example: 720p · 5 s · $0.95/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $0.95/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

wan2.7-t2v

Qwen / Alibaba

Wan 2.7 text-to-video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：720p $0.19 · 1080p $0.31 per second每秒
Gen Studio default example: 720p · 5 s · $0.95/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $0.95/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

wan3.0-video

Qwen / Alibaba

Wan 3.0 Video; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：480p $0.1 · 720p $0.19 · 1080p $0.37 per second每秒
Gen Studio default example: 720p · 5 s · $0.95/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $0.95/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

wan3.0-video-prime

Qwen / Alibaba

Wan 3.0 Video Prime; billed per generated second.

Gen Studio reference base rate: Gen Studio 创作参考基础价：480p $0.14 · 720p $0.28 · 1080p $0.55 per second每秒
Gen Studio default example: 720p · 5 s · $1.4/job. Native API rates are not yet aligned; this is not a native API price.Gen Studio 默认示例：720p · 5 秒 · $1.4/次。原生 API 费率尚未对齐，此价格不代表原生 API 扣费。

sakana

sakana/fugu-ultra

sakana

Model: sakana/fugu-ultra

$4.75 / $28.5 per 1M tokens每百万 Token
Cache read: $4.75/1M · Input context > 272,000: $9.5/$42.75 per 1M input/output · cache read $9.5/1M缓存读取：$4.75/百万 Token · 输入上下文超过 272,000 Token：输入/输出 $9.5/$42.75 每百万 Token · 缓存读取 $9.5/百万 Token

stepfun

stepfun/step-3.7-flash

stepfun

Model: stepfun/step-3.7-flash

$0.19 / $1.0925 per 1M tokens每百万 Token
Cache read: $0.19/1M缓存读取：$0.19/百万 Token

tencent

tencent/hy3

Tencent

Model: tencent/hy3

$0.078375 / $0.3135 per 1M tokens每百万 Token
Cache read: $0.078375/1M · UTC 00:00–16:00: $0.1254/$0.5016 per 1M input/output · cache read $0.1254/1M · UTC 16:00–24:00: $0.078375/$0.3135 per 1M input/output · cache read $0.078375/1M缓存读取：$0.078375/百万 Token · UTC 00:00–16:00：输入/输出 $0.1254/$0.5016 每百万 Token · 缓存读取 $0.1254/百万 Token · UTC 16:00–24:00：输入/输出 $0.078375/$0.3135 每百万 Token · 缓存读取 $0.078375/百万 Token

xai

x-ai/grok-4.20

xAI

Model: x-ai/grok-4.20

$1.1875 / $2.375 per 1M tokens每百万 Token
Cache read: $1.1875/1M · Input context > 200,000: $2.375/$4.75 per 1M input/output · cache read $2.375/1M缓存读取：$1.1875/百万 Token · 输入上下文超过 200,000 Token：输入/输出 $2.375/$4.75 每百万 Token · 缓存读取 $2.375/百万 Token

x-ai/grok-4.5

xAI

Model: x-ai/grok-4.5

$1.9 / $5.7 per 1M tokens每百万 Token
Cache read: $1.9/1M · Input context > 200,000: $3.8/$11.4 per 1M input/output · cache read $3.8/1M缓存读取：$1.9/百万 Token · 输入上下文超过 200,000 Token：输入/输出 $3.8/$11.4 每百万 Token · 缓存读取 $3.8/百万 Token

x-ai/grok-4.6

xAI

Model: x-ai/grok-4.6

$1.9 / $5.7 per 1M tokens每百万 Token
Cache read: $1.9/1M · Input context > 200,000: $3.8/$11.4 per 1M input/output · cache read $3.8/1M缓存读取：$1.9/百万 Token · 输入上下文超过 200,000 Token：输入/输出 $3.8/$11.4 每百万 Token · 缓存读取 $3.8/百万 Token
Token pricing table / Token 价格表 (104)

Snapshot / 快照：2026-10-02. USD per 1M tokens / 每百万 token 美元价。Source / 来源：live pricing catalog. Confirm current rates before use / 使用前确认实时费率。

Token model rates / 模型费率
Model / 模型Input / 输入Output / 输出Access / 使用权限
anthropic/claude-fable-5$9.5$47.5All registered users / 所有注册用户
anthropic/claude-fable-5.1$9.5$47.5All registered users / 所有注册用户
anthropic/claude-haiku-4.5$0.95$4.75All registered users / 所有注册用户
anthropic/claude-opus-4.8$4.75$23.75All registered users / 所有注册用户
anthropic/claude-opus-4.8-fast$9.5$47.5All registered users / 所有注册用户
anthropic/claude-sonnet-5$1.9$9.5All registered users / 所有注册用户
deepseek-ai/DeepSeek-OCR$0$0All registered users / 所有注册用户
deepseek-ai/DeepSeek-V4-Flash$0.039767$0.079534All registered users / 所有注册用户
deepseek-chat$0.24453$0.977265All registered users / 所有注册用户
DeepSeek-R1-0528$0.475$2.0425All registered users / 所有注册用户
deepseek-reasoner$0.475$2.0425All registered users / 所有注册用户
deepseek-v3.2$0.266$0.399All registered users / 所有注册用户
deepseek-v3.2-1222$0.266$0.399All registered users / 所有注册用户
DeepSeek-V3.2-Pro$0.266$0.399All registered users / 所有注册用户
deepseek-v3.2-standard$0.266$0.399All registered users / 所有注册用户
deepseek-v4-flash$0.039767$0.079534All registered users / 所有注册用户
deepseek-v4-flash-0731$0.0855$0.171All registered users / 所有注册用户
deepseek-v4-flash-0731-new$0.01026$1.216All registered users / 所有注册用户
deepseek-v4-pro$0.19836$0.39672All registered users / 所有注册用户
deepseek-v4-pro-0813$0.627$1.881All registered users / 所有注册用户
deepseek-v4-pro-0817$0.41325$0.8265All registered users / 所有注册用户
flowbar-free$0$0All registered users / 所有注册用户
glm-5$0.57$1.824All registered users / 所有注册用户
glm-5.1$0.91637$2.88002All registered users / 所有注册用户
glm-5.2$0.3895$3.7905All registered users / 所有注册用户
glm-5.3$0.210805$3.2205All registered users / 所有注册用户
google/gemini-2.5-flash$0.285$2.375All registered users / 所有注册用户
google/gemini-2.5-pro$1.1875$9.5All registered users / 所有注册用户
google/gemini-3.1-flash-lite$0.2375$1.425All registered users / 所有注册用户
google/gemini-3.1-pro-preview$1.9$11.4All registered users / 所有注册用户
google/gemini-3.5-flash$1.425$8.55All registered users / 所有注册用户
google/gemini-3.7-flash$0.7125$3.5625All registered users / 所有注册用户
google/gemini-3.8-flash$0.7125$3.5625All registered users / 所有注册用户
Kimi-K2$0.5415$2.185All registered users / 所有注册用户
Kimi-K2-Thinking$0.57$2.375All registered users / 所有注册用户
kimi-k2.5$0.4275$2.1375All registered users / 所有注册用户
kimi-k2.6$0.4124425$1.7366All registered users / 所有注册用户
kimi-k3$0.63061$9.5All registered users / 所有注册用户
kwaipilot/kat-coder-pro-v2.5$0.703$2.812All registered users / 所有注册用户
meta-llama/llama-4-maverick$0.178125$0.619875All registered users / 所有注册用户
minimax-m2.5$0.2565$1.026All registered users / 所有注册用户
minimax-m2.7$0.1995$0.798All registered users / 所有注册用户
minimax-m3$0.285$1.14All registered users / 所有注册用户
minimax/minimax-m3$0.285$1.14All registered users / 所有注册用户
mistralai/mistral-large$1.9$5.7All registered users / 所有注册用户
moonshotai/kimi-k3$0.63061$9.5All registered users / 所有注册用户
nvidia/nemotron-3-ultra-550b-a55b$0.57$2.28All registered users / 所有注册用户
openai/gpt-3.5-turbo$0.475$1.425All registered users / 所有注册用户
openai/gpt-4.1-mini$0.38$1.52All registered users / 所有注册用户
openai/gpt-4.1-nano$0.095$0.38All registered users / 所有注册用户
openai/gpt-4o$2.375$9.5All registered users / 所有注册用户
openai/gpt-4o-mini$0.1425$0.57All registered users / 所有注册用户
openai/gpt-5-image$9.5$9.5All registered users / 所有注册用户
openai/gpt-5-mini$0.2375$1.9All registered users / 所有注册用户
openai/gpt-5-pro$14.25$114All registered users / 所有注册用户
openai/gpt-5.1-chat$1.1875$9.5All registered users / 所有注册用户
openai/gpt-5.5$4.75$28.5All registered users / 所有注册用户
openai/gpt-5.5-pro$28.5$171All registered users / 所有注册用户
openai/gpt-5.6-luna$0.19$1.14All registered users / 所有注册用户
openai/gpt-5.6-sol$1.9$9.5All registered users / 所有注册用户
openai/gpt-5.6-terra$1.9$11.4All registered users / 所有注册用户
openai/gpt-6-astra$9.5$47.5All registered users / 所有注册用户
openai/gpt-6-astra-pro$9.5$47.5All registered users / 所有注册用户
openai/o1-pro$142.5$570All registered users / 所有注册用户
openai/o3-deep-research$9.5$38All registered users / 所有注册用户
openai/o3-mini$1.045$4.18All registered users / 所有注册用户
openai/o3-pro$19$76All registered users / 所有注册用户
perplexity/sonar$0.95$0.95All registered users / 所有注册用户
perplexity/sonar-pro-search$2.85$14.25All registered users / 所有注册用户
Pro/moonshotai/Kimi-K2.6$0.4124425$1.7366All registered users / 所有注册用户
Pro/zai-org/GLM-5$0.9025$2.4225All registered users / 所有注册用户
Pro/zai-org/GLM-5.1$0.91637$2.88002All registered users / 所有注册用户
qwen-vl-chat$0.215287$0.646All registered users / 所有注册用户
Qwen/Qwen3-32B$0.076$0.266All registered users / 所有注册用户
qwen/qwen3-coder$0.285$0.95All registered users / 所有注册用户
Qwen/Qwen3-Coder-30B-A3B-Instruct$0.0665$0.266All registered users / 所有注册用户
Qwen/Qwen3.6-27B$0.304$3.04All registered users / 所有注册用户
qwen/qwen3.7-max$1.40125$4.20375All registered users / 所有注册用户
qwen/qwen3.7-plus$0.304$1.216All registered users / 所有注册用户
Qwen2.5-72B-Instruct$0.342$0.38All registered users / 所有注册用户
qwen2.5-vl-72b-instruct$0.76$0.95All registered users / 所有注册用户
qwen3-235b-a22b-instruct-2507$0.142025$0.5681All registered users / 所有注册用户
qwen3-235b-a22b-thinking-2507$0.2185$2.185All registered users / 所有注册用户
qwen3-30b-a3b$0.114$0.475All registered users / 所有注册用户
qwen3-coder-480b-a35b-instruct$0.285$0.95All registered users / 所有注册用户
qwen3-max$0.741$3.705All registered users / 所有注册用户
qwen3-vl-235b-a22b-instruct$0.1995$1.805All registered users / 所有注册用户
qwen3-vl-30b-a3b-instruct$0.1425$0.57All registered users / 所有注册用户
Qwen3.5-35B-A3B$0.133$0.95All registered users / 所有注册用户
qwen3.5-35b-a3b$0.154375$1.235All registered users / 所有注册用户
Qwen3.5-397B-A17B-Pro$0.5225$3.325All registered users / 所有注册用户
qwen3.6-35b-a3b$0.1425$0.95All registered users / 所有注册用户
qwen3.6-flash$0.178125$1.06875All registered users / 所有注册用户
qwen3.6-plus$0.30875$1.8525All registered users / 所有注册用户
qwen3.8-max$1.9$5.7All registered users / 所有注册用户
sakana/fugu-ultra$4.75$28.5All registered users / 所有注册用户
stepfun/step-3.7-flash$0.19$1.0925All registered users / 所有注册用户
tencent/hy3$0.078375$0.3135All registered users / 所有注册用户
text-embedding-v3$0.0665$0All registered users / 所有注册用户
text-embedding-v4$0.0665$0All registered users / 所有注册用户
x-ai/grok-4.20$1.1875$2.375All registered users / 所有注册用户
x-ai/grok-4.5$1.9$5.7All registered users / 所有注册用户
x-ai/grok-4.6$1.9$5.7All registered users / 所有注册用户
z-ai/glm-5.2$0.3895$3.7905All registered users / 所有注册用户
glm-5.3-flash$0.1425$0.475All registered users / 所有注册用户
kimi-k2.7-code$0.63764$3.1825All registered users / 所有注册用户
hy4-preview$0.71307$2.138355All registered users / 所有注册用户

API and tooling references

For integration and self-hosted gateway concepts, consult these official resources. Third-party features and prices follow their current pages; FlowBarAI availability and rates follow our own catalog.

Verified text base rates: 95% of OpenRouter public rates, or creator international rates when unavailable. Cache hits are billed at the normal input rate; upstream cache discounts do not reduce your charge. Cache creation and request-fee details are listed per model. Verified fixed-image base prices match Gen Studio; the main site displays USD, not Gen Credits. Videos generated in Gen Studio use its quote before submission. Native main-site video prices are not yet aligned and must not be substituted for Gen Studio quotes. Charges round to whole account credits.已核验文本基础价按 OpenRouter 公开价格95折；未收录的按厂商国际公开价95折。缓存命中按正常输入价计费，不抵扣费用；缓存创建和请求附加费详见各模型。已验证固定图片的基础价与 Gen Studio 一致，主站显示美元，不显示 Gen Credits。Gen Studio 视频按提交前的规格报价计费；主站原生视频价格尚未完成对齐，不能与 Gen 报价混用。扣费按整数额度舍入。