AI Model API Catalog

#blog-server-fallback{display:block}.blog-fallback{max-width:1120px;margin:0 auto;padding:48px 24px;font-family:system-ui,-apple-system,sans-serif;color:#171717}.blog-fallback a{color:inherit}.blog-fallback__header{margin-bottom:32px}.blog-fallback__header h1,.blog-fallback__postHeader h1{font-size:clamp(2.4rem,7vw,5.5rem);line-height:1;margin:18px 0}.blog-fallback__grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(260px,1fr));gap:24px}.blog-fallback__card{border:1px solid #ddd;border-radius:18px;overflow:hidden}.blog-fallback__card img,.blog-fallback--post figure img{display:block;width:100%;height:auto}.blog-fallback__cardBody{padding:20px}.blog-fallback__card h2{font-size:1.35rem}.blog-fallback__eyebrow,.blog-fallback__meta{color:#666;font-size:.875rem}.blog-fallback__lead{font-size:1.25rem;color:#555}.blog-fallback--post{max-width:880px}.blog-fallback__content{font-size:1.05rem;line-height:1.8}.blog-fallback__content pre{overflow:auto;padding:16px;background:#111;color:#eee;border-radius:12px}.blog-fallback__content img{max-width:100%;height:auto}.blog-fallback__pagination{display:flex;justify-content:center;gap:20px;margin-top:36px}

Text and reasoning

cai-cc-5-5

cai-cc-5-5

Officially integrated Text model

Token billing: input 4.00 points / 1M tokens, output 20.00 points / 1M tokens.

Image generation

seedream-5-flash

seedream-5-flash

Officially integrated Image model

Per-request billing: a fixed amount is charged for each call.

Text and reasoning

deepseek-v4.1-flash-1017

deepseek-v4.1-flash-1017

Officially integrated Text model

Token billing: input 1.00 points / 1M tokens, output 4.00 points / 1M tokens.

Text and reasoning

claude-haiku-5-5

claude-haiku-5-5

Officially integrated Text model

Token billing: input 0.10 points / 1M tokens, output 0.50 points / 1M tokens.

Text and reasoning

claude-sonnet-5-5

claude-sonnet-5-5

Officially integrated Text model

Token billing: input 2.00 points / 1M tokens, output 10.00 points / 1M tokens.

Text and reasoning

gpt-6.1-sol

gpt-6.1-sol

Officially integrated Text model

Token billing: input 2.00 points / 1M tokens, output 10.00 points / 1M tokens.

Image generation

gemini-nano-banana-2.1

gemini-nano-banana-2.1

Officially integrated Image model

Per-request billing: a fixed amount is charged for each call.

Image generation

nano-banana-2.1

nano-banana-2.1

Officially integrated Image model

Per-request billing: a fixed amount is charged for each call.

Text and reasoning

claude-opus-5-5

claude-opus-5-5

Officially integrated Text model

Token billing: input 4.00 points / 1M tokens, output 20.00 points / 1M tokens.

Image generation

gpt-image-2.5-sunburst

gpt-image-2.5-sunburst

Officially integrated Image model

Per-request billing: a fixed amount is charged for each call.

Text and reasoning

gpt-6-sol

gpt-6-sol

Officially integrated Text model

Token billing: input 2.00 points / 1M tokens, output 10.00 points / 1M tokens.

Text and reasoning

jev-preview

jev-preview

Officially integrated Text model

Token billing: input 0.042 points / 1M tokens, output 0.042 points / 1M tokens.

Text and reasoning

jev-latest

jev-latest

Officially integrated Text model

Token billing: input 0.042 points / 1M tokens, output 0.042 points / 1M tokens.

Text and reasoning

Jev 1.13

jev-1.13.0

Officially integrated Text model

Token billing: input 0.042 points / 1M tokens, output 0.042 points / 1M tokens.

Text and reasoning

claude-fable-5-1

claude-fable-5-1

Officially integrated Text model

Token billing: input 10.00 points / 1M tokens, output 50.00 points / 1M tokens.

Text and reasoning

deepseek-flash

deepseek-flash

Officially integrated Text model

Token billing: input 1.50 points / 1M tokens, output 4.50 points / 1M tokens.

Text and reasoning

deepseek-v4.1-flash

deepseek-v4.1-flash

Officially integrated Text model

Token billing: input 1.50 points / 1M tokens, output 4.50 points / 1M tokens.

Image generation

gpt-image-2.5

gpt-image-2.5

Officially integrated Image model

Per-image billing: charges are based on the number of generated images.

Image generation

gpt-image-2.5-flare

gpt-image-2.5-flare

Officially integrated Image model

Per-request billing: a fixed amount is charged for each call.

Video generation

jimeng-seedance-2.5

jimeng-seedance-2.5

Officially integrated Video model

Per-second billing: charges are based on generated video duration.

Video generation

jimeng-seedance-2.0-vip

jimeng-seedance-2.0-vip

Officially integrated Video model

Per-second billing: charges are based on generated video duration.

Text and reasoning

gpt-6-astra

gpt-6-astra

Officially integrated Text model

Token billing: input 10.00 points / 1M tokens, output 50.00 points / 1M tokens.

Text and reasoning

glm-5.3

glm-5.3

Officially integrated Text model

Token billing: input 8.00 points / 1M tokens, output 28.00 points / 1M tokens.

Text and reasoning

glm-5.3-flash

glm-5.3-flash

Officially integrated Text model

Token billing: input 0.80 points / 1M tokens, output 2.80 points / 1M tokens.

Video generation

sd2.5

sd2.5

Officially integrated Video model

Per-second billing: charges are based on generated video duration.

Text and reasoning

qwen3.8-max

qwen3.8-max

Officially integrated Text model

Token billing: input 12.00 points / 1M tokens, output 36.00 points / 1M tokens.

Text and reasoning

grok-4.6

grok-4.6

grok-4.6

Token billing: input 2.00 points / 1M tokens, output 6.00 points / 1M tokens.

Image generation

grok-imagine-image-2.0

grok-imagine-image-2.0

Officially integrated Image model

Per-image billing: charges are based on the number of generated images.

Image generation

gemini-3-pro-image

gemini-3-pro-image

Officially integrated Image model

Per-image billing: charges are based on the number of generated images.

Text and reasoning

kimi-k3

kimi-k3

Officially integrated Text model

Token billing: input 20.00 points / 1M tokens, output 100.00 points / 1M tokens.

Video generation

grok-imagine-video-1.5

grok-imagine-video-1.5

Officially integrated Video model

Per-second billing: charges are based on generated video duration.

Text and reasoning

claude-opus-5

claude-opus-5

Officially integrated Text model

Token billing: input 5.00 points / 1M tokens, output 25.00 points / 1M tokens.

Text and reasoning

glm-t-5.6

glm-t-5.6

Officially integrated Text model

Token billing: input 2.50 points / 1M tokens, output 15.00 points / 1M tokens.

Text and reasoning

glm-s-5.6

glm-s-5.6

Officially integrated Text model

Token billing: input 5.00 points / 1M tokens, output 30.00 points / 1M tokens.

Text and reasoning

gpt-5.6-sol

gpt-5.6-sol

gpt-5.6-sol

Token billing: input 5.00 points / 1M tokens, output 30.00 points / 1M tokens.

Text and reasoning

gpt-5.6-terra

gpt-5.6-terra

Officially integrated Text model

Token billing: input 2.00 points / 1M tokens, output 12.00 points / 1M tokens.

Text and reasoning

gpt-5.6-luna

gpt-5.6-luna

Officially integrated Text model

Token billing: input 0.20 points / 1M tokens, output 1.20 points / 1M tokens.

Text and reasoning

glm-gr-4.5

glm-gr-4.5

Officially integrated Text model

Token billing: input 2.00 points / 1M tokens, output 6.00 points / 1M tokens.

Text and reasoning

grok-4.5

grok-4.5

Officially integrated Text model

Token billing: input 2.00 points / 1M tokens, output 6.00 points / 1M tokens.

Image generation

seedream-5-pro

seedream-5-pro

Officially integrated Image model

Per-image billing: charges are based on the number of generated images.

Text and reasoning

glm-5.2-fast

glm-5.2-fast

Officially integrated Text model

Token billing: input 12.00 points / 1M tokens, output 42.00 points / 1M tokens.

Text and reasoning

claude-sonnet-5

claude-sonnet-5

Officially integrated Text model

Token billing: input 2.00 points / 1M tokens, output 10.00 points / 1M tokens.

Text and reasoning

kimi-2.7-code-fast

kimi-2.7-code-fast

Officially integrated Text model

Token billing: input 13.00 points / 1M tokens, output 53.9994 points / 1M tokens.

Text and reasoning

kimi-2.7-code

kimi-2.7-code

Officially integrated Text model

Token billing: input 6.50 points / 1M tokens, output 26.9997 points / 1M tokens.

Image generation

nano-banana-2-lite

nano-banana-2-lite

Officially integrated Image model

Per-image billing: charges are based on the number of generated images.

Image generation

FLUX 1.1 Pro

flux-1-1-pro

Officially integrated Image model

Per-request billing: a fixed amount is charged for each call.

Text and reasoning

glm-g-5.2

glm-g-5.2

Officially integrated Text model

Token billing: input 8.00 points / 1M tokens, output 28.00 points / 1M tokens.

Text and reasoning

qwen3.7-plus

qwen3.7-plus

Officially integrated Text model

Token billing: input 2.00 points / 1M tokens, output 8.00 points / 1M tokens.

The current catalog contains 163 models.