Live billing catalog

Model pricing

Compare input, output and cache rates side by side. Filter by provider, use case, price tier or image capability, and copy any model ID with one click. All prices are USD and come straight from the billing configuration that charges your account.

How billing works Get API access

Models available

Providers

Lowest input price

$0.0384 / 1M

Exchange rate

6.77 CNY/USD

Provider

Use case

Price

Images

Showing 33 of 33 models

Sort by

Model prices in USD per million tokens
Model	Provider	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M	Context	Images
claude-sonnet-4-6 Exclusive	AI API Proxy	$0.0384	$0.1920	$0.0038	$0.0384	1M	Understands
claude-haiku-4-5-20251001	Anthropic	$0.0768	$0.3840	$0.0077	$0.1152	256K	Understands
gpt-5.6-luna	OpenAI	$0.0768	$0.4609	$0.0077	$0.0960	258K	Understands
gpt-5.6-terra	OpenAI	$0.0768	$0.4609	$0.0077	$0.0960	258K	Understands
hy3	Tencent Hunyuan	$0.0768	$0.3840	$0.0077	$0.0768	256K	—
LongCat-2.0	Meituan / LongCat	$0.0768	$0.3072	$0.0077	$0.0768	1M	—
MiniMax-M3	MiniMax	$0.0768	$0.3840	$0.0077	$0.0192	1M	Understands
step-3.7-flash	StepFun	$0.0768	$0.3840	$0.0077	$0.0384	256K	Understands
deepseek-v4-flash	DeepSeek	$0.1477	$0.7386	$0.0148	$0.1477	1M	—
mimo-v2.5	Xiaomi / MiMo	$0.1536	$0.7681	$0.0154	$0.1536	1M	Understands
doubao-seed-2.0-code	ByteDance / Doubao	$0.2304	$1.15	$0.0230	$0.2304	200K	Understands
doubao-seed-2.0-pro	ByteDance / Doubao	$0.2304	$1.15	$0.0230	$0.2304	128K	Understands
gpt-5.4	OpenAI	$0.2304	$1.38	$0.0230	$0.2304	1M	Understands
qwen3.6-plus	Alibaba / Qwen	$0.2304	$1.15	$0.0230	$0.2304	1M	Understands
mimo-v2.5-pro	Xiaomi / MiMo	$0.3072	$1.54	$0.0307	$0.3072	1M	—
qwen3.7-plus	Alibaba / Qwen	$0.3072	$1.54	$0.0307	$0.3072	1M	Understands
glm-5.1	Zhipu / Z.ai	$0.3840	$1.92	$0.0384	$0.3840	256K	Understands
grok-4.5	xAI / Grok	$0.3840	$1.92	$0.4801	$0.3840	500K	Understands
deepseek-v4-pro	DeepSeek	$0.4431	$2.22	$0.0443	$0.4431	1M	—
gpt-5.5	OpenAI	$0.4609	$2.77	$0.0461	$0.4609	258K	Understands
gpt-5.6-sol	OpenAI	$0.4609	$2.77	$0.0461	$0.5761	258K	Understands
glm-5.2	Zhipu / Z.ai	$0.6145	$3.07	$0.0614	$0.6145	1M	Understands
claude-sonnet-5	Anthropic	$0.7681	$3.84	$0.0768	$0.9601	1M	Understands
qwen3.7-max	Alibaba / Qwen	$0.7681	$3.84	$0.0768	$0.7681	1M	—
qwen3.8-max	Alibaba / Qwen	$0.7681	$2.30	$0.0960	$0.7681	1M	Understands
claude-opus-4-6	Anthropic	$1.15	$5.76	$0.1152	$0.1440	1M	Understands
claude-opus-4-7	Anthropic	$1.15	$5.76	$0.1152	$1.44	1M	Understands
claude-opus-4-8	Anthropic	$1.15	$5.76	$0.1152	$1.44	1M	Understands
claude-opus-5	Anthropic	$1.15	$5.76	$0.1152	$1.44	1M	Understands
kimi-k3	Moonshot / Kimi	$1.92	$9.60	$0.1920	$1.92	1M	Understands
claude-fable-5	Anthropic	$3.07	$15.36	$0.3072	$3.84	1M	Understands
gpt-image-2	OpenAI	$0.0192 per image				1–2K output	Generates
gpt-image-2-4k	OpenAI	$0.1920 per image				4K output	Generates

claude-sonnet-4-6

AI API Proxy

Input / 1M: $0.0384
Output / 1M: $0.1920
Cache read: $0.0038
Cache write: $0.0384

1MUnderstands imagesExclusive

claude-haiku-4-5-20251001

Anthropic

Input / 1M: $0.0768
Output / 1M: $0.3840
Cache read: $0.0077
Cache write: $0.1152

256KUnderstands images

gpt-5.6-luna

OpenAI

Input / 1M: $0.0768
Output / 1M: $0.4609
Cache read: $0.0077
Cache write: $0.0960

258KUnderstands images

gpt-5.6-terra

OpenAI

Input / 1M: $0.0768
Output / 1M: $0.4609
Cache read: $0.0077
Cache write: $0.0960

258KUnderstands images

hy3

Tencent Hunyuan

Input / 1M: $0.0768
Output / 1M: $0.3840
Cache read: $0.0077
Cache write: $0.0768

256KText input only

LongCat-2.0

Meituan / LongCat

Input / 1M: $0.0768
Output / 1M: $0.3072
Cache read: $0.0077
Cache write: $0.0768

1MText input only

MiniMax-M3

MiniMax

Input / 1M: $0.0768
Output / 1M: $0.3840
Cache read: $0.0077
Cache write: $0.0192

1MUnderstands images

step-3.7-flash

StepFun

Input / 1M: $0.0768
Output / 1M: $0.3840
Cache read: $0.0077
Cache write: $0.0384

256KUnderstands images

deepseek-v4-flash

DeepSeek

Input / 1M: $0.1477
Output / 1M: $0.7386
Cache read: $0.0148
Cache write: $0.1477

1MText input only

mimo-v2.5

Xiaomi / MiMo

Input / 1M: $0.1536
Output / 1M: $0.7681
Cache read: $0.0154
Cache write: $0.1536

1MUnderstands images

doubao-seed-2.0-code

ByteDance / Doubao

Input / 1M: $0.2304
Output / 1M: $1.15
Cache read: $0.0230
Cache write: $0.2304

200KUnderstands images

doubao-seed-2.0-pro

ByteDance / Doubao

Input / 1M: $0.2304
Output / 1M: $1.15
Cache read: $0.0230
Cache write: $0.2304

128KUnderstands images

gpt-5.4

OpenAI

Input / 1M: $0.2304
Output / 1M: $1.38
Cache read: $0.0230
Cache write: $0.2304

1MUnderstands images

qwen3.6-plus

Alibaba / Qwen

Input / 1M: $0.2304
Output / 1M: $1.15
Cache read: $0.0230
Cache write: $0.2304

1MUnderstands images

mimo-v2.5-pro

Xiaomi / MiMo

Input / 1M: $0.3072
Output / 1M: $1.54
Cache read: $0.0307
Cache write: $0.3072

1MText input only

qwen3.7-plus

Alibaba / Qwen

Input / 1M: $0.3072
Output / 1M: $1.54
Cache read: $0.0307
Cache write: $0.3072

1MUnderstands images

glm-5.1

Zhipu / Z.ai

Input / 1M: $0.3840
Output / 1M: $1.92
Cache read: $0.0384
Cache write: $0.3840

256KUnderstands images

grok-4.5

xAI / Grok

Input / 1M: $0.3840
Output / 1M: $1.92
Cache read: $0.4801
Cache write: $0.3840

500KUnderstands images

deepseek-v4-pro

DeepSeek

Input / 1M: $0.4431
Output / 1M: $2.22
Cache read: $0.0443
Cache write: $0.4431

1MText input only

gpt-5.5

OpenAI

Input / 1M: $0.4609
Output / 1M: $2.77
Cache read: $0.0461
Cache write: $0.4609

258KUnderstands images

gpt-5.6-sol

OpenAI

Input / 1M: $0.4609
Output / 1M: $2.77
Cache read: $0.0461
Cache write: $0.5761

258KUnderstands images

glm-5.2

Zhipu / Z.ai

Input / 1M: $0.6145
Output / 1M: $3.07
Cache read: $0.0614
Cache write: $0.6145

1MUnderstands images

claude-sonnet-5

Anthropic

Input / 1M: $0.7681
Output / 1M: $3.84
Cache read: $0.0768
Cache write: $0.9601

1MUnderstands images

qwen3.7-max

Alibaba / Qwen

Input / 1M: $0.7681
Output / 1M: $3.84
Cache read: $0.0768
Cache write: $0.7681

1MText input only

qwen3.8-max

Alibaba / Qwen

Input / 1M: $0.7681
Output / 1M: $2.30
Cache read: $0.0960
Cache write: $0.7681

1MUnderstands images

claude-opus-4-6

Anthropic

Input / 1M: $1.15
Output / 1M: $5.76
Cache read: $0.1152
Cache write: $0.1440

1MUnderstands images

claude-opus-4-7

Anthropic

Input / 1M: $1.15
Output / 1M: $5.76
Cache read: $0.1152
Cache write: $1.44

1MUnderstands images

claude-opus-4-8

Anthropic

Input / 1M: $1.15
Output / 1M: $5.76
Cache read: $0.1152
Cache write: $1.44

1MUnderstands images

claude-opus-5

Anthropic

Input / 1M: $1.15
Output / 1M: $5.76
Cache read: $0.1152
Cache write: $1.44

1MUnderstands images

kimi-k3

Moonshot / Kimi

Input / 1M: $1.92
Output / 1M: $9.60
Cache read: $0.1920
Cache write: $1.92

1MUnderstands images

claude-fable-5

Anthropic

Input / 1M: $3.07
Output / 1M: $15.36
Cache read: $0.3072
Cache write: $3.84

1MUnderstands images

gpt-image-2

OpenAI

$0.0192 per image

1–2K outputGenerates images

gpt-image-2-4k

OpenAI

$0.1920 per image

4K outputGenerates images

Where these numbers come from

Prices are read from the live billing configuration on every page load, so a rate change takes effect here without a redeploy.
Token models are billed per token with no minimum. Input, output, cache reads and cache writes are each billed at their own rate — cache writes cost more than standard input on some models, so they are listed separately rather than folded into input.
Image models are billed per image, not per token. The price is the same regardless of prompt length. Call POST /api/v1/images/generations.
USD figures are converted from the internal CNY rate at 6.77 CNY/USD. Context window and image capability come from each provider's published specs.