Models

Model	Context	Max output	Official price	TokenLab price	Discount
qwen-maxPrompt Cache	31K	8K	Input$1.60/1MOutput$6.40/1M	—	—
qwen-flash-characterPrompt Cache	8K	4K	Input$0.05/1MOutput$0.40/1M	—	—
gemma-4-31b	—	—	Input$0.102/1MOutput$0.297/1M	—	—
qwen3.5-27b	260K	64K	Input$0.30/1MOutput$2.40/1M	—	—
qwen3.5-omni-flashVision	197K	64K	Input$0.40/1MOutput$2.20/1M	—	—
qwen3.5-omni-plusVision	197K	64K	Input$1.40/1MOutput$8.30/1M	—	—
qwen3.6-27bTool useVision	128K	32K	Input$0.60/1MOutput$3.60/1M	—	—
qwen3-omni-flashVision	49K	16K	Input$0.43/1MOutput$1.66/1M	—	—
qwen3.5-ocrVision	49K	16K	Input$0.0735/1MOutput$0.2941/1M	—	—
allam-2-7b	32K	4K	Input$0.05/1MOutput$0.08/1M	—	—
qwen-vl-ocrVision	30K	8K	Input$0.07/1MOutput$0.16/1M	—	—
hunyuan-role	29K	4K	Input$0.3529/1MOutput$1.41/1M	—	—
tongyi-xiaomi-analysis-flash	29K	4K	Input$0.0294/1MOutput$0.0588/1M	—	—
tongyi-xiaomi-analysis-pro	29K	4K	Input$0.1471/1MOutput$0.3971/1M	—	—
qwen-mt-flash	8K	8K	Input$0.16/1MOutput$0.49/1M	—	—
qwen-mt-lite	8K	8K	Input$0.12/1MOutput$0.36/1M	—	—
qwen-mt-plus	8K	8K	Input$2.46/1MOutput$7.37/1M	—	—
tongyi-intent-detect-v3	8K	4K	Input$0.0588/1MOutput$0.1471/1M	—	—
hy-mt2-pro	4K	4K	Input$0.074/1MOutput$0.295/1M	—	—
hailuo-h3Image to VideoMultimodalReference to VideoStart-end to videoText to Video	—	—	$0.08/sec	$0.08/sec	—
gemini-embedding-2	8K	—	Input$0.20/1MOutput$0.00/1M	—	—
codestral-embed	8K	—	Input$0.15/1MOutput$0.00/1M	—	—
qwen3.7-text-embedding	128K	—	Input$0.0735/1MOutput$0.00/1M	—	—
qwen3.7-text-embedding-flash	128K	—	Input$0.0184/1MOutput$0.00/1M	—	—

6 / 18

All model series

6 series

Gemini Embedding

Google

Save 50%

Embedding

Auto from $0.075 · per 1M tokens

2 modelsOpen series

Veo 3

Google

Save 30%

Video

Auto from $0.05 · per second

3 modelsOpen series

GPT-6

OpenAI

Save 70%

ChatVisionCode+1

Auto from $0.03 · per 1M tokens

4 modelsOpen series

Claude 5

Anthropic

Save 70%

ChatVisionCode+1

Auto from $0.60 · per 1M tokens

6 modelsOpen series

Grok 4

xAI

Save 50%

ChatImageVision+1

Auto from $0.625 · per 1M tokens

7 modelsOpen series

Gemini 3

Google

Save 50%

ChatImageVision+1

Auto from $0.125 · per 1M tokens

11 modelsOpen series