Skip to main content

Explore and discover language models

Find a model by name or ID

Qwen4 Max

Image input · Structured output · Streaming

View details

Models

7

DeepSeek-V4.1-Flash

Model IDdeepseek-flash

The official alias currently resolves to DeepSeek-V4.1-Flash-1017. Actual Acosmi capabilities follow the selected interface.

Anthropic · deepseek
Input
¥1 / million tokens
Output
¥4 / million tokens
Context length
1M
Max output
382K

DeepSeek V4 Pro

Model IDdeepseek-v4-pro

DeepSeek-V4-Pro-0813, a text model. Official prices distinguish cache, input/output and peak periods.

Anthropic · deepseek
Input
¥4.5 / million tokens
Output
¥13.5 / million tokens
Context length
1M
Max output
300K

GLM-5.2

Model IDglm-5.2

A Z.AI text model with a 1M official context window. Acosmi limits and availability follow the selected interface.

Input
¥8 / million tokens
Output
¥28 / million tokens
Context length
1M
Max output
8.2K

HappyHorse-1.0

Model IDhappyhorse-1.0-t2v

Text-to-video, billed by successful output duration and resolution. The text interface does not generate video.

OpenAI · dashscope
Acosmi pricing pending
Context length
—
Max output
—

Qwen-Image-2.0-Pro

Model IDqwen-image-2.0-pro

Image generation billed per image, not text Tokens. A text catalog entry does not establish image API availability.

OpenAI · dashscope
Acosmi pricing pending
Context length
—
Max output
—

Qwen3.7-Plus

Model IDqwen3.7-plus

Qwen model with input-length pricing tiers. Official prices below are for Bailian Beijing, with the temporary discount identified.

Tiered by input length

Context length
1M
Max output
64K

Qwen4 Max

Model IDqwen4-max

Image input · Structured output · Streaming

Anthropic · dashscope
Input
¥10 / million tokens
Output
¥30 / million tokens
Context length
983.6K
Max output
131.1K
Catalog observed