Skip to sign in
ProsGrow AIInference Sign in

Powerful models. Practical economics.

Intelligence, unlocked. Priced for scale.

Build with powerful AI models at affordable, transparent prices. One API for your applications, with the visibility and control to run with confidence.

OpenAI-compatible API Pay for what you use
Start building with DeepSeek V4GLM-5.2Seedance 2.5 Preview

The model lineup

The right model. The right economics.

From everyday requests to complex reasoning, choose the capability and cost that fit your workload.

Available

Everyday speed

DeepSeek V4 Flash

Fast, cost-efficient intelligence for chat, summaries, extraction, and real-time assistants.

StreamingTool callingJSON output

USD / 1M tokens

Input
$0.20
Output
$0.54
Cached input
$0.03
Sign in to explore
Available

Reasoning & coding

DeepSeek V4 Pro

Advanced reasoning for complex analysis, coding, debugging, and agentic workflows.

StreamingTool callingJSON output

USD / 1M tokens

Input
$1.83
Output
$3.65
Cached input
$0.15
Sign in to explore
Available

Reasoning & coding

GLM-5.2

Bring GLM-5.2 into your application through a familiar chat API, with streaming responses and transparent token pricing.

Streaming

USD / 1M tokens

Input
$8.40
Output
$29.40
Cached input
$2.10
Sign in to explore
Preview

Text to video

Seedance 2.5

Turn a text prompt into a video in the signed-in playground. Preview access is subject to your account permissions.

Video playground480p · 720p · 1080p

USD / 1M generated-video tokens

480p / 720p
$11.24
1080p
$12.28
Request preview access

Prices follow the published model catalog. Model access depends on your account permissions.

LOOKING AHEAD

Have another model in mind?

Interested in GLM-5.3? Ask our team about future access. It is not currently in the published catalog.

Built for the work ahead

More capability. Less overhead.

Keep costs in view.

Transparent token pricing, usage-based billing, and budget controls. Track what you spend as your application grows.

Compare model pricing

Operate with confidence.

Monitor request outcomes, review usage and errors, and manage your budget. Keep performance visible from development to production.

Explore error handling

Integrate once. Build more.

Use familiar OpenAI-compatible requests and streaming. Choose models that support tool calling and structured JSON output, and manage access in one console.

Read the API docs
No prompts or completions in our logs, traces, or billing database

From idea to API

Your next application starts here.

Choose a model, create an API key, and start building with ProsGrow.

Get started