TokenMarket

TM

Unified API for AI Tokens

Use one entrypoint for model access, price comparison, routing governance, and token settlement.

Multi-model catalogExplainable routingUnified billing
ModelsDocsConsole
Login
Language
EN中文

Filter

Clear

Series

All12gpt4Doubao2Claude1DeepSeek1Google1Kimi1MiniMax1Qwen1
Show less

Modality

All12Text7Image2Embeddings0Audio0Video2Rerank0Speech1Transcription0

Billing

All12Token10Per request1Per second1

Model marketplace

One market for leading AI models

Filter and sort

2 filters active

Sort
Sort
RecommendedNewestLowest input priceLowest output priceLargest context

Series

All12gpt4Doubao2Claude1DeepSeek1Google1Kimi1MiniMax1Qwen1
Show less

Modality

All12Text7Image2Embeddings0Audio0Video2Rerank0Speech1Transcription0

Billing

All12Token10Per request1Per second1
Sort
RecommendedNewestLowest input priceLowest output priceLargest context
Models 1Sorted by Recommended
Modality: Text ×Series: DeepSeek ×
D

DeepSeek-V4-pro

Text
DeepSeekDeepSeekDeepSeek-V4-pro
⧉□

DeepSeek-V4-Pro is DeepSeek's flagship MoE hybrid expert model, employing a highly efficient architecture with 1.6T total parameters and 49B activation parameters, and natively supporting an ultra-long context window of 1 million tokens. The model features a dedicated inference mode, achieving industry-leading performance in three core areas: complex logical reasoning, professional code generation, and intelligent agent execution. Its overall performance rivals that of top-tier closed-source models globally.

chatcodingmultilingualToken

Input

$1.55 / 1M

Output

$3.1 / 1M

Cache write

$0.13 / 1M

Cache read

$0.13 / 1M

CompareCopy

Page 1 of 1 · 1 models

Previous
1
1
Next