State-of-the-Art

AI Model Library

One API to run inference on 200+ cutting-edge AI models, and deploy in seconds

State-of-the-Art

AI Model Library

One API to run inference on 200+ cutting-edge AI models, and deploy in seconds

State-of-the-Art

AI Model Library

One API to run inference on 200+ cutting-edge AI models, and deploy in seconds

Tencent

Text Generation

Hunyuan-A13B-Instruct

Hunyuan-A13B-Instruct mengaktifkan hanya 13 B dari 80 B parameternya, namun sebanding dengan LLM yang jauh lebih besar pada tolok ukur arus utama. Ini menawarkan penalaran hibrida: mode “cepat” latensi rendah atau mode “lambat” presisi tinggi, dapat dialihkan per panggilan. Konteks 256 K-token asli memungkinkan untuk mencerna dokumen sepanjang buku tanpa degradasi. Keterampilan agen disesuaikan untuk kepemimpinan BFCL-v3, τ-Bench, dan C3-Bench, menjadikannya tulang punggung asisten otonom yang sangat baik. Grouped Query Attention plus kuantisasi multi-format memberikan inferensi yang ringan-memori, efisien-GPU untuk penerapan dunia nyata, dengan dukungan multibahasa bawaan dan penyelarasan keselamatan yang kuat untuk aplikasi kelas perusahaan....

Total Context:

131K

Max output:

131K

Input:

$

0.14

/ M Tokens

Input:

$

text

/ M Tokens

Output:

$

0.57

/ M Tokens

Tencent

Text Generation

Hy4-preview

Hy4 preview is Tencent Hy's new-generation productivity flagship model, built on Gated DeepSeek Sparse Attention with iHC residual design, with approximately 770B total and 49B activated parameters per token. It natively supports a 1M context window with up to 64k output and a native MTP layer for speculative decoding to boost generation throughput. It demonstrates strong comprehension, planning, and sustained execution on complex tasks, and natively supports tool calls, structured output, and context caching. Deeply optimized for Agent, Coding, and productivity scenarios, it suits long-horizon planning and code workflows....

Total Context:

1049K

Max output:

262K

Input:

$

0.834

/ M Tokens

Input:

$

text

/ M Tokens

Output:

$

2.501

/ M Tokens

Tencent

Text Generation

Hy3

Built for real-world business scenarios, Hy3 features a 295B/21B active MoE architecture, native 256K context support, and three reasoning modes. It enhances coding, long-form comprehension, multi-turn dialogue, and agentic task execution, balancing reliability, efficiency, and cost across both high-frequency interactions and complex workflows....

Total Context:

262K

Max output:

262K

Input:

$

0.132

/ M Tokens

Input:

$

text

/ M Tokens

Output:

$

0.528

/ M Tokens

Siap untuk mempercepat pengembangan AI Anda?

Siap untuk mempercepat pengembangan AI Anda?

Siap untuk mempercepat pengembangan AI Anda?