Model Library

Access open-source AI models through a single, unified API.

/
All Models 16 models
Sort
deepseek-v3.2
DeepSeek
pro

DeepSeek's flagship MoE model. 685B total parameters (37B active) with MIT license. Achieves GPT-5-level performance across reasoning and coding benchmarks. Best-in-class for complex code generation and multi-step problem solving.

reasoningcode
DeepSeek
164K
Context
685B MoE
Parameters
deepseek-v3.2-speciale
DeepSeek
pro

Specialized reasoning variant of DeepSeek V3.2. Surpasses GPT-5 on AIME and HMMT benchmarks, matching Gemini-3.0-Pro. Optimized for mathematics, logic, and scientific reasoning tasks.

reasoning
DeepSeek
164K
Context
685B MoE
Parameters
Llama 4 Scout
Meta
pro

Meta's natively multimodal MoE model. 109B total parameters (17B active, 16 experts) with an industry-leading 10M token context window. Strong all-rounder for chat, code, and image understanding.

chatvision
Meta
10M
Context
109B MoE
Parameters
Qwen 3.5 27B
Alibaba
pro

Alibaba's latest model from the Qwen 3.5 series. Competes with Claude Sonnet 4.5 and GPT-5.2 on major benchmarks. Supports text, image, and video input with 262K native context.

chatreasoning
Alibaba
262K
Context
27B
Parameters
kimi-k2.5
Moonshot AI
pro

State-of-the-art for software engineering and front-end development. Excels at image/video-to-code, visual debugging, and UI reconstruction. 256K context handles large codebases.

codereasoning
Moonshot AI
256K
Context
32B active
Parameters
Llama 4 Maverick
Meta
pro

Meta's largest openly available Llama 4 model. 400B total MoE parameters (17B active, 128 experts) with natively multimodal image understanding and 1M token context.

chatvision
Meta
1M
Context
400B MoE
Parameters
Devstral 24B
Mistral
free

Mistral's dedicated code model. 24B parameters focused on code generation, completion, and explanation. Optimized for IDE integration and agentic coding workflows.

128K
Context
24B
Parameters
GLM-5
Zhipu AI
pro

Zhipu AI's flagship for complex systems engineering and long-horizon agentic tasks. 744B total parameters with 40B active per token. Trained on 28.5 trillion tokens.

reasoning
Zhipu AI
200K
Context
40B active
Parameters
Gemma 3 27B
Google
free

Google's open model with multimodal capabilities. Handles text and image inputs. Strong general-purpose for chat, summarization, and visual question answering.

chatvision
Google
128K
Context
27B
Parameters
MiMo V2 Flash
Xiaomi
pro

Ultra-fast reasoning model from Xiaomi. 309B total but only 15B active per token — exceptional speed-to-quality ratio. Designed for coding and agentic workflows.

reasoningcode
Xiaomi
256K
Context
15B active
Parameters
Mistral Small 24B
Mistral
free

General-purpose chat model. 24B parameters with 128K context and strong multilingual support. A reliable workhorse for production chat applications.

128K
Context
24B
Parameters
Codestral 22B
Mistral
free

Mistral's Fill-in-the-Middle code model. 22B parameters with exceptional autocomplete and code infilling. Supports 80+ programming languages.

256K
Context
22B
Parameters
Qwen 3.5 9B
Alibaba
free

Compact model from the Qwen 3.5 series. Same architecture as the 27B with excellent quality-per-parameter. Great for latency-sensitive and cost-efficient deployments.

262K
Context
9B
Parameters
Phi-4 14B
Microsoft
free

Microsoft's small but powerful reasoning model. Punches above its weight on math, science, and logical reasoning. Excellent choice for strong reasoning at low cost.

reasoning
Microsoft
16K
Context
14B
Parameters
DeepSeek R1 8B
DeepSeek
free

Distilled reasoning model. 8B parameters with chain-of-thought reasoning capabilities inherited from the larger R1. Best reasoning model in the sub-10B class.

reasoning
DeepSeek
128K
Context
8B
Parameters
Qwen 3.5 4B
Alibaba
free

Lightweight model from the Qwen 3.5 series. 4B parameters yet supports the full 262K context. Ideal for edge deployments, mobile, and high-throughput serving.

262K
Context
4B
Parameters

No models found

Try a different search term or filter.