Guide

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open GPT reasoning model for self-hosted agents and controllable deployments

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open GPT reasoning model for self-hosted agents and controllable deployments

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Open GPT reasoning model for self-hosted agents and controllable deployments

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Open GPT reasoning model for self-hosted agents and controllable deployments

Open GPT reasoning model for self-hosted agents and controllable deployments

Open GPT reasoning model for self-hosted agents and controllable deployments

Open GPT reasoning model for self-hosted agents and controllable deployments

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open GPT reasoning model for self-hosted agents and controllable deployments

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open GPT reasoning model for self-hosted agents and controllable deployments

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open GPT reasoning model for self-hosted agents and controllable deployments

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

GLM 4.5 Air from Fireworks AI - text input, 131,072 token context

DeepSeek R1 (0528) from Synthetic - text input, 128,000 token context

DeepSeek V3 (0324) from Synthetic - text input, 128,000 token context

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

Smaller Qwen coder for efficient local agents and repo-level fixes

Qwen coding model for software agents, repository edits, and code reasoning

Video model for prompt-guided generation, editing, and motion workflows

Cohere vision model for multilingual document analysis, OCR, and image understanding

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

GLM 4.5 from Fireworks AI - text input, 131,072 token context

GLM 4.5 from Synthetic - text input, 128,000 token context

GLM-4.5 from DeepInfra - text input, 131,072 token context

Lighter GLM-4.5 variant for fast coding assistance and cheaper agents

Hybrid-reasoning GLM release that made the 4.5 line broadly useful