Guide

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

GLM 4.7 FP8 from Chutes - text input, 202,752 token context

GLM 4.7 Flash from Chutes - text input, 202,752 token context

GLM 4.5 FP8 from Chutes - text input, 131,072 token context

GLM 4.6 FP8 from Chutes - text input, 202,752 token context

Llama 3.2 1B Instruct from Chutes - text input, 16,384 token context

TNG R1T Chimera Turbo from Chutes - text input, 163,840 token context

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Kimi multimodal agent model for visual understanding, coding, and planning

Kimi multimodal agent model for visual understanding, coding, and planning

OCR model for extracting structured text from documents and screenshots

Kimi multimodal agent model for visual understanding, coding, and planning

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...

Qwen reasoning model for deliberate problem solving, math, and coding

Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...

LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...

Budget GLM lane for fast coding help, routing, and everyday automation

Budget GLM lane for fast coding help, routing, and everyday automation

Efficient GLM model for fast reasoning, coding, and agent workflows

Budget GLM lane for fast coding help, routing, and everyday automation

Efficient GLM model for fast reasoning, coding, and agent workflows

Budget GLM lane for fast coding help, routing, and everyday automation

Efficient GLM model for fast reasoning, coding, and agent workflows

Efficient GLM model for fast reasoning, coding, and agent workflows

Multimodal model for analyzing text, images, documents, and rich media

Efficient Mistral model for fast chat, extraction, and production assistants

Flagship model for demanding analysis, coding, and production agent workflows

General-purpose chat model for instruction following, writing, and analysis

Efficient model for low-latency assistance, extraction, and routine automation

Image model for prompt-driven generation, editing, and visual design workflows

Image model for prompt-driven generation, editing, and visual design workflows

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

Devstral 2 123B Instruct 2512 TEE from Chutes - text input, 262,144 token context

MiroThinker V1.5 235B from Chutes - text input, 262,144 token context

Molmo2-8B is an open vision-language model developed by the Allen Institute for AI (Ai2) as part of the Molmo2 family, supporting image, video, and multi-image understanding and grounding. It is based on Qwen3-8B and uses SigLIP 2 as its vision backbone, outperforming other open-weight, open-data models on short videos, counting, and captioning, while remaining competitive on long-video tasks.

Olmo 3.1 32B Instruct is a large-scale, 32-billion-parameter instruction-tuned language model engineered for high-performance conversational AI, multi-turn dialogue, and practical instruction following. As part of the Olmo 3.1 family, this...

Coding model for repository understanding, refactors, and agentic engineering tasks

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Kimi K2.5 TEE from Chutes - text, image, video input, 262,144 token context

Kimi K2.5 from Synthetic - text, image input, 262,144 token context

Kimi K2.5 (NVFP4) from Synthetic - text, image input, 262,144 token context

Kimi multimodal agent model for visual understanding, coding, and planning

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Hermes 4.3 36B from Chutes - text input, 32,768 token context

Hermes 4 70B from Chutes - text input, 131,072 token context

Hermes 4 14B from Chutes - text input, 40,960 token context

Hermes 4 405B FP8 TEE from Chutes - text input, 131,072 token context