Open flagship GLM for long-horizon coding agents and million-token context work
72 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
62 providers
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
62 providers
Qwen vision-language model for visual reasoning, documents, and agent tasks
24 providers
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
7 providers
Open multimodal Qwen MoE for local agents that need vision, audio, and code
19 providers
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
33 providers
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
22 providers
Qwen vision-language model for visual reasoning, documents, and agent tasks
14 providers
Qwen vision-language model for visual reasoning, documents, and agent tasks
16 providers
Qwen vision-language model for visual reasoning, documents, and agent tasks
11 providers
Large open Qwen multimodal MoE for visual agents and long technical tasks
18 providers
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...
53 providers
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...
32 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| GLM-5.2zhipuai/glm-5.2 | Zhipu AI |
1M | $1.4 | $4.4 | 2026-06-13 | ||
| DeepSeek: DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro | DeepSeek |
1.024M | $0.86 | $1.72 | 2026-04-24 | ||
| DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | DeepSeek |
1.024M | $0.086 | $0.172 | 2026-04-24 | ||
| Qwen3.6 27Balibaba/qwen3.6-27b | Alibaba Qwen |
262.144K | $0.6 | $3.6 | 2026-04-22 | ||
| Tencent: Hy3 previewtencent/hy3-preview | Tencent |
262.144K | $0.18 | $0.6 | 2026-04-20 | ||
| Qwen3.6 35B-A3Balibaba/qwen3.6-35b-a3b | Alibaba Qwen |
262.144K | $0.248 | $1.485 | 2026-04-17 | ||
| Google: Gemma 4 31Bgoogle/gemma-4-31b-it | Google |
262.144K | $0.09 | $0.34 | 2026-04-02 | ||
| Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | Google |
131.072K | $0.042 | $0.22 | 2026-04-02 | ||
| Qwen3.5 27Balibaba/qwen3.5-27b | Alibaba Qwen |
262.144K | $0.3 | $2.4 | 2026-02-23 | ||
| Qwen3.5 122B-A10Balibaba/qwen3.5-122b-a10b | Alibaba Qwen |
262.144K | $0.4 | $3.2 | 2026-02-23 | ||
| Qwen3.5 35B-A3Balibaba/qwen3.5-35b-a3b | Alibaba Qwen |
262.144K | $0.25 | $2 | 2026-02-23 | ||
| Qwen3.5 397B-A17Balibaba/qwen3.5-397b-a17b | Alibaba Qwen |
262.144K | $0.6 | $3.6 | 2026-02-15 | ||
| OpenAI: gpt-oss-120bopenai/gpt-oss-120b | OpenAI |
131.072K | $0.037 | $0.17 | 2025-08-05 | ||
| OpenAI: gpt-oss-20bopenai/gpt-oss-20b | OpenAI |
131.072K | $0.03 | $0.13 | 2025-08-05 |