Coding-optimized GPT model for repository edits, reviews, and agentic software work
13 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
17 providers
StepFun flash model for efficient multimodal reasoning, coding, and tool use
6 providers
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
14 providers
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
29 providers
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
18 providers
Hybrid-reasoning GLM release that made the 4.5 line broadly useful
14 providers
Flagship Qwen3 model for coding agents, complex reasoning, and tool use
20 providers
Lighter GLM-4.5 variant for fast coding assistance and cheaper agents
11 providers
Fast Mistral production model for chat, extraction, and cost-sensitive agents
12 providers
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...
30 providers
DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....
14 providers
GLM vision model for visual reasoning, documents, and multimodal agents
7 providers
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
18 providers
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
25 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| GPT-5-Codexopenai/gpt-5-codex | OpenAI |
37.9 | 400K | $1.1 | $9 | 2025-09-15 | ||
| StepFun: Step 3.7 Flashstepfun/step-3.7-flash | StepFun |
35.6 | 256K | $0.2 | $1.15 | 2026-05-29 | ||
| Step 3.5 Flash 2603stepfun/step-3.5-flash-2603 | StepFun |
32.6 | 256K | $0.1 | $0.3 | 2026-04-02 | ||
| StepFun: Step 3.5 Flashstepfun/step-3.5-flash | StepFun |
27.3 | 262.144K | $0.1 | $0.3 | 2026-01-29 | ||
| Google: Gemini 2.5 Progoogle/gemini-2.5-pro | Google |
26.5 | 1.04858M | $1.25 | $10 | 2025-06-17 | ||
| GLM-4.6zhipuai/glm-4.6 | Zhipu AI |
25.0 | 204.8K | $0.6 | $2.2 | 2025-09-30 | ||
| GLM-4.5zhipuai/glm-4.5 | Zhipu AI |
22.0 | 131.072K | $0.6 | $2.2 | 2025-07-28 | ||
| Qwen3 Maxalibaba/qwen3-max | Alibaba Qwen |
20.5 | 262.144K | $1.2 | $6 | 2025-09-23 | ||
| GLM-4.5-Airzhipuai/glm-4.5-air | Zhipu AI |
20.5 | 131.072K | $0.2 | $1.1 | 2025-07-28 | ||
| Mistral Small 4mistral/mistral-small-2603 | Mistral AI |
17.4 | 256K | $0.15 | $0.6 | 2026-03-16 | ||
| Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash | Google |
13.6 | 1.04858M | $0.3 | $2.5 | 2025-06-17 | ||
| DeepSeek: R1deepseek/deepseek-r1 | DeepSeek |
6.1 | 64K | $0.7 | $2.5 | 2025-01-20 | ||
| GLM-4.5Vzhipuai/glm-4.5v | Zhipu AI |
5.3 | 64K | $0.6 | $1.8 | 2025-08-11 | ||
| Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | Google |
4.5 | 1.04858M | $0.1 | $0.4 | 2025-06-17 | ||
| Llama-3.3-70B-Instructmeta/llama-3.3-70b-instruct | Meta |
3.0 | 128K | $0.1 | $0.32 | 2024-12-06 |