Coding-optimized GPT model for repository edits, reviews, and agentic software work
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Newer StepFun flash model for faster agents, coding, and multimodal prompts
StepFun flash model for efficient multimodal reasoning, coding, and tool use
Cohere coding model for practical software engineering and agentic edits
Google's proven reasoning model for coding, math, and multimodal analysis
StepFun flash lane for quick multimodal reasoning and coding assistance
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
Flagship Qwen3 model for coding agents, complex reasoning, and tool use
Hybrid-reasoning GLM release that made the 4.5 line broadly useful
Fast Mistral production model for chat, extraction, and cost-sensitive agents
GPT model for general reasoning, writing, coding, and tool-assisted tasks
Mistral's coding-agent model for repository work, terminal tasks, and software fixes
Mistral's largest general model for enterprise agents, coding, and multilingual reasoning
Fast Gemini workhorse for multimodal apps where latency and price matter
Compact GPT model for low-latency assistance and high-volume workloads
Smaller Qwen coder for efficient local agents and repo-level fixes
GPT model for general reasoning, writing, coding, and tool-assisted tasks
GPT model for general reasoning, writing, coding, and tool-assisted tasks
Classic open reasoning model for transparent math, coding, and deliberate problem solving
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| GPT-5-Codexopenai/gpt-5-codex | 38.9 | 400K | $1.1 | $9 | 2025-09-15 | |||
| Step 3.7 Flashstepfun/step-3.7-flash | 37.1 | 256K | $0.185 | $1.11 | 2026-05-29 | |||
| Step 3.5 Flash 2603stepfun/step-3.5-flash-2603 | 34.6 | 256K | $0.1 | $0.3 | 2026-04-02 | |||
| North Mini Codecohere/north-mini-code-1-0 | 33.4 | 256K | — | — | 2026-06-09 | |||
| Gemini 2.5 Progoogle/gemini-2.5-pro | 32.0 | 1.04858M | $1.25 | $10 | 2025-06-17 | |||
| Step 3.5 Flashstepfun/step-3.5-flash | 31.6 | 256K | $0.1 | $0.3 | 2026-01-29 | |||
| GLM-4.6zhipuai/glm-4.6 | 29.5 | 204.8K | $0.6 | $2.2 | 2025-09-30 | |||
| Qwen3 Maxalibaba/qwen3-max | 26.4 | 262.144K | $1.2 | $6 | 2025-09-23 | |||
| GLM-4.5zhipuai/glm-4.5 | 26.3 | 131.072K | $0.6 | $2.2 | 2025-07-28 | |||
| Mistral Small 4mistral/mistral-small-2603 | 24.3 | 256K | $0.15 | $0.6 | 2026-03-16 | |||
| GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13 | 24.2 | 128K | $5 | $15 | 2024-05-13 | |||
| Devstral 2mistral/devstral-2512 | 23.7 | 262.144K | $0.4 | $2 | 2025-12-09 | |||
| Mistral Large 3mistral/mistral-large-2512 | 22.7 | 262.144K | $0.5 | $1.5 | 2024-11-01 | |||
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | 22.2 | 1.04858M | $0.3 | $2.5 | 2025-06-17 | |||
| GPT-4 Turboopenai/gpt-4-turbo | 21.5 | 128K | $10 | $30 | 2023-11-06 | |||
| Qwen3-Coder 30B-A3B Instructalibaba/qwen3-coder-30b-a3b-instruct | 19.4 | 262.144K | $0.45 | $2.25 | 2025-04 | |||
| GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | 16.7 | 128K | $2.5 | $10 | 2024-11-20 | |||
| GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | 16.6 | 128K | $2.5 | $10 | 2024-08-06 | |||
| DeepSeek-R1deepseek/deepseek-r1 | 15.9 | 128K | $0.7 | $2.5 | 2025-01-20 | |||
| Mistral Medium 3mistral/mistral-medium-2505 | 13.6 | 131.072K | $0.4 | $2 | 2025-05-07 | |||
| Llama-3.3-70B-Instructmeta/llama-3.3-70b-instruct | 10.7 | 128K | $0.1 | $0.32 | 2024-12-06 | |||
| Gemini 2.5 Flash-Litegoogle/gemini-2.5-flash-lite | 9.5 | 1.04858M | $0.1 | $0.4 | 2025-06-17 |