Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
High-effort o3 tier for difficult technical reasoning and careful answers
Google's proven reasoning model for coding, math, and multimodal analysis
Deliberate o-series reasoner for hard math, coding, and multi-step analysis
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Fast o-series model for compact reasoning, coding, and tool use
DeepSeek chat model for instruction following, coding, and analysis
Balanced Claude model for coding, analysis, agent workflows, and cost control
O-series reasoning model for hard analysis, math, coding, and planning
Balanced Claude model for coding, analysis, agent workflows, and cost control
Smaller o-series reasoner for economical coding, math, and planning tasks
Large open Qwen MoE for multilingual reasoning, coding, and tool use
Classic open reasoning model for transparent math, coding, and deliberate problem solving
Fast Gemini workhorse for multimodal apps where latency and price matter
Long-lived GPT workhorse for coding, instruction following, and production apps
Dense open Qwen model for self-hosted chat, reasoning, and coding
Affordable GPT-4.1 lane for fast coding help and structured extraction
Omni-era GPT for multimodal chat, practical coding, and general assistants
GPT model for general reasoning, writing, coding, and tool-assisted tasks
Flagship Qwen model for complex reasoning, coding, and agentic workflows
GPT model for general reasoning, writing, coding, and tool-assisted tasks
Open multimodal Llama for strong reasoning with efficient everyday serving
Cohere command model for multilingual enterprise agents, tools, and chat
Mistral code model for completions, refactors, and developer IDE workflows
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks
Small omni GPT for cheap multimodal assistance and production-scale traffic
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| GPT-5openai/gpt-5 | 88.0 | 400K | $1.25 | $10 | 2025-08-07 | |||
| o3-proopenai/o3-pro | 84.9 | 200K | $20 | $80 | 2025-06-10 | |||
| Gemini 2.5 Progoogle/gemini-2.5-pro | 83.1 | 1.04858M | $1.25 | $10 | 2025-06-17 | |||
| o3openai/o3 | 81.3 | 200K | $2 | $8 | 2025-04-16 | |||
| DeepSeek Reasonerdeepseek/deepseek-reasoner | 74.2 | 1M | $0.147 | $0.295 | 2025-12-01 | |||
| Claude Opus 4anthropic/claude-opus-4-20250514 | 72.0 | 200K | $15 | $75 | 2025-05-22 | |||
| o4-miniopenai/o4-mini | 72.0 | 200K | $1.1 | $4.4 | 2025-04-16 | |||
| DeepSeek Chatdeepseek/deepseek-chat | 70.2 | 1M | $0.147 | $0.295 | 2025-12-01 | |||
| Claude Sonnet 3.7anthropic/claude-3-7-sonnet-20250219 | 64.9 | 200K | $3 | $15 | 2025-02-19 | |||
| o1openai/o1 | 61.7 | 200K | $15 | $60 | 2024-12-05 | |||
| Claude Sonnet 4 (latest)anthropic/claude-sonnet-4-0 | 61.3 | 200K | $2.898 | $14.493 | 2025-05-22 | |||
| o3-miniopenai/o3-mini | 60.4 | 200K | $1.1 | $4.4 | 2024-12-20 | |||
| Qwen3 235B-A22Balibaba/qwen3-235b-a22b | 59.6 | 131.072K | $0.7 | $2.8 | 2025-04 | |||
| DeepSeek-R1deepseek/deepseek-r1 | 56.9 | 128K | $0.7 | $2.5 | 2025-01-20 | |||
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | 55.1 | 1.04858M | $0.3 | $2.5 | 2025-06-17 | |||
| GPT-4.1openai/gpt-4.1 | 52.4 | 1.04758M | $2 | $8 | 2025-04-14 | |||
| Qwen3 32Balibaba/qwen3-32b | 40.0 | 131.072K | $0.7 | $2.8 | 2025-04 | |||
| GPT-4.1 miniopenai/gpt-4.1-mini | 32.4 | 1.04758M | $0.4 | $1.6 | 2025-04-14 | |||
| GPT-4oopenai/gpt-4o | 23.1 | 128K | $2.5 | $10 | 2024-05-13 | |||
| GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | 23.1 | 128K | $2.5 | $10 | 2024-08-06 | |||
| Qwen Maxalibaba/qwen-max | 21.8 | 32.768K | $1.6 | $6.4 | 2024-04-03 | |||
| GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | 18.2 | 128K | $2.5 | $10 | 2024-11-20 | |||
| Llama 4 Maverick 17B Instructmeta/llama-4-maverick-17b-instruct | 15.6 | 1M | $0.14 | $0.59 | 2025-04-05 | |||
| Command Acohere/command-a-03-2025 | 12.0 | 256K | $2.5 | $10 | 2025-03-13 | |||
| Codestral (latest)mistral/codestral-latest | 11.1 | 256K | $0.3 | $0.9 | 2024-05-29 | |||
| GPT-4.1 nanoopenai/gpt-4.1-nano | 8.9 | 1.04758M | $0.1 | $0.4 | 2025-04-14 | |||
| GPT-4o miniopenai/gpt-4o-mini | 3.6 | 128K | $0.15 | $0.6 | 2024-07-18 |