Agent-ready GPT for coding and computer-use workflows at a lower cost
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Strongest Claude Opus model for coding, agents, and professional work
Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Balanced GPT-5.6 model for capable, cost-efficient everyday work
Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
Everyday Claude agent model for coding, planning, browsing, and general work
Sharper GPT-5 generation for coding, product work, and tool-assisted tasks
Cost-efficient GPT-5.6 model for fast, high-volume workloads
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
Open MoE flagship with million-token context for coding and long agent runs
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking
Open Gemma instruction model for efficient chat and self-hosted deployments
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Small GPT-5 for responsive agents, coding help, and everyday automation
Google's proven reasoning model for coding, math, and multimodal analysis
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
Affordable GPT-4.1 lane for fast coding help and structured extraction
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
Open GPT reasoning model for self-hosted agents and controllable deployments
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks
Open GPT reasoning model for self-hosted agents and controllable deployments
Largest open Gemma 3 instruction model for multilingual text generation and visual understanding
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| GPT-5.4openai/gpt-5.4 | 53.1 | 1.05M | $2.5 | $15 | 2026-03-05 | |||
| Claude Opus 5anthropic/claude-opus-5 | 50.7 | 1M | $5 | $25 | 2026-07-24 | |||
| GPT-5.6 Solopenai/gpt-5.6-sol | 47.1 | 1.05M | $4 | $20 | 2026-07-09 | |||
| Kimi K2.6moonshotai/kimi-k2.6 | 45.1 | 262.144K | $0.95 | $4 | 2026-04-21 | |||
| Kimi K3moonshotai/kimi-k3 | 43.8 | 1.04858M | $3 | $15 | 2026-07-16 | |||
| GPT-5.6 Terraopenai/gpt-5.6-terra | 42.3 | 1.05M | $2 | $12 | 2026-07-09 | |||
| Gemini 3.8 Flashgoogle/gemini-3.8-flash | 41.2 | 1.04858M | $0.75 | $3.75 | 2026-09-02 | |||
| Gemini 3.7 Flashgoogle/gemini-3.7-flash | 39.4 | 1.04858M | $0.75 | $3.75 | 2026-08-13 | |||
| Claude Sonnet 5anthropic/claude-sonnet-5 | 38.4 | 1M | $2 | $10 | 2026-06-30 | |||
| GPT-5.1openai/gpt-5.1 | 37.5 | 400K | $1.25 | $10 | 2025-11-13 | |||
| GPT-5.6 Lunaopenai/gpt-5.6-luna | 37.5 | 1.05M | $0.2 | $1.2 | 2026-07-09 | |||
| DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813 | 36.3 | 1M | $0.442 | $0.884 | 2026-08-12 | |||
| Kimi K2.5moonshotai/kimi-k2.5 | 36.0 | 262.144K | $0.3 | $1.9 | 2026-01 | |||
| GPT-5openai/gpt-5 | 35.3 | 400K | $1.25 | $10 | 2025-08-07 | |||
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | 34.5 | 1M | $0.035 | $0.07 | 2026-07-31 | |||
| Gemini 3.6 Flashgoogle/gemini-3.6-flash | 34.3 | 1.04858M | $0.75 | $3.75 | 2026-07-21 | |||
| Gemini 3.5 Flashgoogle/gemini-3.5-flash | 33.0 | 1.04858M | $1.5 | $9 | 2026-05-19 | |||
| DeepSeek V3.2deepseek/deepseek-v3.2 | 32.6 | 128K | $0.18 | $0.35 | 2025-12-01 | |||
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | 30.9 | 1M | $0.435 | $0.87 | 2026-04-24 | |||
| Kimi K2.7 Codemoonshotai/kimi-k2.7-code | 26.3 | 262.144K | $0.95 | $4 | 2026-06-12 | |||
| Gemma 4 26B A4B ITgoogle/gemma-4-26b-a4b-it | 26.1 | 262.144K | $0.042 | $0.22 | 2026-04-02 | |||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | 24.8 | 1M | $0.15 | $0.6 | 2026-04-24 | |||
| Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | 22.7 | 1.04858M | $0.3 | $2.5 | 2026-07-21 | |||
| GPT-5 Miniopenai/gpt-5-mini | 17.4 | 400K | $0.25 | $2 | 2025-08-07 | |||
| Gemini 2.5 Progoogle/gemini-2.5-pro | 16.7 | 1.04858M | $1.25 | $10 | 2025-06-17 | |||
| Gemma 4 31B ITgoogle/gemma-4-31b-it | 15.4 | 262.144K | $0.09 | $0.34 | 2026-04-02 | |||
| GPT-4.1 miniopenai/gpt-4.1-mini | 14.8 | 1.04758M | $0.4 | $1.6 | 2025-04-14 | |||
| Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b | 13.6 | 262.144K | $0.2 | $0.8 | 2026-03-11 | |||
| GPT OSS 120Bopenai/gpt-oss-120b | 12.3 | 131.072K | $0.03 | $0.17 | 2025-08-05 | |||
| GPT-4.1 nanoopenai/gpt-4.1-nano | 9.6 | 1.04758M | $0.1 | $0.4 | 2025-04-14 | |||
| GPT OSS 20Bopenai/gpt-oss-20b | 9.0 | 131.072K | $0.02 | $0.1 | 2025-08-05 | |||
| Gemma 3 27B ITgoogle/gemma-3-27b-it | 4.9 | 131.072K | $0.08 | $0.16 | 2025-03-12 |