Models
| Model | Description | Length limits for this model |
|---|---|---|
| Claude Opus 5 | Claude Opus 5.5 is built for long-running agentic coding and knowledge work. |
|
| Claude Opus 5 | Claude Opus 5 is a step-change improvement over Claude Opus 4.8, with the largest gains in deep reasoning, agentic and long-horizon tasks, and test-time compute scaling. |
|
| Claude Opus 4.8 | Claude Opus 4.8 is Anthropic's most capable model for complex reasoning and agentic coding |
|
| Claude Opus 4.7 | Claude Opus 4.7 is Anthropic's latest flagship model with a 1M ultra-large context window. It can independently build complex Agent Harnesses and complete highly complex productivity tasks based on Agent Teams, complex Skills, Tools, and other capabilities. |
|
| Claude Opus 4.6 | Claude Opus 4.6 is one of Anthropic's most powerful coding models, with exceptional reasoning, code generation, and complex task execution capabilities, suitable for high-difficulty programming scenarios. |
|
| Claude Sonnet 5.5 | Claude Sonnet 5.5 offers the best combination of speed and intelligence |
|
| Claude Sonnet 5 | Claude Sonnet 5 is The best combination of speed and intelligence. |
|
| Claude Sonnet 4.6 | Claude Sonnet 4.6 is Anthropic's latest generation cost-effective coding model with a 1M ultra-large context window. It excels in coding, reasoning, and tool calling, making it the best choice for daily development. |
|
| Claude Haiku 5.5 | Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. |
|
| GPT 6 Astra | GPT-6 Astra is our most capable model for the most demanding work. Use it for complex reasoning, coding, computer use, research, and document creation |
|
| GPT 6 Sol | GPT-6 Sol is built for complex coding and agentic workflows. |
|
| GPT 6 Luna | GPT-6 Luna is our most efficient model for focused, high-volume tasks. |
|
| GPT 5.6 Luna | GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly corresponds to the nano model tier used in earlier GPT-5 families. |
|
| GPT 5.6 Terra | GPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly corresponds to the mini model tier used in earlier GPT-5 families. |
|
| GPT 5.6 Sol | GPT-5.6 Sol is the frontier model in the GPT-5.6 family. It roughly corresponds to the unsuffixed model tier used in earlier GPT-5 families. The gpt-5.6 alias routes requests to GPT-5.6 Sol. |
|
| GPT 5.5 | GPT-5.5 is our newest frontier model for the most complex professional work. |
|
| GLM 5.2 | Superior code performance and advanced reasoning capabilities. |
|
| DeepSeek V4 Pro | Powered by massive high-quality training data, it features top-tier mathematical logic, complex reasoning, professional coding, and deep long-text analysis capabilities, suitable for advanced scientific research, complex office work, deep intelligent agents, and other high-difficulty scenarios. |
|
| Kimi K3 | Kimi K3 is Kimi's most capable flagship model to date, with 2.8 trillion parameters. Built on the KDA hybrid linear attention mechanism (Kimi Delta Attention) and Attention Residuals technology, it natively supports visual understanding and features a 1 million token context window. It is the world's first open-source model at the 3-trillion-parameter scale, designed for frontier intelligent scenarios such as long-horizon programming, knowledge work, and reasoning. |
|