GPT 5.5:
Everything you need to know about the model

GPT-5.5 is Anthropic's most capable large language model, designed for complex reasoning, nuanced analysis, and long-horizon tasks that require sustained attention across a 200K-token context window.


GPT 5.5 consistently outperforms previous Opus generations on reasoning benchmarks and instruction-following evaluations.


GPT 5.5 performance*

Intelligence
26%
Coding
12%
Agentic
46%
*Performance data is provided by Artificial Analysis and is subject to change.

GPT 5.5 pricing

| Provider | Speed (output tokens / sec) | Latency time (time to first token) | Context window | |--------------------|-----------------------------|------------------------------------|----------------| | OpenAI | 55 tok/s | 1.1s | 200K | | Azure OpenAI | 47 tok/s | 1.3s | 200K | | AWS Bedrock | 82 tok/s | 1.5s | 200K | | Google Vertex AI | 24 tok/s | 1.8s | 200K | | Groq | 315 tok/s *LPU-accelerated* | 0.28s | 32K | | Together AI | 88 tok/s | 0.75s | 200K | | Fireworks AI | 95 tok/s | 0.68s | 200K |

Test GPT 5.5 with Merge Gateway’s Simulator

GPT 5.5
Synced
Synced
Run simulation to see response

Ready to try it out?

Start routing requests to hundreds of large language models in your product in minutes.

Route requests to GPT 5.5 with Merge Gateway

Merge Gateway is a unified LLM API that lets your product route requests to GPT 5.5 and every other major model through a single endpoint. You get built-in fallback routing, per-request cost tracking, zero data retention support, and observability without changing your application architecture.
To get started in seconds, add our Gateway Implementation skill to your project, or pick your preferred SDK below. Check out our other quick start skills here.
Install the Merge Gateway SDK
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Make your first API call
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Try a diffrent model
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Install the Merge Gateway SDK
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Make your first API call
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Try a diffrent model
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Install the Merge Gateway SDK
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Make your first API call
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Try a diffrent model
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Install the Merge Gateway SDK
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Make your first API call
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Try a diffrent model
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11

Explore other models available in Merge Gateway

gpt-5-5
GPT 5.5

GPT 5.5 FAQ

In case you have any more questions on using GPT 5.5, we’ve addressed several more commonly-asked questions below.

Heading

What other models does anthropic support?

Anthropic’s current model lineup spans three tiers. GPT 5.5 is the most capable, built for complex reasoning and long-horizon tasks. Claude Sonnet 4.6 sits in the middle: strong performance at a meaningfully lower cost, suited for production workloads where quality and economics both matter. Claude Haiku 4.5 is the fastest and cheapest, optimized for high-volume, latency-sensitive tasks like classification, summarization, and simple Q&A.

What other models does anthropic support?

Anthropic’s current model lineup spans three tiers. GPT 5.5 is the most capable, built for complex reasoning and long-horizon tasks. Claude Sonnet 4.6 sits in the middle: strong performance at a meaningfully lower cost, suited for production workloads where quality and economics both matter. Claude Haiku 4.5 is the fastest and cheapest, optimized for high-volume, latency-sensitive tasks like classification, summarization, and simple Q&A.

Route to Claude GPT with Merge Gateway

One API key. Every major model. Built-in fallbacks, cost tracking, and zero data retention.