Compare Claude Haiku 4.5 from Anthropic and GPT-5.1 from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
| Attribute | Claude Haiku 4.5 | GPT-5.1 |
|---|---|---|
| Input price | $1/M tokens | $1.25/M tokens |
| Output price | $5/M tokens | $10/M tokens |
| Context window | 200,000 tokens | 400,000 tokens |
| Intelligence Index | 7.4 | Not available |
| Coding Index | 43.9 | 49.4 |
| Agentic Index | 8.0 | Not available |
| Latency (p50) | 0.62 s | 0.92 s |
| Throughput (p50) | 85.0 tok/s | 66.0 tok/s |
| Provided by | Anthropic | OpenAI |
| Model page | Claude Haiku 4.5 model details, providers and pricing | GPT-5.1 model details, providers and pricing |
Benchmark data updated
Claude Haiku 4.5 is cheaper than GPT-5.1 on OpenRouter: Claude Haiku 4.5 costs $1/M tokens input and $5/M tokens output, while GPT-5.1 costs $1.25/M tokens input and $10/M tokens output.
GPT-5.1 has the longer context window at 400,000 tokens, compared with 200,000 tokens for Claude Haiku 4.5.
Claude Haiku 4.5 is faster on OpenRouter, generating a median 85.0 tokens per second compared with 66.0 tokens per second for GPT-5.1.
GPT-5.1 scores higher on coding, with an Artificial Analysis Coding Index of 49.4 compared with 43.9 for Claude Haiku 4.5.