Skip to content

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

chore: default Anthropic model to claude-opus-4-8

Oguz Vuruskaner04fdb2c83638
diff --git a/README.md b/README.md
index d5a501f..d79acae 100644
--- a/README.md
+++ b/README.md
@@ -98,7 +98,7 @@ Hyper-Extract relies on the LLM's structured output capability (`json_schema` or
| Platform | Verified Models |
|----------|-----------------|
| **OpenAI** | gpt-4o, gpt-4o-mini, gpt-5 |
-| **Anthropic** | claude-sonnet-4-6, claude-opus-4-1, claude-haiku-4-5 |
+| **Anthropic** | claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5 |
| **阿里云百炼** | qwen-plus, qwen-turbo, deepseek-r1 |
| **Local vLLM** | Qwen3.5-9B (GPTQ-Marlin) |
diff --git a/README_ZH.md b/README_ZH.md
index 30d9784..9c0b25d 100644
--- a/README_ZH.md
+++ b/README_ZH.md
@@ -98,7 +98,7 @@ Hyper-Extract 依赖大语言模型的结构化输出能力(`json_schema` 或
| 平台 | 已验证模型 |
|----------|-----------------|
| **OpenAI** | gpt-4o, gpt-4o-mini, gpt-5 |
-| **Anthropic** | claude-sonnet-4-6, claude-opus-4-1, claude-haiku-4-5 |
+| **Anthropic** | claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5 |
| **阿里云百炼** | qwen-plus, qwen-turbo, deepseek-r1 |
| **本地 vLLM** | Qwen3.5-9B (GPTQ-Marlin) |
diff --git a/hyperextract/cli/config.py b/hyperextract/cli/config.py
index a5a275e..09d2c2d 100644
--- a/hyperextract/cli/config.py
+++ b/hyperextract/cli/config.py
@@ -32,12 +32,12 @@ PROVIDER_PRESETS: Dict[str, Dict[str, str | None]] = {
# Anthropic (Claude): native client, no base_url, no embeddings API.
"anthropic": {
"base_url": "",
- "default_llm": "claude-sonnet-4-6",
+ "default_llm": "claude-opus-4-8",
"default_embedder": None,
},
"claude": {
"base_url": "",
- "default_llm": "claude-sonnet-4-6",
+ "default_llm": "claude-opus-4-8",
"default_embedder": None,
},
}
diff --git a/hyperextract/utils/client.py b/hyperextract/utils/client.py
index 9b2510b..ac20e3a 100644
--- a/hyperextract/utils/client.py
+++ b/hyperextract/utils/client.py
@@ -50,12 +50,12 @@ PROVIDER_PRESETS: Dict[str, Dict[str, str | None]] = {
# OpenAI-compatible embedder.
"anthropic": {
"base_url": "",
- "default_llm": "claude-sonnet-4-6",
+ "default_llm": "claude-opus-4-8",
"default_embedder": None,
},
"claude": {
"base_url": "",
- "default_llm": "claude-sonnet-4-6",
+ "default_llm": "claude-opus-4-8",
"default_embedder": None,
},
}