diff --git a/docs/my-website/blog/claude_opus_4_7/index.md b/docs/my-website/blog/claude_opus_4_7/index.md new file mode 100644 index 0000000000..16b4275e3a --- /dev/null +++ b/docs/my-website/blog/claude_opus_4_7/index.md @@ -0,0 +1,367 @@ +--- +slug: claude_opus_4_7 +title: "Day 0 Support: Claude Opus 4.7" +date: 2026-04-16T10:00:00 +authors: + - sameer + - ishaan-alt + - krrish +description: "Day 0 support for Claude Opus 4.7 on LiteLLM AI Gateway - use across Anthropic, Azure, Vertex AI, and Bedrock." +tags: [anthropic, claude, opus 4.7] +hide_table_of_contents: false +--- + +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +LiteLLM now supports [Claude Opus 4.7](https://www.anthropic.com/news/claude-opus-4-7) on Day 0. Use it across Anthropic, Azure, Vertex AI, and Bedrock through the LiteLLM AI Gateway. + +{/* truncate */} + +## Docker Image + +```bash +docker pull ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.82.0-stable.opus-4-7 +``` + +## Usage - Anthropic + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: claude-opus-4-7 + litellm_params: + model: anthropic/claude-opus-4-7 + api_key: os.environ/ANTHROPIC_API_KEY +``` + +**2. Start the proxy** + +```bash +docker run -d \ + -p 4000:4000 \ + -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \ + -v $(pwd)/config.yaml:/app/config.yaml \ + ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.82.0-stable.opus-4-7 \ + --config /app/config.yaml +``` + +**3. Test it!** + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-7", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ] +}' +``` + + + + +## Usage - Azure + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: claude-opus-4-7 + litellm_params: + model: azure_ai/claude-opus-4-7 + api_key: os.environ/AZURE_AI_API_KEY + api_base: os.environ/AZURE_AI_API_BASE # https://.services.ai.azure.com +``` + +**2. Start the proxy** + +```bash +docker run -d \ + -p 4000:4000 \ + -e AZURE_AI_API_KEY=$AZURE_AI_API_KEY \ + -e AZURE_AI_API_BASE=$AZURE_AI_API_BASE \ + -v $(pwd)/config.yaml:/app/config.yaml \ + ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.82.0-stable.opus-4-7 \ + --config /app/config.yaml +``` + +**3. Test it!** + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-7", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ] +}' +``` + + + + +## Usage - Vertex AI + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: claude-opus-4-7 + litellm_params: + model: vertex_ai/claude-opus-4-7 + vertex_project: os.environ/VERTEX_PROJECT + vertex_location: us-east5 +``` + +**2. Start the proxy** + +```bash +docker run -d \ + -p 4000:4000 \ + -e VERTEX_PROJECT=$VERTEX_PROJECT \ + -e GOOGLE_APPLICATION_CREDENTIALS=/app/credentials.json \ + -v $(pwd)/config.yaml:/app/config.yaml \ + -v $(pwd)/credentials.json:/app/credentials.json \ + ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.82.0-stable.opus-4-7 \ + --config /app/config.yaml +``` + +**3. Test it!** + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-7", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ] +}' +``` + + + + +## Usage - Bedrock + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: claude-opus-4-7 + litellm_params: + model: bedrock/anthropic.claude-opus-4-7-v1 + aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID + aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY + aws_region_name: us-east-1 +``` + +**2. Start the proxy** + +```bash +docker run -d \ + -p 4000:4000 \ + -e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \ + -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \ + -v $(pwd)/config.yaml:/app/config.yaml \ + ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.82.0-stable.opus-4-7 \ + --config /app/config.yaml +``` + +**3. Test it!** + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-7", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ] +}' +``` + + + + +## Advanced Features + +### Adaptive Thinking + +:::note +When using `reasoning_effort` with Claude Opus 4.7, all values (`low`, `medium`, `high`, `xhigh`, `max`) are mapped to `thinking: {type: "adaptive"}`. To use explicit thinking budgets with `type: "enabled"`, pass the native `thinking` parameter directly. +::: + + + + +LiteLLM supports adaptive thinking through the `reasoning_effort` parameter: + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-7", + "messages": [ + { + "role": "user", + "content": "Solve this complex problem: What is the optimal strategy for..." + } + ], + "reasoning_effort": "high" +}' +``` + + + + +Use the `thinking` parameter with `type: "adaptive"` to enable adaptive thinking mode: + +```bash +curl --location 'http://0.0.0.0:4000/v1/messages' \ +--header 'x-api-key: sk-12345' \ +--header 'content-type: application/json' \ +--data '{ + "model": "claude-opus-4-7", + "max_tokens": 16000, + "thinking": { + "type": "adaptive" + }, + "messages": [ + { + "role": "user", + "content": "Explain why the sum of two even numbers is always even." + } + ] +}' +``` + + + + +### Effort Levels + +Claude Opus 4.7 supports five effort levels: `low`, `medium`, `high` (default), `xhigh`, and `max`. These give you finer-grained control over how much reasoning the model applies to a task. Pass the effort level via the `output_config` parameter. + +`xhigh` is a new effort level introduced with Opus 4.7 that sits between `high` and `max`. `max` is available on Claude Opus 4.6 and 4.7 only. + + + + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-7", + "messages": [ + { + "role": "user", + "content": "Explain quantum computing" + } + ], + "output_config": { + "effort": "max" + } +}' +``` + +**Using OpenAI SDK:** + +```python +import openai + +client = openai.OpenAI( + api_key="your-litellm-key", + base_url="http://0.0.0.0:4000" +) + +response = client.chat.completions.create( + model="claude-opus-4-7", + messages=[{"role": "user", "content": "Explain quantum computing"}], + extra_body={"output_config": {"effort": "max"}} +) +``` + +**Using LiteLLM SDK:** + +```python +from litellm import completion + +response = completion( + model="anthropic/claude-opus-4-7", + messages=[{"role": "user", "content": "Explain quantum computing"}], + output_config={"effort": "max"}, +) +``` + +You can combine `reasoning_effort` with `output_config` for even more fine-grained control over the model's behavior. + + + + +```bash +curl --location 'http://0.0.0.0:4000/v1/messages' \ +--header 'x-api-key: sk-12345' \ +--header 'content-type: application/json' \ +--data '{ + "model": "claude-opus-4-7", + "max_tokens": 4096, + "messages": [ + { + "role": "user", + "content": "Explain quantum computing" + } + ], + "output_config": { + "effort": "max" + } +}' +``` + + + + +**Effort level guide:** + +| Effort | When to use | +|--------|-------------| +| `low` | Short, fast responses — simple lookups, formatting, classification | +| `medium` | Balanced tradeoff for everyday Q&A and light reasoning | +| `high` (default) | Complex reasoning, code generation, analysis | +| `xhigh` | Harder reasoning than `high` when `max` is overkill — tough debugging, non-trivial planning | +| `max` | Hardest problems — multi-step math, deep research, agentic planning (Opus 4.6 and 4.7 only) | + diff --git a/litellm/anthropic_beta_headers_config.json b/litellm/anthropic_beta_headers_config.json index 7dd5975b7b..662b62cf20 100644 --- a/litellm/anthropic_beta_headers_config.json +++ b/litellm/anthropic_beta_headers_config.json @@ -71,12 +71,12 @@ "computer-use-2025-01-24": "computer-use-2025-01-24", "computer-use-2025-11-24": "computer-use-2025-11-24", "context-1m-2025-08-07": "context-1m-2025-08-07", - "context-management-2025-06-27": "context-management-2025-06-27", + "context-management-2025-06-27": null, "effort-2025-11-24": null, "fast-mode-2026-02-01": null, "files-api-2025-04-14": null, "fine-grained-tool-streaming-2025-05-14": null, - "interleaved-thinking-2025-05-14": "interleaved-thinking-2025-05-14", + "interleaved-thinking-2025-05-14": null, "mcp-client-2025-11-20": null, "mcp-client-2025-04-04": null, "mcp-servers-2025-12-04": null, @@ -102,12 +102,12 @@ "computer-use-2025-01-24": "computer-use-2025-01-24", "computer-use-2025-11-24": "computer-use-2025-11-24", "context-1m-2025-08-07": "context-1m-2025-08-07", - "context-management-2025-06-27": "context-management-2025-06-27", + "context-management-2025-06-27": null, "effort-2025-11-24": null, "fast-mode-2026-02-01": null, "files-api-2025-04-14": null, "fine-grained-tool-streaming-2025-05-14": null, - "interleaved-thinking-2025-05-14": "interleaved-thinking-2025-05-14", + "interleaved-thinking-2025-05-14": null, "mcp-client-2025-11-20": null, "mcp-client-2025-04-04": null, "mcp-servers-2025-12-04": null, diff --git a/litellm/llms/anthropic/chat/transformation.py b/litellm/llms/anthropic/chat/transformation.py index fcb87c721b..eca41b3c8d 100644 --- a/litellm/llms/anthropic/chat/transformation.py +++ b/litellm/llms/anthropic/chat/transformation.py @@ -1534,13 +1534,20 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig): f"Invalid effort value: {effort}. Must be one of: " f"'high', 'medium', 'low', 'xhigh', 'max'" ) - # xhigh / max are opt-in effort levels; gate them on the model map - # capability flag (``supports_xhigh_reasoning_effort`` / ``supports_max_reasoning_effort``). - if effort in ("xhigh", "max") and not self._supports_effort_level( - model, effort + # ``max`` is Claude Opus 4.6 and 4.7 only (not Sonnet 4.6, not Opus 4.5). + # Keep this hardcoded so the error message is specific and stable. + if effort == "max" and not ( + self._is_opus_4_6_model(model) or self._is_opus_4_7_model(model) ): raise ValueError( - f"effort={effort!r} is not supported by this model. Got model: {model}" + f"effort='max' is only supported by Claude Opus 4.6 and 4.7. " + f"Got model: {model}" + ) + # ``xhigh`` is data-driven via ``supports_xhigh_reasoning_effort`` so + # enabling it for a new model is a pure model-map change. + if effort == "xhigh" and not self._supports_effort_level(model, "xhigh"): + raise ValueError( + f"effort='xhigh' is not supported by this model. Got model: {model}" ) data["output_config"] = output_config diff --git a/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py b/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py index 6b8a4086ef..a76c411821 100644 --- a/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py +++ b/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py @@ -432,7 +432,10 @@ def test_bedrock_invoke_messages_skips_thinking_injection_when_already_enabled() litellm_params=GenericLiteLLMParams(), headers={}, ) - assert result["thinking"]["budget_tokens"] == 2048 + # Claude 4.6/4.7 reject ``thinking.type=enabled``; legacy ``enabled`` is + # translated to ``adaptive`` (budget_tokens => output_config.effort) and the + # pre-4.6 ``interleaved-thinking-2025-05-14`` beta must not be attached. + assert result["thinking"]["type"] == "adaptive" betas = result.get("anthropic_beta") or [] assert "interleaved-thinking-2025-05-14" not in betas diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 0acbe90130..67b6269619 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -771,6 +771,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "supports_minimal_reasoning_effort": {"type": "boolean"}, "supports_none_reasoning_effort": {"type": "boolean"}, "supports_xhigh_reasoning_effort": {"type": "boolean"}, + "supports_max_reasoning_effort": {"type": "boolean"}, "supports_service_tier": {"type": "boolean"}, "supports_preset": {"type": "boolean"}, "tool_use_system_prompt_tokens": {"type": "number"},