Skip to content

Commit 101d23f

Browse files
Update providers/anthropic.mdx
Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
1 parent 1999c99 commit 101d23f

1 file changed

Lines changed: 26 additions & 43 deletions

File tree

providers/anthropic.mdx

Lines changed: 26 additions & 43 deletions
Original file line numberDiff line numberDiff line change
@@ -1,60 +1,43 @@
11
---
22
title: "Anthropic"
3-
description: "Learn how to configure and use Anthropic Claude models with CodinIT. Covers API key setup, model selection, and advanced features like prompt caching."
3+
description: "Configure Anthropic Claude models with CodinIT for advanced reasoning and code generation."
44
---
55

66
**Website:** [https://www.anthropic.com/](https://www.anthropic.com/)
77

8-
### Getting an API Key
8+
## Getting an API Key
99

10-
1. **Sign Up/Sign In:** Go to the [Anthropic Console](https://console.anthropic.com/). Create an account or sign in.
11-
2. **Navigate to API Keys:** Go to the [API keys](https://console.anthropic.com/settings/keys) section.
12-
3. **Create a Key:** Click "Create Key". Give your key a descriptive name (e.g., "CodinIT").
13-
4. **Copy the Key:** **Important:** Copy the API key _immediately_. You will not be able to see it again. Store it securely.
10+
1. Go to [Anthropic Console](https://console.anthropic.com/) and sign in
11+
2. Navigate to [API keys](https://console.anthropic.com/settings/keys)
12+
3. Click "Create Key" and name it (e.g., "CodinIT")
13+
4. Copy the key immediately - you won't see it again
1414

15-
### Supported Models
15+
## Configuration
1616

17-
CodinIT supports the following Anthropic Claude models:
17+
1. Click the settings icon (⚙️) in CodinIT
18+
2. Select "Anthropic" as the API Provider
19+
3. Paste your API key
20+
4. Choose your model
1821

19-
- `claude-haiku-4-5-20251001`
20-
- `claude-opus-4-1-20250805`
21-
- `claude-opus-4-20250514`
22-
- `anthropic/claude-sonnet-4.5` (Recommended)
23-
- `claude-3-7-sonnet-20250219`
24-
- `claude-3-5-sonnet-20241022`
25-
- `claude-3-5-haiku-20241022`
26-
- `claude-3-opus-20240229`
27-
- `claude-3-haiku-20240307`
22+
## Supported Models
2823

29-
See [Anthropic's Model Documentation](https://docs.anthropic.com/en/about-claude/models) for more details on each model's capabilities.
24+
- `anthropic/claude-sonnet-4.5` (Recommended)
25+
- `claude-opus-4-1-20250805`
26+
- `claude-3-7-sonnet-20250219`
27+
- `claude-3-5-sonnet-20241022`
28+
- `claude-3-5-haiku-20241022`
3029

31-
### Configuration in CodinIT
30+
See [Anthropic's documentation](https://docs.anthropic.com/en/about-claude/models) for full model details.
3231

33-
1. **Open CodinIT Settings:** Click the settings icon (⚙️) in the CodinIT panel.
34-
2. **Select Provider:** Choose "Anthropic" from the "API Provider" dropdown.
35-
3. **Enter API Key:** Paste your Anthropic API key into the "Anthropic API Key" field.
36-
4. **Select Model:** Choose your desired Claude model from the "Model" dropdown.
37-
5. **(Optional) Custom Base URL:** If you need to use a custom base URL for the Anthropic API, check "Use custom base URL" and enter the URL. Most users won't need to adjust this setting.
32+
## Extended Thinking
3833

39-
### Extended Thinking
34+
Enable enhanced reasoning for complex tasks by checking "Enable Extended Thinking" in CodinIT settings. Available for Claude Opus 4, Sonnet 4.5, and Sonnet 3.7.
4035

41-
Anthropic models offer an "Extended Thinking" feature, designed to give them enhanced reasoning capabilities for complex tasks. This feature allows the model to output its step-by-step thought process before delivering a final answer, providing transparency and enabling more thorough analysis for challenging prompts.
36+
Learn more in the [Extended Thinking documentation](https://docs.anthropic.com/en/build-with-claude/extended-thinking).
4237

43-
When extended thinking is in CodinIT, the model generates `thinking` content blocks that detail its internal reasoning. These insights are then incorporated into its final response.
44-
CodinIT users can leverage this by checking the `Enable Extended Thinking` box below the model selection menu after selecting a Claude Model from any provider.
38+
## Notes
4539

46-
**Key Aspects of Extended Thinking:**
47-
48-
- **Supported Models:** This feature is available for select models, including Claude Opus 4, Claude Sonnet 4.5, and Claude Sonnet 3.7.
49-
- **Summarized Thinking (Claude 4):** For Claude 4 and 4.5 models, the API returns a summary of the full thinking process to balance insight with efficiency and prevent misuse. You are billed for the full thinking tokens, not just the summary.
50-
- **Streaming:** Extended thinking responses, including the `thinking` blocks, can be streamed.
51-
- **Tool Use & Prompt Caching:** Extended thinking interacts with tool use (requiring thinking blocks to be passed back) and prompt caching (with specific behaviors around cache invalidation and context).
52-
53-
For comprehensive details on how extended thinking works, including API examples, interaction with tool use, prompt caching, and pricing, please refer to the [official Anthropic documentation on Extended Thinking](https://docs.anthropic.com/en/build-with-claude/extended-thinking).
54-
55-
### Tips and Notes
56-
57-
- **Prompt Caching:** Claude 3 models support [prompt caching](https://docs.anthropic.com/en/build-with-claude/prompt-caching), which can significantly reduce costs and latency for repeated prompts.
58-
- **Context Window:** Claude models have large context windows (200,000 tokens), allowing you to include a significant amount of code and context in your prompts.
59-
- **Pricing:** Refer to the [Anthropic Pricing](https://www.anthropic.com/pricing) page for the latest pricing information.
60-
- **Rate Limits:** Anthropic has strict rate limits based on [usage tiers](https://docs.anthropic.com/en/api/rate-limits#requirements-to-advance-tier). If you're repeatedly hitting rate limits, consider contacting Anthropic sales or accessing Claude through a different provider like [OpenRouter](/providers/openrouter) or [Requesty](/providers/openrouter).
40+
- **Context Window:** 200,000 tokens
41+
- **Prompt Caching:** Reduces costs for repeated prompts
42+
- **Rate Limits:** Based on [usage tiers](https://docs.anthropic.com/en/api/rate-limits). Consider [OpenRouter](/providers/openrouter) if hitting limits
43+
- **Pricing:** See [Anthropic Pricing](https://www.anthropic.com/pricing)

0 commit comments

Comments
 (0)