Skip to main content

Faheem Code

Obtain your Faheem Code LLM API key

  1. Log in to Faheem Code Cloud.
  2. Go to the Settings page and navigate to the API Keys tab.
  3. Copy your LLM API Key.

Screenshot: Faheem Code LLM API Key.

Configuration

When running Faheem Code, you'll need to set the following in the Faheem Code UI through the Settings under the LLM tab:

  • LLM Provider to Faheem Code
  • LLM Model to the model you will be using (e.g. claude-sonnet-4-20250514 or claude-sonnet-4-5-20250929)
  • API Key to your Faheem Code LLM API key copied from above

Using Faheem Code LLM provider in the CLI

  1. Run Faheem Code CLI.
  2. To select Faheem Code as the LLM provider:
  • If this is your first time running the CLI, choose faheemcode and then select the model that you would like to use.
  • If you have previously run the CLI, run the /settings command and select to modify the Basic settings. Then choose faheemcode and finally the model.

Screenshot: Faheem Code Provider in CLI.

Using Faheem Code LLM provider with the SDK

You can use your Faheem Code LLM API key with the Faheem Code SDK to build custom agents and automation pipelines.

Configuration

The SDK automatically configures the correct API endpoint when you use the faheemcode/ model prefix. Simply set two environment variables:

export LLM_API_KEY="example-user-api-key"
export LLM_MODEL="faheemcode/claude-sonnet-4-20250514"

Example

from faheemcode.sdk import LLM

# The faheemcode/ prefix auto-configures the base URL
llm = LLM.load_from_env()

# Or configure directly
llm = LLM(
model="faheemcode/claude-sonnet-4-20250514",
api_key="example-user-api-key",
)

The faheemcode/ prefix tells the SDK to automatically route requests to the Faheem Code LLM proxy—no need to manually set a base URL.

Available models

When using the SDK, prefix any model from the pricing table below with faheemcode/:

  • faheemcode/claude-sonnet-4-20250514
  • faheemcode/claude-sonnet-4-5-20250929
  • faheemcode/claude-opus-4-20250514
  • faheemcode/gpt-5-2025-08-07
  • etc.

Pricing

Pricing follows official API provider rates. Below are the current pricing details for Faheem Code models:

ModelInput Cost (per 1M tokens)Cached Input Cost (per 1M tokens)Output Cost (per 1M tokens)Max Input TokensMax Output Tokens
claude-sonnet-4-5-20250929$3.00$0.30$15.00200,00064,000
claude-sonnet-4-20250514$3.00$0.30$15.001,000,00064,000
claude-opus-4-20250514$15.00$1.50$75.00200,00032,000
claude-opus-4-1-20250805$15.00$1.50$75.00200,00032,000
claude-haiku-4-5-20251001$1.00$0.10$5.00200,00064,000
gpt-5-codex$1.25$0.125$10.00272,000128,000
gpt-5-2025-08-07$1.25$0.125$10.00272,000128,000
gpt-5-mini-2025-08-07$0.25$0.025$2.00272,000128,000
devstral-medium-2507$0.40N/A$2.00128,000128,000
devstral-small-2507$0.10N/A$0.30128,000128,000
o3$2.00$0.50$8.00200,000100,000
o4-mini$1.10$0.275$4.40200,000100,000
gemini-3-pro-preview$2.00$0.20$12.001,048,57665,535
kimi-k2-0711-preview$0.60$0.15$2.50131,072131,072
qwen3-coder-480b$0.40N/A$1.60N/AN/A

Note: Prices listed reflect provider rates with no markup, sourced via LiteLLM’s model price database and provider pricing pages. Cached input tokens are charged at a reduced rate when the same content is reused across requests. Models that don't support prompt caching show "N/A" for cached input cost.