Documentation
Integrations
Create one freeapis key, then connect it to Codex or Claude Code. These are the first supported tools; more clients are in development.
Models & Limits
Our API key currently supports deepseek-v4-flash, mimo-v2.5, and GPT-5.5 / GPT-5.4 model variants. Free quota can be increased through Reward tasks such as watching ads, while GPT models use permanent quota.
Usage limits: free quota provides 2,000,000 tokens per 5 hours and 10,000,000 tokens per week. All usage uses model-specific input/output multipliers with GPT-5.4 as the 1x baseline.
curl https://api.freeapis.dev/v1/example \
-H "Authorization: Bearer fapi_your_key"CODEX
Codex integration
Codex reads provider settings from ~/.codex/config.toml. Add freeapis as a custom provider and point Codex at one of the supported free models.
export FREEAPIS_API_KEY="fapi_your_key"
# ~/.codex/config.toml
model = "deepseek-v4-flash"
model_provider = "freeapis"
[model_providers.freeapis]
name = "freeapis"
base_url = "https://api.freeapis.dev/v1"
wire_api = "responses"
env_key = "FREEAPIS_API_KEY"You can switch model to other supported values such as mimo-v2.5, gpt-5.5-medium, or gpt-5.4-mini-high.
CLAUDE CODE
Claude Code integration
Claude Code can route requests through an LLM gateway by setting ANTHROPIC_BASE_URL. Use your freeapis key as a bearer token with ANTHROPIC_AUTH_TOKEN.
export ANTHROPIC_BASE_URL="https://api.freeapis.dev/anthropic"
export ANTHROPIC_AUTH_TOKEN="fapi_your_key"
export ANTHROPIC_CUSTOM_MODEL_OPTION="deepseek-v4-flash"
export ANTHROPIC_CUSTOM_MODEL_OPTION_NAME="deepseek-v4-flash via freeapis"
claudeTo use other models, set ANTHROPIC_CUSTOM_MODEL_OPTION to your preferred model identifier (e.g. mimo-v2.5, gpt-5.5-medium, or gpt-5.4-mini-high).