Save up to 60% on AI models

Quick start

1. Create an API key from API Keys. Copy it before leaving the page.
2. Set your client base URL to https://api.cheaperinference.com/v1.
3. Pick a supported model id from the list below.
4. Send a chat or image request and check History for usage and savings.

Example: cURL chat completion

curl https://api.cheaperinference.com/v1/chat/completions \
  -H "Authorization: Bearer ir_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example: cURL image generation

curl https://api.cheaperinference.com/v1/images/generations \
  -H "Authorization: Bearer ir_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nano-banana-pro",
    "prompt": "A clean product render of a banana invoice",
    "n": 1,
    "size": "1024x1024",
    "resolution": "1K",
    "quality": "high",
    "response_format": "url"
  }'

Use /v1/images/generations for every model whose /v1/models entry has type: "image" or capabilities.image_generation: true, including grok-imagine. Image-generation models are not accepted by /v1/responses, /v1/chat/completions, or /v1/completions.

Example: Grok Imagine

curl https://api.cheaperinference.com/v1/images/generations \
  -H "Authorization: Bearer ir_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine",
    "prompt": "A cinematic city at night",
    "n": 1,
    "response_format": "url"
  }'

Nano Banana image output uses fixed output-token amounts for the selected resolution. Nano Banana 2 uses 747 tokens at 0.5K, 1,120 at 1K, 1,680 at 2K, and 2,520 at 4K. Nano Banana Pro uses 1,120 tokens at 1K or 2K and 2,000 at 4K.

Kimi K3 reasoning effort

Send reasoning: {"effort": "low"}, "high", or "max" with model: "kimi-k3". Kimi K3 does not expose medium as a native effort level. Set the value explicitly when consistent behavior matters; reasoning tokens are billed as output usage.

Temporary vision uploads

For larger base64 payloads, upload each image separately as multipart form data. The returned file ID expires after one hour and is converted to a short-lived, private image URL when the chat request is forwarded. Uploads keep the JSON body small but do not change the limit of 10 images per request.

curl https://api.cheaperinference.com/v1/uploads \
  -H "Authorization: Bearer ir_live_YOUR_API_KEY" \
  -F "file=@tile.png"

# Use the returned id in a chat message:
{
  "type": "image_file",
  "image_file": {"file_id": "img_RETURNED_ID"}
}

# Optional early deletion:
curl -X DELETE https://api.cheaperinference.com/v1/uploads/img_RETURNED_ID \
  -H "Authorization: Bearer ir_live_YOUR_API_KEY"

Model catalog API

Retrieve currently available models and their current catalog rates. A fallback route can change the final rate, but never above the applicable direct list price. Filter by type, vision, reasoning, streaming, or provider to compare only models that meet your workload's requirements.

curl 'https://api.cheaperinference.com/v1/models?type=text&vision=true&streaming=true' \
  -H 'Authorization: Bearer ir_live_YOUR_API_KEY'

Token rates are USD per 1 million tokens. Fixed media rates use media_input_unit_price and media_unit_price per unit. For tiered models, use pricing.above_threshold when the request exceeds input_token_price_threshold.

Automatic retries and fallback

Network failures and HTTP 404, 408, 409, 425, 429, and 5xx responses are retried once. Other 4xx responses are not retried; when another route is eligible, the gateway immediately tries it in price order. The serving route determines the settled rate, capped at direct list price with no separate Cheaper Inference routing surcharge. Prompts and model responses are not stored; billing and operational metadata is retained for History and support.