- Context
- 1.0M
- Input /M
- $0.66/M
- Output /M
- $2.50/M
- Cache read /M
- $0.04/M
- TTFT
- N/A
- Throughput
- N/A
Pearl Research
Written zero-retention and resale confirmation from Sacha, 2026-11-22 09:13Z, Zoho message 1795338834192014200. Prompts and outputs are not stored or used for training.
Privacy can differ by model. See each model’s label.
Models served by Pearl Research
11 models
- Context
- 1.0M
- Input /M
- $0.66/M
- Output /M
- $2.50/M
- Cache read /M
- $0.04/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 1.0M
- Input /M
- $0.0387/M
- Output /M
- $0.40/M
- Cache read /M
- $0.0089/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 1.0M
- Input /M
- $0.0387/M
- Output /M
- $0.40/M
- Cache read /M
- $0.0089/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 1.0M
- Input /M
- $0.10/M
- Output /M
- $0.60/M
- Cache read /M
- $0.0042/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 1.0M
- Input /M
- $0.10/M
- Output /M
- $0.60/M
- Cache read /M
- $0.0042/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 1M
- Input /M
- $0.60/M
- Output /M
- $1.10/M
- Cache read /M
- $0.20/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 1M
- Input /M
- $0.60/M
- Output /M
- $1.10/M
- Cache read /M
- $0.20/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 1.0M
- Input /M
- $0.10/M
- Output /M
- $0.30/M
- Cache read /M
- $0.025/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 262k
- Input /M
- $0.15/M
- Output /M
- $0.70/M
- Cache read /M
- $0.04/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 262k
- Input /M
- $0.15/M
- Output /M
- $0.70/M
- Cache read /M
- $0.04/M
- TTFT
- N/A
- Throughput
- N/A
Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.
Using Pearl Research via the API
Call a model served by Pearl Research using its displayed model ID, including the provider suffix when selection is supported.
cURL
curl https://api.nano-gpt.com/api/v1/chat/completions \
-H "Authorization: Bearer $NANOGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-pro-0813:pearl",
"messages": [{"role": "user", "content": "Hello"}]
}'For models with provider selection, append :pearl to the model ID, set "provider": "pearl" in the request body, or send an X-Provider: pearl header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.
See the API documentation for provider preferences, price-aware routing, and error behavior.