- Context
- 1.0M
- Input /M
- $1.39/M
- Output /M
- $4.16/M
- Cache read /M
- $0.0462/M
- TTFT
- N/A
- Throughput
- N/A
Inworld
Theai, Inc. dba Inworld AI confirmed in writing (12 November 2026) that zero data retention is on for NanoGPT's workspace: prompts and outputs are processed in memory and redacted from logs, never used for training, and served from Inworld's own US deployment with no third-party fallback. NanoGPT routes text to Inworld only for models Inworld hosts itself. Voice cloning keeps the uploaded source audio.
Privacy can differ by model. See each model’s label.
Broader provider policy: Unverified. The labels beside individual models apply only to those routes.
Models served by Inworld
- Context
- 1.0M
- Input /M
- $1.39/M
- Output /M
- $4.16/M
- Cache read /M
- $0.0462/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 524k
- Input /M
- $0.147/M
- Output /M
- $0.294/M
- Cache read /M
- $0.0032/M
- TTFT
- N/A
- Throughput
- N/A
- Context
- 524k
- Input /M
- $0.452/M
- Output /M
- $0.913/M
- Cache read /M
- $0.0038/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 Inworld via the API
Call a model served by Inworld 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:inworld",
"messages": [{"role": "user", "content": "Hello"}]
}'For models with provider selection, append :inworld to the model ID, set "provider": "inworld" in the request body, or send an X-Provider: inworld 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.