- Context
- 1.0M
- Input /M
- $0.0672/M
- Output /M
- $0.252/M
- Cache read /M
- $0.0013/M
- TTFT
- N/A
- Throughput
- N/A
50X
50X Holding LLC signed a statement for NanoGPT (2026-11-15) that prompts and outputs on its DeepSeek V4.1 Flash 1017 route are not kept in persistent storage after a request finishes, including by its GPU host and other subprocessors, and are not used to train, fine-tune or evaluate models. Prompt-derived prefix cache state may stay in volatile memory to speed up later requests. Operational records without content (request IDs, token counts, latency, status codes) are kept. See its zero data retention policy at https://50x.energy/zero-data-retention.
Privacy can differ by model. See each model’s label.
Broader provider policy: 50X’s signed zero-retention statement covers its DeepSeek V4.1 Flash 1017 route. Any other route stays unverified until reviewed.. The labels beside individual models apply only to those routes.
Models served by 50X
- Context
- 1.0M
- Input /M
- $0.0672/M
- Output /M
- $0.252/M
- Cache read /M
- $0.0013/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 50X via the API
Call a model served by 50X 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-v4.1-flash-1017:fiftyx",
"messages": [{"role": "user", "content": "Hello"}]
}'For models with provider selection, append :fiftyx to the model ID, set "provider": "fiftyx" in the request body, or send an X-Provider: fiftyx 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.