- Context
- 524k
- Input /M
- $0.33/M
- Output /M
- $1.32/M
- Cache read /M
- $0.00825/M
- Cache hit
- N/A
- TTFT
- N/A
- Throughput
- N/A
OrcaRouter
SG/US/JP
10 models available
OrcaRouter serves its OrcaCyber models on its own compute. Its policy states that prompts and outputs are processed in transit, are not stored unless request logging is enabled for the workspace, and are not used for training. Request metadata, including source IP, is retained for 13 months. It operates from Singapore on infrastructure in Singapore, the United States and Japan. No zero-retention agreement is signed for this account.
Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.
Models served by OrcaRouter
10 models
- Context
- 524k
- Input /M
- $0.33/M
- Output /M
- $1.32/M
- Cache read /M
- $0.00825/M
- Cache hit
- N/A
- TTFT
- N/A
- Throughput
- N/A
- Context
- 1.0M
- Input /M
- $0.84/M
- Output /M
- $1.68/M
- Cache read /M
- $0.157/M
- Cache hit
- 75.9%
- TTFT
- 35.1s
- Throughput
- 137.1 tps
- Context
- 1.0M
- Input /M
- $0.84/M
- Output /M
- $1.68/M
- Cache read /M
- $0.157/M
- Cache hit
- 94.2%
- TTFT
- 16.7s
- Throughput
- 74.7 tps
- Context
- 1.0M
- Input /M
- $0.84/M
- Output /M
- $1.68/M
- Cache read /M
- $0.157/M
- Cache hit
- 98.3%
- TTFT
- 28.9s
- Throughput
- 156.6 tps
- Context
- 1.0M
- Input /M
- $0.84/M
- Output /M
- $1.68/M
- Cache read /M
- $0.157/M
- Cache hit
- 0.4%
- TTFT
- 11.4s
- Throughput
- 89.9 tps
- Context
- 1.0M
- Input /M
- $0.84/M
- Output /M
- $1.68/M
- Cache read /M
- $0.157/M
- Cache hit
- 44.6%
- TTFT
- 6.9s
- Throughput
- 50.3 tps
- Context
- 1.0M
- Input /M
- $0.84/M
- Output /M
- $1.68/M
- Cache read /M
- $0.157/M
- Cache hit
- 90%
- TTFT
- 3.1s
- Throughput
- 110.2 tps
- Context
- 1.0M
- Input /M
- $0.84/M
- Output /M
- $1.68/M
- Cache read /M
- $0.157/M
- Cache hit
- 0.6%
- TTFT
- 8.1s
- Throughput
- 165.8 tps
- Context
- 999k
- Input /M
- $3.15/M
- Output /M
- $7.88/M
- Cache read /M
- $0.787/M
- Cache hit
- N/A
- TTFT
- 0.6s
- Throughput
- 269.6 tps
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 OrcaRouter via the API
Call a model served by OrcaRouter using its displayed model ID, including the provider suffix when selection is supported.
cURL
curl https://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-0910-uncensored",
"messages": [{"role": "user", "content": "Hello"}]
}'For models with provider selection, append :orcarouter to the model ID, set "provider": "orcarouter" in the request body, or send an X-Provider: orcarouter 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.