SiliconFlow

SiliconFlow

SG
50 models available

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 SiliconFlow

ModelContextInput /MOutput /MCache read /MLatencyThroughput
128k$0.53/M$2.29/MN/A1.5s19 tps
128k$0.26/M$1.05/MN/A1.9s19 tps
128k$0.28/M$1.05/MN/A1.6s18 tps
128k$0.28/M$1.05/MN/A1.9s15 tps
128k$0.28/M$1.05/MN/A1.9s15 tps
163k$0.27/M$0.44/M$0.14/M2.1s14 tps
163k$0.27/M$0.44/M$0.14/M2.1s14 tps
1.0M$0.15/M$0.29/M$0.03/M1.5s35 tps
1.0M$0.15/M$0.29/M$0.03/M1.5s35 tps
1.0M$0.23/M$0.69/M$0.03/M1.7s52 tps
1.0M$0.23/M$0.69/M$0.03/M1.7s52 tps
1.0M$0.46/M$1.39/M$0.03/M1.3s68 tps
1.0M$1.83/M$3.65/M$0.15/M2.3s36 tps
1.0M$1.83/M$3.65/M$0.15/M2.3s36 tps
1.0M$1.39/M$4.16/M$0.05/M1.4s54 tps
1.0M$1.39/M$4.16/M$0.05/M1.4s54 tps
1.0M$0.31/M$1.26/M$0.0063/M2s100 tps
1.0M$0.31/M$1.26/M$0.0063/M2s100 tps
262k$0.15/M$0.42/M$0.05/M1.6s28 tps
262k$0.15/M$0.42/M$0.05/M1.6s28 tps
262k$0.79/M$1.05/M$0.26/M1.9s32 tps
262k$0.79/M$1.05/M$0.26/M1.9s32 tps
128k$0.15/M$0.90/MN/A4.9s16 tps
128k$0.15/M$0.90/MN/A4.9s16 tps
200k$1.00/M$2.68/M$0.21/M2.4s47 tps
200k$1.00/M$2.68/M$0.21/M2.4s47 tps
200k$1.25/M$3.93/M$0.63/M2.1s25 tps
200k$1.25/M$3.93/M$0.63/M2.1s25 tps
1.0M$1.25/M$3.93/M$0.23/M2.1s53 tps
1.0M$1.25/M$3.93/M$0.23/M2.1s53 tps
1.0M$1.18/M$3.70/M$0.22/M1.8s46 tps
1.0M$1.18/M$3.70/M$0.22/M1.8s46 tps
1.0M$0.16/M$0.53/M$0.03/M5s16 tps
128k$0.16/M$0.63/M$0.08/M1.6s18 tps
128k$0.04/M$0.19/MN/A1.2s17 tps
256k$0.47/M$2.36/M$0.07/M1.9s23 tps
256k$0.47/M$2.36/M$0.07/M1.9s23 tps
262k$0.90/M$3.99/M$0.19/M2.9s20 tps
1.0M$0.79/M$3.10/M$0.02/MN/AN/A
1.0M$0.79/M$3.10/M$0.02/MN/AN/A
512k$0.63/M$2.52/M$0.13/MN/AN/A
512k$0.63/M$2.52/M$0.13/MN/AN/A
260k$0.31/M$3.36/MN/A2.1s24.5 tps
260k$0.31/M$3.36/MN/A2.1s24.5 tps
262k$0.25/M$1.89/M$0.16/M1.7s59 tps
262k$0.25/M$1.89/M$0.16/M1.7s59 tps
41k$0.15/M$0.60/MN/A1.2s24 tps
1.0M$2.10/M$6.30/M$0.26/M1.8s33 tps
1.0M$2.10/M$6.30/M$0.26/M1.8s33 tps
262k$0.07/M$0.26/M$0.03/MN/AN/A

Prices are per million tokens. 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 SiliconFlow via the API

For models with provider selection, append :siliconflow to the model ID, set "provider": "siliconflow" in the request body, or send an X-Provider: siliconflow 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.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-R1-0528:siliconflow",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.