StreamLake

36 models available

Models served by StreamLake

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
DeepSeek R1-0528	128k	$0.60/M	$2.40/M	N/A	3.3s	46 tps
DeepSeek V3.1 Terminus	128k	$0.36/M	$1.08/M	N/A	1.5s	46.5 tps
DeepSeek V3.1 Terminus (Thinking)	128k	$0.36/M	$1.08/M	N/A	1.5s	46.5 tps
DeepSeek V3.2 FP8	163k	$0.23/M	$0.34/M	$0.02/M	1.3s	21 tps
DeepSeek V3.2 (Thinking) FP8	163k	$0.23/M	$0.34/M	$0.02/M	1.3s	21 tps
DeepSeek V4 Flash FP8	1.0M	$0.09/M	$0.17/M	$0.02/M	1.8s	38 tps
DeepSeek V4 Flash (Thinking) FP8	1.0M	$0.09/M	$0.17/M	$0.02/M	1.8s	38 tps
DeepSeek V4 Flash 0731 FP8	1.0M	$0.09/M	$0.28/M	$0.0029/M	0.9s	51 tps
DeepSeek V4 Flash 0731 (Thinking) FP8	1.0M	$0.09/M	$0.28/M	$0.0029/M	0.9s	51 tps
DeepSeek V4 Pro FP8	1.0M	$1.83/M	$3.65/M	$0.02/M	2.8s	28 tps
DeepSeek V4 Pro (Thinking) FP8	1.0M	$1.83/M	$3.65/M	$0.02/M	2.8s	28 tps
DeepSeek V4 Pro 0813	1.0M	$0.61/M	$1.83/M	$0.02/M	2.7s	50 tps
DeepSeek V4 Pro 0813 (Thinking)	1.0M	$0.61/M	$1.83/M	$0.02/M	2.7s	50 tps
GLM 4.7 FP8	200k	$0.50/M	$1.85/M	N/A	1.7s	38 tps
GLM 4.7 (Thinking) FP8	200k	$0.50/M	$1.85/M	N/A	1.7s	38 tps
GLM 5 FP8	200k	$0.63/M	$2.02/M	$0.13/M	2.3s	47 tps
GLM 5 (Thinking) FP8	200k	$0.63/M	$2.02/M	$0.13/M	2.3s	47 tps
GLM 5.1 FP8	200k	$1.01/M	$3.19/M	$0.19/M	1.7s	29 tps
GLM 5.1 (Thinking) FP8	200k	$1.01/M	$3.19/M	$0.19/M	1.7s	29 tps
GLM 5.2 FP8	1.0M	$0.34/M	$1.08/M	$0.06/M	1.5s	64 tps
GLM 5.2 (Thinking) FP8	1.0M	$0.34/M	$1.08/M	$0.06/M	1.5s	64 tps
Kimi K2.5 FP8	256k	$0.57/M	$2.84/M	$0.09/M	1.2s	54 tps
Kimi K2.5 Thinking FP8	256k	$0.57/M	$2.84/M	$0.09/M	1.2s	54 tps
Kimi K2.6 FP8	256k	$0.63/M	$2.65/M	$0.11/M	1.5s	42 tps
Kimi K2.6 Thinking FP8	256k	$0.63/M	$2.65/M	$0.11/M	1.5s	42 tps
MiMo V2.5	1M	$0.18/M	$0.35/M	$0.0035/M	3.2s	26 tps
MiMo V2.5 Pro	1.0M	$0.55/M	$1.10/M	$0.0045/M	2.4s	24 tps
MiMo V2.5 Pro Thinking	1.0M	$0.55/M	$1.10/M	$0.0045/M	2.4s	24 tps
MiMo V2.5 Thinking	1M	$0.18/M	$0.35/M	$0.0035/M	3.2s	26 tps
MiniMax M2.5	205k	$0.28/M	$1.13/M	$0.03/M	0.8s	47 tps
MiniMax M3 FP8	1M	$0.31/M	$1.26/M	$0.06/M	1.4s	83 tps
MiniMax M3 Thinking FP8	1M	$0.31/M	$1.26/M	$0.06/M	1.4s	83 tps
Qwen3 235B A22B	41k	$0.22/M	$0.88/M	N/A	1.3s	20 tps
Qwen3 Coder Next	262k	$0.19/M	$0.94/M	$0.04/M	1.6s	38.5 tps
Qwen3.5 397B	258k	$0.63/M	$3.78/M	$0.13/M	1.4s	82 tps
Qwen3.5 397B Thinking	258k	$0.63/M	$3.78/M	$0.13/M	1.4s	82 tps

Prices are per million tokens and include the 5% provider-selection markup. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using StreamLake via the API

Append :streamlake to the model ID, set "provider": "streamlake" in the request body, or send an X-Provider: streamlake header. Explicit provider selection adds a 5% markup over that provider's base price; the prices in the table above already include it.

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:streamlake",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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

StreamLake terms of use StreamLake privacy policy