StreamLake

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 StreamLake

Model name

34 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek R1-0528 deepseek-ai/DeepSeek-R1-0528:streamlake	128k	$0.60/M	$2.40/M	N/A	0%	3.1s	46 tps
DeepSeek V3.1 Terminus deepseek-ai/DeepSeek-V3.1-Terminus:streamlake	128k	$0.36/M	$1.08/M	N/A	27.9%	1s	66 tps
DeepSeek V3.1 Terminus (Thinking) deepseek-ai/DeepSeek-V3.1-Terminus:thinking:streamlake	128k	$0.36/M	$1.08/M	N/A	0%	1s	66 tps
DeepSeek V4 Flash FP8 deepseek/deepseek-v4-flash:streamlake	1.0M	$0.07/M	$0.15/M	$0.01/M	23.2%	1.1s	79 tps
DeepSeek V4 Flash (Thinking) FP8 deepseek/deepseek-v4-flash:thinking:streamlake	1.0M	$0.07/M	$0.15/M	$0.01/M	85.1%	1.1s	79 tps
DeepSeek V4 Flash 0731 FP8 deepseek/deepseek-v4-flash-0731:streamlake	1.0M	$0.05/M	$0.14/M	$0.0015/M	78.5%	1.3s	45 tps
DeepSeek V4 Flash 0731 (Thinking) FP8 deepseek/deepseek-v4-flash-0731:thinking:streamlake	1.0M	$0.05/M	$0.14/M	$0.0015/M	78.5%	1.3s	45 tps
DeepSeek V4 Pro FP8 deepseek/deepseek-v4-pro:streamlake	1.0M	$1.83/M	$3.65/M	$0.15/M	90.1%	2.2s	35 tps
DeepSeek V4 Pro (Thinking) FP8 deepseek/deepseek-v4-pro:thinking:streamlake	1.0M	$1.83/M	$3.65/M	$0.15/M	78.6%	2.2s	35 tps
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813:streamlake	1.0M	$0.69/M	$2.08/M	$0.02/M	N/A	2.2s	47 tps
DeepSeek V4 Pro 0813 (Thinking) deepseek/deepseek-v4-pro-0813:thinking:streamlake	1.0M	$0.69/M	$2.08/M	$0.02/M	N/A	2.2s	47 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:streamlake	1.0M	$0.16/M	$0.63/M	$0.0032/M	58.3%	1.5s	75 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:streamlake	1.0M	$0.16/M	$0.63/M	$0.0032/M	69%	1.5s	75 tps
GLM 5 FP8 z-ai/glm-5:streamlake	198k	$0.63/M	$2.02/M	$0.13/M	66.9%	3s	39 tps
GLM 5 (Thinking) FP8 z-ai/glm-5:thinking:streamlake	198k	$0.63/M	$2.02/M	$0.13/M	37%	3s	39 tps
GLM 5.1 FP8 z-ai/glm-5.1:streamlake	200k	$1.01/M	$3.19/M	$0.19/M	47.1%	1.3s	48 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:streamlake	200k	$1.01/M	$3.19/M	$0.19/M	0%	1.3s	48 tps
GLM 5.2 FP8 z-ai/glm-5.2:streamlake	1.0M	$0.59/M	$1.85/M	$0.11/M	83.3%	1.1s	54 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:streamlake	1.0M	$0.59/M	$1.85/M	$0.11/M	79.3%	1.1s	54 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:streamlake	1.0M	$0.09/M	$0.30/M	$0.02/M	0%	3.9s	34 tps
Kimi K2.6 FP8 moonshotai/kimi-k2.6:streamlake	256k	$0.63/M	$2.65/M	$0.11/M	18.3%	13.1s	66 tps
Kimi K2.6 Thinking FP8 moonshotai/kimi-k2.6:thinking:streamlake	256k	$0.63/M	$2.65/M	$0.11/M	68.6%	13.1s	66 tps
Kimi K2.7 Code moonshotai/kimi-k2.7-code:streamlake	256k	$0.75/M	$3.15/M	$0.15/M	N/A	1s	83 tps
MiMo V2.5 xiaomi/mimo-v2.5:streamlake	1M	$0.18/M	$0.35/M	$0.0035/M	N/A	2.4s	32.5 tps
MiMo V2.5 Pro xiaomi/mimo-v2.5-pro:streamlake	1M	$0.55/M	$1.10/M	$0.0045/M	N/A	1.2s	33.5 tps
MiMo V2.5 Pro Thinking xiaomi/mimo-v2.5-pro:thinking:streamlake	1M	$0.55/M	$1.10/M	$0.0045/M	N/A	1.2s	33.5 tps
MiMo V2.5 Thinking xiaomi/mimo-v2.5:thinking:streamlake	1M	$0.18/M	$0.35/M	$0.0035/M	N/A	2.4s	32.5 tps
MiniMax M2.5 minimax/minimax-m2.5:streamlake	200k	$0.28/M	$1.13/M	$0.03/M	N/A	1.1s	70 tps
MiniMax M3 FP8 minimax/minimax-m3:streamlake	1M	$0.31/M	$1.26/M	$0.06/M	N/A	2.6s	97 tps
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:streamlake	1M	$0.31/M	$1.26/M	$0.06/M	N/A	2.6s	97 tps
Qwen3 235B A22B qwen/qwen3-235b-a22b:streamlake	128k	$0.22/M	$0.88/M	N/A	<0.1%	0.7s	53 tps
Qwen3 Coder Next qwen/qwen3-coder-next:streamlake	256k	$0.19/M	$0.94/M	$0.04/M	N/A	1.2s	60 tps
Qwen3.5 397B qwen/qwen3.5-397b-a17b:streamlake	256k	$0.63/M	$3.78/M	$0.13/M	N/A	0.5s	157 tps
Qwen3.5 397B Thinking qwen/qwen3.5-397b-a17b-thinking:streamlake	256k	$0.63/M	$3.78/M	$0.13/M	N/A	0.5s	157 tps

DeepSeek R1-0528

deepseek-ai/DeepSeek-R1-0528:streamlake

Context

128k

Input /M

$0.60/M

Output /M

$2.40/M

Cache read /M

N/A

Cache hit

0%

TTFT

3.1s

Throughput

46 tps

DeepSeek V3.1 Terminus

deepseek-ai/DeepSeek-V3.1-Terminus:streamlake

Context

128k

Input /M

$0.36/M

Output /M

$1.08/M

Cache read /M

N/A

Cache hit

27.9%

TTFT

1s

Throughput

66 tps

DeepSeek V3.1 Terminus (Thinking)

deepseek-ai/DeepSeek-V3.1-Terminus:thinking:streamlake

Context

128k

Input /M

$0.36/M

Output /M

$1.08/M

Cache read /M

N/A

Cache hit

0%

TTFT

1s

Throughput

66 tps

DeepSeek V4 Flash

FP8

deepseek/deepseek-v4-flash:streamlake

Context

1.0M

Input /M

$0.07/M

Output /M

$0.15/M

Cache read /M

$0.01/M

Cache hit

23.2%

TTFT

1.1s

Throughput

79 tps

DeepSeek V4 Flash (Thinking)

FP8

deepseek/deepseek-v4-flash:thinking:streamlake

Context

1.0M

Input /M

$0.07/M

Output /M

$0.15/M

Cache read /M

$0.01/M

Cache hit

85.1%

TTFT

1.1s

Throughput

79 tps

DeepSeek V4 Flash 0731

FP8

deepseek/deepseek-v4-flash-0731:streamlake

Context

1.0M

Input /M

$0.05/M

Output /M

$0.14/M

Cache read /M

$0.0015/M

Cache hit

78.5%

TTFT

1.3s

Throughput

45 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

deepseek/deepseek-v4-flash-0731:thinking:streamlake

Context

1.0M

Input /M

$0.05/M

Output /M

$0.14/M

Cache read /M

$0.0015/M

Cache hit

78.5%

TTFT

1.3s

Throughput

45 tps

DeepSeek V4 Pro

FP8

deepseek/deepseek-v4-pro:streamlake

Context

1.0M

Input /M

$1.83/M

Output /M

$3.65/M

Cache read /M

$0.15/M

Cache hit

90.1%

TTFT

2.2s

Throughput

35 tps

DeepSeek V4 Pro (Thinking)

FP8

deepseek/deepseek-v4-pro:thinking:streamlake

Context

1.0M

Input /M

$1.83/M

Output /M

$3.65/M

Cache read /M

$0.15/M

Cache hit

78.6%

TTFT

2.2s

Throughput

35 tps

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813:streamlake

Context

1.0M

Input /M

$0.69/M

Output /M

$2.08/M

Cache read /M

$0.02/M

Cache hit

N/A

TTFT

2.2s

Throughput

47 tps

DeepSeek V4 Pro 0813 (Thinking)

deepseek/deepseek-v4-pro-0813:thinking:streamlake

Context

1.0M

Input /M

$0.69/M

Output /M

$2.08/M

Cache read /M

$0.02/M

Cache hit

N/A

TTFT

2.2s

Throughput

47 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:streamlake

Context

1.0M

Input /M

$0.16/M

Output /M

$0.63/M

Cache read /M

$0.0032/M

Cache hit

58.3%

TTFT

1.5s

Throughput

75 tps

DeepSeek V4.1 Flash (Thinking)

FP8

deepseek/deepseek-v4.1-flash:thinking:streamlake

Context

1.0M

Input /M

$0.16/M

Output /M

$0.63/M

Cache read /M

$0.0032/M

Cache hit

69%

TTFT

1.5s

Throughput

75 tps

GLM 5

FP8

z-ai/glm-5:streamlake

Context

198k

Input /M

$0.63/M

Output /M

$2.02/M

Cache read /M

$0.13/M

Cache hit

66.9%

TTFT

3s

Throughput

39 tps

GLM 5 (Thinking)

FP8

z-ai/glm-5:thinking:streamlake

Context

198k

Input /M

$0.63/M

Output /M

$2.02/M

Cache read /M

$0.13/M

Cache hit

37%

TTFT

3s

Throughput

39 tps

GLM 5.1

FP8

z-ai/glm-5.1:streamlake

Context

200k

Input /M

$1.01/M

Output /M

$3.19/M

Cache read /M

$0.19/M

Cache hit

47.1%

TTFT

1.3s

Throughput

48 tps

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:streamlake

Context

200k

Input /M

$1.01/M

Output /M

$3.19/M

Cache read /M

$0.19/M

Cache hit

0%

TTFT

1.3s

Throughput

48 tps

GLM 5.2

FP8

z-ai/glm-5.2:streamlake

Context

1.0M

Input /M

$0.59/M

Output /M

$1.85/M

Cache read /M

$0.11/M

Cache hit

83.3%

TTFT

1.1s

Throughput

54 tps

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:streamlake

Context

1.0M

Input /M

$0.59/M

Output /M

$1.85/M

Cache read /M

$0.11/M

Cache hit

79.3%

TTFT

1.1s

Throughput

54 tps

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:streamlake

Context

1.0M

Input /M

$0.09/M

Output /M

$0.30/M

Cache read /M

$0.02/M

Cache hit

0%

TTFT

3.9s

Throughput

34 tps

Kimi K2.6

FP8

moonshotai/kimi-k2.6:streamlake

Context

256k

Input /M

$0.63/M

Output /M

$2.65/M

Cache read /M

$0.11/M

Cache hit

18.3%

TTFT

13.1s

Throughput

66 tps

Kimi K2.6 Thinking

FP8

moonshotai/kimi-k2.6:thinking:streamlake

Context

256k

Input /M

$0.63/M

Output /M

$2.65/M

Cache read /M

$0.11/M

Cache hit

68.6%

TTFT

13.1s

Throughput

66 tps

Kimi K2.7 Code

moonshotai/kimi-k2.7-code:streamlake

Context

256k

Input /M

$0.75/M

Output /M

$3.15/M

Cache read /M

$0.15/M

Cache hit

N/A

TTFT

1s

Throughput

83 tps

MiMo V2.5

xiaomi/mimo-v2.5:streamlake

Context

1M

Input /M

$0.18/M

Output /M

$0.35/M

Cache read /M

$0.0035/M

Cache hit

N/A

TTFT

2.4s

Throughput

32.5 tps

MiMo V2.5 Pro

xiaomi/mimo-v2.5-pro:streamlake

Context

1M

Input /M

$0.55/M

Output /M

$1.10/M

Cache read /M

$0.0045/M

Cache hit

N/A

TTFT

1.2s

Throughput

33.5 tps

MiMo V2.5 Pro Thinking

xiaomi/mimo-v2.5-pro:thinking:streamlake

Context

1M

Input /M

$0.55/M

Output /M

$1.10/M

Cache read /M

$0.0045/M

Cache hit

N/A

TTFT

1.2s

Throughput

33.5 tps

MiMo V2.5 Thinking

xiaomi/mimo-v2.5:thinking:streamlake

Context

1M

Input /M

$0.18/M

Output /M

$0.35/M

Cache read /M

$0.0035/M

Cache hit

N/A

TTFT

2.4s

Throughput

32.5 tps

MiniMax M2.5

minimax/minimax-m2.5:streamlake

Context

200k

Input /M

$0.28/M

Output /M

$1.13/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

1.1s

Throughput

70 tps

MiniMax M3

FP8

minimax/minimax-m3:streamlake

Context

1M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

Cache hit

N/A

TTFT

2.6s

Throughput

97 tps

MiniMax M3 Thinking

FP8

minimax/minimax-m3:thinking:streamlake

Context

1M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

Cache hit

N/A

TTFT

2.6s

Throughput

97 tps

Qwen3 235B A22B

qwen/qwen3-235b-a22b:streamlake

Context

128k

Input /M

$0.22/M

Output /M

$0.88/M

Cache read /M

N/A

Cache hit

<0.1%

TTFT

0.7s

Throughput

53 tps

Qwen3 Coder Next

qwen/qwen3-coder-next:streamlake

Context

256k

Input /M

$0.19/M

Output /M

$0.94/M

Cache read /M

$0.04/M

Cache hit

N/A

TTFT

1.2s

Throughput

60 tps

Qwen3.5 397B

qwen/qwen3.5-397b-a17b:streamlake

Context

256k

Input /M

$0.63/M

Output /M

$3.78/M

Cache read /M

$0.13/M

Cache hit

N/A

TTFT

0.5s

Throughput

157 tps

Qwen3.5 397B Thinking

qwen/qwen3.5-397b-a17b-thinking:streamlake

Context

256k

Input /M

$0.63/M

Output /M

$3.78/M

Cache read /M

$0.13/M

Cache hit

N/A

TTFT

0.5s

Throughput

157 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 StreamLake via the API

Call a model served by StreamLake using its displayed model ID, including the provider suffix when selection is supported.

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"}]
  }'

For models with provider selection, 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 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.