Runware

Runware directly confirmed zero data retention for the five original self-hosted text models: GLM 5.3, GLM 5.3 Flash, GLM 5.2, DeepSeek V4 Flash, and GPT OSS 120B. This confirmation does not cover the newer DeepSeek V4.1 Flash, MiniMax M2.7 Turbo, Kimi K2.6, or Kimi K3 routes, whose retention and training policies remain unverified.

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 Runware

Model name

20 models

Model	Context	Input /M	Output /M	Cache read /M	Cache write /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash deepseek/deepseek-v4-flash:runware	1.0M	$0.07/M	$0.14/M	$0.01/M	N/A	N/A	1.8s	68.1 tps
DeepSeek V4 Flash (Thinking) deepseek/deepseek-v4-flash:thinking:runware	1.0M	$0.07/M	$0.14/M	$0.01/M	N/A	N/A	1.8s	68.1 tps
DeepSeek V4 Pro deepseek/deepseek-v4-pro:runware	1.0M	$0.91/M	$1.82/M	$0.07/M	N/A	N/A	N/A	N/A
DeepSeek V4 Pro (Thinking) deepseek/deepseek-v4-pro:thinking:runware	1.0M	$0.91/M	$1.82/M	$0.07/M	N/A	42.7%	7.6s	70.4 tps
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash:runware	1.0M	$0.14/M	$0.57/M	$0.0095/M	N/A	N/A	N/A	N/A
DeepSeek V4.1 Flash (Thinking) deepseek/deepseek-v4.1-flash:thinking:runware	1.0M	$0.14/M	$0.57/M	$0.0095/M	N/A	N/A	N/A	N/A
Gemma 4 31B google/gemma-4-31b-it:runware	262k	$0.10/M	$0.28/M	$0.01/M	N/A	76.1%	2.3s	77.5 tps
Gemma 4 31B (Thinking) google/gemma-4-31b-it:thinking:runware	262k	$0.10/M	$0.28/M	$0.01/M	N/A	9.6%	3.8s	35.3 tps
GLM 5.2 z-ai/glm-5.2:runware	1.0M	$0.76/M	$2.41/M	$0.15/M	N/A	N/A	N/A	N/A
GLM 5.2 (Thinking) z-ai/glm-5.2:thinking:runware	1.0M	$0.76/M	$2.41/M	$0.15/M	N/A	N/A	N/A	N/A
GLM 5.3 z-ai/glm-5.3:runware	1.0M	$1.13/M	$3.78/M	$0.19/M	N/A	N/A	4.1s	238.3 tps
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:runware	1.0M	$1.13/M	$3.78/M	$0.19/M	N/A	99.7%	7.8s	321.6 tps
GLM 5.3 Flash z-ai/glm-5.3-flash:runware	1M	$0.14/M	$0.47/M	$0.03/M	N/A	0%	5.3s	135.5 tps
GPT OSS 120B openai/gpt-oss-120b:runware	128k	$0.03/M	$0.13/M	$0.03/M	N/A	N/A	N/A	N/A
Kimi K2.6 moonshotai/kimi-k2.6:runware	262k	$0.57/M	$2.88/M	$0.12/M	N/A	N/A	N/A	N/A
Kimi K2.6 Thinking moonshotai/kimi-k2.6:thinking:runware	262k	$0.57/M	$2.88/M	$0.12/M	N/A	N/A	N/A	N/A
Kimi K3 moonshotai/kimi-k3:runware	1.0M	$3.15/M	$15.75/M	$0.31/M	N/A	N/A	N/A	N/A
MiniMax M2.7 minimax/minimax-m2.7:runware	205k	$0.28/M	$1.13/M	$0.06/M	$0.35/M	N/A	N/A	N/A
MiniMax M2.7 Turbo minimax/minimax-m2.7-turbo:runware	205k	$0.57/M	$2.27/M	$0.06/M	$0.35/M	N/A	N/A	N/A
MiniMax M3 Thinking minimax/minimax-m3:thinking:runware	1M	$0.28/M	$1.13/M	$0.06/M	N/A	N/A	N/A	N/A

DeepSeek V4 Flash

deepseek/deepseek-v4-flash:runware

Context

1.0M

Input /M

$0.07/M

Output /M

$0.14/M

Cache read /M

$0.01/M

Cache write /M

N/A

Cache hit

N/A

TTFT

1.8s

Throughput

68.1 tps

DeepSeek V4 Flash (Thinking)

deepseek/deepseek-v4-flash:thinking:runware

Context

1.0M

Input /M

$0.07/M

Output /M

$0.14/M

Cache read /M

$0.01/M

Cache write /M

N/A

Cache hit

N/A

TTFT

1.8s

Throughput

68.1 tps

DeepSeek V4 Pro

deepseek/deepseek-v4-pro:runware

Context

1.0M

Input /M

$0.91/M

Output /M

$1.82/M

Cache read /M

$0.07/M

Cache write /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4 Pro (Thinking)

deepseek/deepseek-v4-pro:thinking:runware

Context

1.0M

Input /M

$0.91/M

Output /M

$1.82/M

Cache read /M

$0.07/M

Cache write /M

N/A

Cache hit

42.7%

TTFT

7.6s

Throughput

70.4 tps

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash:runware

Context

1.0M

Input /M

$0.14/M

Output /M

$0.57/M

Cache read /M

$0.0095/M

Cache write /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash (Thinking)

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

Context

1.0M

Input /M

$0.14/M

Output /M

$0.57/M

Cache read /M

$0.0095/M

Cache write /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Gemma 4 31B

google/gemma-4-31b-it:runware

Context

262k

Input /M

$0.10/M

Output /M

$0.28/M

Cache read /M

$0.01/M

Cache write /M

N/A

Cache hit

76.1%

TTFT

2.3s

Throughput

77.5 tps

Gemma 4 31B (Thinking)

google/gemma-4-31b-it:thinking:runware

Context

262k

Input /M

$0.10/M

Output /M

$0.28/M

Cache read /M

$0.01/M

Cache write /M

N/A

Cache hit

9.6%

TTFT

3.8s

Throughput

35.3 tps

GLM 5.2

z-ai/glm-5.2:runware

Context

1.0M

Input /M

$0.76/M

Output /M

$2.41/M

Cache read /M

$0.15/M

Cache write /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GLM 5.2 (Thinking)

z-ai/glm-5.2:thinking:runware

Context

1.0M

Input /M

$0.76/M

Output /M

$2.41/M

Cache read /M

$0.15/M

Cache write /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GLM 5.3

z-ai/glm-5.3:runware

Context

1.0M

Input /M

$1.13/M

Output /M

$3.78/M

Cache read /M

$0.19/M

Cache write /M

N/A

Cache hit

N/A

TTFT

4.1s

Throughput

238.3 tps

GLM 5.3 (Thinking)

z-ai/glm-5.3:thinking:runware

Context

1.0M

Input /M

$1.13/M

Output /M

$3.78/M

Cache read /M

$0.19/M

Cache write /M

N/A

Cache hit

99.7%

TTFT

7.8s

Throughput

321.6 tps

GLM 5.3 Flash

z-ai/glm-5.3-flash:runware

Context

1M

Input /M

$0.14/M

Output /M

$0.47/M

Cache read /M

$0.03/M

Cache write /M

N/A

Cache hit

0%

TTFT

5.3s

Throughput

135.5 tps

GPT OSS 120B

openai/gpt-oss-120b:runware

Context

128k

Input /M

$0.03/M

Output /M

$0.13/M

Cache read /M

$0.03/M

Cache write /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Kimi K2.6

moonshotai/kimi-k2.6:runware

Context

262k

Input /M

$0.57/M

Output /M

$2.88/M

Cache read /M

$0.12/M

Cache write /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Kimi K2.6 Thinking

moonshotai/kimi-k2.6:thinking:runware

Context

262k

Input /M

$0.57/M

Output /M

$2.88/M

Cache read /M

$0.12/M

Cache write /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Kimi K3

moonshotai/kimi-k3:runware

Context

1.0M

Input /M

$3.15/M

Output /M

$15.75/M

Cache read /M

$0.31/M

Cache write /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

MiniMax M2.7

minimax/minimax-m2.7:runware

Context

205k

Input /M

$0.28/M

Output /M

$1.13/M

Cache read /M

$0.06/M

Cache write /M

$0.35/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

MiniMax M2.7 Turbo

minimax/minimax-m2.7-turbo:runware

Context

205k

Input /M

$0.57/M

Output /M

$2.27/M

Cache read /M

$0.06/M

Cache write /M

$0.35/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

MiniMax M3 Thinking

minimax/minimax-m3:thinking:runware

Context

1M

Input /M

$0.28/M

Output /M

$1.13/M

Cache read /M

$0.06/M

Cache write /M

N/A

Cache hit

N/A

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 Runware via the API

Call a model served by Runware 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/deepseek-v4-flash:runware",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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