Runware

UNK

21 models available

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, or Kimi K3 routes, whose retention and training policies remain unverified.

Some routes unverified

Privacy can differ by model. See each model’s label.

ZDR

DeepSeek V4 Flash, DeepSeek V4 Flash (Thinking), DeepSeek V4 Pro, DeepSeek V4 Pro (Thinking), DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash 1017 (Thinking), Gemma 4 31B, Gemma 4 31B (Thinking), GLM 5.2, GLM 5.2 (Thinking), GLM 5.3, GLM 5.3 (Thinking), GLM 5.3 Flash, GPT OSS 120B, MiniMax M2.7, MiniMax M3 Thinking, MiniMax M3.1 Flash

Unverified

DeepSeek V4.1 Flash, DeepSeek V4.1 Flash (Thinking), Kimi K3, MiniMax M2.7 Turbo

Models served by Runware

21 models

Model	Context	Input /M	Output /M	Cache read /M	Cache write /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash ZDR	1.0M	$0.0718/M	$0.145/M	$0.0132/M	N/A	N/A	1.1s	221.9 tps
DeepSeek V4 Flash (Thinking) ZDR	1.0M	$0.0718/M	$0.145/M	$0.0132/M	N/A	95.1%	1.3s	275.1 tps
DeepSeek V4 Pro ZDR	1.0M	$0.908/M	$1.82/M	$0.0747/M	N/A	N/A	N/A	N/A
DeepSeek V4 Pro (Thinking) ZDR	1.0M	$0.908/M	$1.82/M	$0.0747/M	N/A	0%	2s	115.3 tps
DeepSeek V4.1 Flash Unverified	1.0M	$0.142/M	$0.567/M	$0.00945/M	N/A	N/A	N/A	N/A
DeepSeek V4.1 Flash (Thinking) Unverified	1.0M	$0.142/M	$0.567/M	$0.00945/M	N/A	N/A	N/A	N/A
DeepSeek V4.1 Flash 1017 ZDR	1.0M	$0.142/M	$0.567/M	$0.00945/M	N/A	99.5%	2s	536.8 tps
DeepSeek V4.1 Flash 1017 (Thinking) ZDR	1.0M	$0.142/M	$0.567/M	$0.00945/M	N/A	99.5%	2s	536.8 tps
Gemma 4 31B ZDR	262k	$0.0964/M	$0.281/M	$0.0113/M	N/A	0%	2.5s	249.4 tps
Gemma 4 31B (Thinking) ZDR	262k	$0.0964/M	$0.281/M	$0.0113/M	N/A	29%	7.8s	233.5 tps
GLM 5.2 ZDR	1.0M	$0.756/M	$2.41/M	$0.151/M	N/A	N/A	N/A	N/A
GLM 5.2 (Thinking) ZDR	1.0M	$0.756/M	$2.41/M	$0.151/M	N/A	N/A	1.4s	109 tps
GLM 5.3 ZDR	1.0M	$1.13/M	$3.78/M	$0.189/M	N/A	N/A	N/A	N/A
GLM 5.3 (Thinking) ZDR	1.0M	$1.13/M	$3.78/M	$0.189/M	N/A	N/A	N/A	N/A
GLM 5.3 Flash ZDR	1M	$0.142/M	$0.473/M	$0.0284/M	N/A	85.2%	3.8s	129.4 tps
GPT OSS 120B ZDR	128k	$0.0302/M	$0.132/M	$0.0302/M	N/A	N/A	N/A	N/A
Kimi K3 Unverified	1.0M	$3.15/M	$15.75/M	$0.315/M	N/A	N/A	N/A	N/A
MiniMax M2.7 ZDR	205k	$0.284/M	$1.13/M	$0.0567/M	$0.354/M	N/A	N/A	N/A
MiniMax M2.7 Turbo Unverified	205k	$0.567/M	$2.27/M	$0.0567/M	$0.354/M	N/A	N/A	N/A
MiniMax M3 Thinking ZDR	1M	$0.284/M	$1.13/M	$0.0567/M	N/A	N/A	N/A	N/A
MiniMax M3.1 Flash ZDR	1M	$0.157/M	$0.63/M	$0.0158/M	N/A	N/A	N/A	N/A

DeepSeek V4 Flash

ZDR

Context: 1.0M
Input /M: $0.0718/M
Output /M: $0.145/M
Cache read /M: $0.0132/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 1.1s
Throughput: 221.9 tps

DeepSeek V4 Flash (Thinking)

ZDR

Context: 1.0M
Input /M: $0.0718/M
Output /M: $0.145/M
Cache read /M: $0.0132/M
Cache write /M: N/A
Cache hit: 95.1%
TTFT: 1.3s
Throughput: 275.1 tps

DeepSeek V4 Pro

ZDR

Context: 1.0M
Input /M: $0.908/M
Output /M: $1.82/M
Cache read /M: $0.0747/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

DeepSeek V4 Pro (Thinking)

ZDR

Context: 1.0M
Input /M: $0.908/M
Output /M: $1.82/M
Cache read /M: $0.0747/M
Cache write /M: N/A
Cache hit: 0%
TTFT: 2s
Throughput: 115.3 tps

DeepSeek V4.1 Flash

Unverified

Context: 1.0M
Input /M: $0.142/M
Output /M: $0.567/M
Cache read /M: $0.00945/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

DeepSeek V4.1 Flash (Thinking)

Unverified

Context: 1.0M
Input /M: $0.142/M
Output /M: $0.567/M
Cache read /M: $0.00945/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

DeepSeek V4.1 Flash 1017

ZDR

Context: 1.0M
Input /M: $0.142/M
Output /M: $0.567/M
Cache read /M: $0.00945/M
Cache write /M: N/A
Cache hit: 99.5%
TTFT: 2s
Throughput: 536.8 tps

DeepSeek V4.1 Flash 1017 (Thinking)

ZDR

Context: 1.0M
Input /M: $0.142/M
Output /M: $0.567/M
Cache read /M: $0.00945/M
Cache write /M: N/A
Cache hit: 99.5%
TTFT: 2s
Throughput: 536.8 tps

Gemma 4 31B

ZDR

Context: 262k
Input /M: $0.0964/M
Output /M: $0.281/M
Cache read /M: $0.0113/M
Cache write /M: N/A
Cache hit: 0%
TTFT: 2.5s
Throughput: 249.4 tps

Gemma 4 31B (Thinking)

ZDR

Context: 262k
Input /M: $0.0964/M
Output /M: $0.281/M
Cache read /M: $0.0113/M
Cache write /M: N/A
Cache hit: 29%
TTFT: 7.8s
Throughput: 233.5 tps

GLM 5.2

ZDR

Context: 1.0M
Input /M: $0.756/M
Output /M: $2.41/M
Cache read /M: $0.151/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

GLM 5.2 (Thinking)

ZDR

Context: 1.0M
Input /M: $0.756/M
Output /M: $2.41/M
Cache read /M: $0.151/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 1.4s
Throughput: 109 tps

GLM 5.3

ZDR

Context: 1.0M
Input /M: $1.13/M
Output /M: $3.78/M
Cache read /M: $0.189/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

GLM 5.3 (Thinking)

ZDR

Context: 1.0M
Input /M: $1.13/M
Output /M: $3.78/M
Cache read /M: $0.189/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

GLM 5.3 Flash

ZDR

Context: 1M
Input /M: $0.142/M
Output /M: $0.473/M
Cache read /M: $0.0284/M
Cache write /M: N/A
Cache hit: 85.2%
TTFT: 3.8s
Throughput: 129.4 tps

GPT OSS 120B

ZDR

Context: 128k
Input /M: $0.0302/M
Output /M: $0.132/M
Cache read /M: $0.0302/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Kimi K3

Unverified

Context: 1.0M
Input /M: $3.15/M
Output /M: $15.75/M
Cache read /M: $0.315/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

MiniMax M2.7

ZDR

Context: 205k
Input /M: $0.284/M
Output /M: $1.13/M
Cache read /M: $0.0567/M
Cache write /M: $0.354/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

MiniMax M2.7 Turbo

Unverified

Context: 205k
Input /M: $0.567/M
Output /M: $2.27/M
Cache read /M: $0.0567/M
Cache write /M: $0.354/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

MiniMax M3 Thinking

ZDR

Context: 1M
Input /M: $0.284/M
Output /M: $1.13/M
Cache read /M: $0.0567/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

MiniMax M3.1 Flash

ZDR

Context: 1M
Input /M: $0.157/M
Output /M: $0.63/M
Cache read /M: $0.0158/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

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.

Runware terms of use Runware privacy policy

Model

Context

Input /M

Output /M

Cache read /M

Cache write /M

Cache hit

TTFT

Throughput

DeepSeek V4 Flash

ZDR

1.0M

$0.0718/M

$0.145/M

$0.0132/M

N/A

1.1s

221.9 tps

DeepSeek V4 Flash (Thinking)

ZDR

1.0M

$0.0718/M

$0.145/M

$0.0132/M

N/A

95.1%

1.3s

275.1 tps

DeepSeek V4 Pro

ZDR

1.0M

$0.908/M

$1.82/M

$0.0747/M

N/A

DeepSeek V4 Pro (Thinking)

ZDR

1.0M

$0.908/M

$1.82/M

$0.0747/M

N/A

115.3 tps

DeepSeek V4.1 Flash

Unverified

1.0M

$0.142/M

$0.567/M

$0.00945/M

N/A

DeepSeek V4.1 Flash (Thinking)

Unverified

1.0M

$0.142/M

$0.567/M

$0.00945/M

N/A

DeepSeek V4.1 Flash 1017

ZDR

1.0M

$0.142/M

$0.567/M

$0.00945/M

N/A

99.5%

536.8 tps

DeepSeek V4.1 Flash 1017 (Thinking)

ZDR

1.0M

$0.142/M

$0.567/M

$0.00945/M

N/A

99.5%

536.8 tps

Gemma 4 31B

ZDR

262k

$0.0964/M

$0.281/M

$0.0113/M

N/A

2.5s

249.4 tps

Gemma 4 31B (Thinking)

ZDR

262k

$0.0964/M

$0.281/M

$0.0113/M

N/A

29%

7.8s

233.5 tps

GLM 5.2

ZDR

1.0M

$0.756/M

$2.41/M

$0.151/M

N/A

GLM 5.2 (Thinking)

ZDR

1.0M

$0.756/M

$2.41/M

$0.151/M

N/A

1.4s

109 tps

GLM 5.3

ZDR

1.0M

$1.13/M

$3.78/M

$0.189/M

N/A

GLM 5.3 (Thinking)

ZDR

1.0M

$1.13/M

$3.78/M

$0.189/M

N/A

GLM 5.3 Flash

ZDR

$0.142/M

$0.473/M

$0.0284/M

N/A

85.2%

3.8s

129.4 tps

GPT OSS 120B

ZDR

128k

$0.0302/M

$0.132/M

$0.0302/M

N/A

Kimi K3

Unverified

1.0M

$3.15/M

$15.75/M

$0.315/M

N/A

MiniMax M2.7

ZDR

205k

$0.284/M

$1.13/M

$0.0567/M

$0.354/M

N/A

MiniMax M2.7 Turbo

Unverified

205k

$0.567/M

$2.27/M

$0.0567/M

$0.354/M

N/A

MiniMax M3 Thinking

ZDR

$0.284/M

$1.13/M

$0.0567/M

N/A

MiniMax M3.1 Flash

ZDR

$0.157/M

$0.63/M

$0.0158/M

N/A

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

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"}]
  }'

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