Venice

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 Venice

Model name

42 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V3.2 deepseek/deepseek-v3.2:venice	160k	$0.28/M	$0.41/M	$0.14/M	3.1s	10 tps
DeepSeek V3.2 (Thinking) deepseek/deepseek-v3.2:thinking:venice	160k	$0.28/M	$0.41/M	$0.14/M	3.1s	10 tps
DeepSeek V4 Flash deepseek/deepseek-v4-flash:venice	1M	$0.10/M	$0.20/M	$0.02/M	1.7s	48 tps
DeepSeek V4 Flash (Thinking) deepseek/deepseek-v4-flash:thinking:venice	1M	$0.10/M	$0.20/M	$0.02/M	1.7s	48 tps
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731:venice	1M	$0.14/M	$0.27/M	$0.03/M	2.5s	46 tps
DeepSeek V4 Flash 0731 (Thinking) deepseek/deepseek-v4-flash-0731:thinking:venice	1M	$0.14/M	$0.27/M	$0.03/M	2.5s	46 tps
DeepSeek V4 Pro deepseek/deepseek-v4-pro:venice	1M	$1.73/M	$3.47/M	$0.35/M	1.6s	31 tps
DeepSeek V4 Pro (Thinking) deepseek/deepseek-v4-pro:thinking:venice	1M	$1.73/M	$3.47/M	$0.35/M	1.6s	31 tps
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813:venice	1M	$1.73/M	$5.20/M	$0.17/M	2s	27.5 tps
DeepSeek V4 Pro 0813 (Thinking) deepseek/deepseek-v4-pro-0813:thinking:venice	1M	$1.73/M	$5.20/M	$0.17/M	2s	27.5 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:venice	1M	$0.31/M	$1.26/M	$0.0079/M	1s	141 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:venice	1M	$0.31/M	$1.26/M	$0.0079/M	1s	141 tps
GLM 4.7 FP4 z-ai/glm-4.7:venice	198k	$0.42/M	$2.03/M	$0.08/M	23.8s	10 tps
GLM 4.7 (Thinking) FP4 z-ai/glm-4.7:thinking:venice	198k	$0.42/M	$2.03/M	$0.08/M	23.8s	10 tps
GLM 5.1 FP8 z-ai/glm-5.1:venice	200k	$1.47/M	$4.62/M	$0.27/M	101.6s	4.5 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:venice	200k	$1.47/M	$4.62/M	$0.27/M	101.6s	4.5 tps
GLM 5.2 FP8 z-ai/glm-5.2:venice	1M	$1.47/M	$4.62/M	$0.27/M	1.7s	48 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:venice	1M	$1.47/M	$4.62/M	$0.27/M	1.7s	48 tps
GLM 5.3 z-ai/glm-5.3:venice	1M	$1.47/M	$4.62/M	$0.27/M	3s	44 tps
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:venice	1M	$1.47/M	$4.62/M	$0.27/M	3s	44 tps
GLM 5.3 Flash z-ai/glm-5.3-flash:venice	1.0M	$0.16/M	$0.53/M	$0.03/M	0.8s	82 tps
GPT OSS 120B INT4 openai/gpt-oss-120b:venice	128k	$0.03/M	$0.16/M	$0.03/M	2.5s	16 tps
Kimi K2.5 Thinking moonshotai/kimi-k2.5:thinking:venice	256k	$0.56/M	$3.49/M	$0.22/M	1.4s	24 tps
Kimi K2.7 Code INT4 moonshotai/kimi-k2.7-code:venice	256k	$0.79/M	$3.68/M	$0.17/M	2.1s	16.5 tps
MiMo V2.5 FP8 xiaomi/mimo-v2.5:venice	1M	$0.42/M	$2.10/M	$0.08/M	2.2s	11 tps
MiMo V2.5 Thinking FP8 xiaomi/mimo-v2.5:thinking:venice	1M	$0.42/M	$2.10/M	$0.08/M	2.2s	11 tps
MiMo V2.6 Flash FP8 xiaomi/mimo-v2.6-flash:venice	1M	$0.18/M	$0.37/M	$0.0039/M	101.3s	2 tps
MiniMax M3 FP8 minimax/minimax-m3:venice	524k	$0.31/M	$1.26/M	$0.06/M	1.1s	116 tps
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:venice	524k	$0.31/M	$1.26/M	$0.06/M	1.1s	116 tps
Qwen 3.6 35B A3B FP8 Qwen/Qwen3.6-35B-A3B:venice	256k	$0.10/M	$1.05/M	N/A	0.7s	123.5 tps
Qwen 3.6 35B A3B Thinking FP8 Qwen/Qwen3.6-35B-A3B:thinking:venice	256k	$0.10/M	$1.05/M	N/A	0.7s	123.5 tps
Qwen3 235B A22B FP8 qwen/qwen3-235b-a22b:venice	128k	$0.16/M	$0.79/M	N/A	0.8s	18 tps
Qwen3 235B A22B Thinking FP8 Qwen/Qwen3-235B-A22B-Thinking-2507:venice	128k	$0.47/M	$3.68/M	N/A	0.9s	49 tps
Qwen3.5 35B A3B qwen3.5-35b-a3b:venice	256k	$0.16/M	$1.05/M	$0.05/M	0.9s	84 tps
Qwen3.5 35B A3B Thinking qwen3.5-35b-a3b:thinking:venice	256k	$0.16/M	$1.05/M	$0.05/M	0.9s	84 tps
Qwen3.5 397B qwen/qwen3.5-397b-a17b:venice	128k	$0.79/M	$4.73/M	N/A	1s	34 tps
Qwen3.5 397B Thinking qwen/qwen3.5-397b-a17b-thinking:venice	128k	$0.79/M	$4.73/M	N/A	1s	34 tps
Qwen3.5 9B FP8 qwen/qwen3.5-9b:venice	256k	$0.10/M	$0.16/M	N/A	0.5s	84 tps
Qwen3.8 27B FP8 qwen3.8-27b:venice	262k	$0.47/M	$3.36/M	N/A	1.1s	80 tps
Qwen3.8 27B Thinking FP8 qwen3.8-27b:thinking:venice	262k	$0.47/M	$3.36/M	N/A	1.1s	80 tps
Qwen3.8 Max qwen3.8-max:venice	262k	$2.10/M	$6.30/M	$0.26/M	0.8s	127 tps
Qwen3.8 Max Thinking qwen3.8-max:thinking:venice	262k	$2.10/M	$6.30/M	$0.26/M	0.8s	127 tps

DeepSeek V3.2

deepseek/deepseek-v3.2:venice

Context

160k

Input /M

$0.28/M

Output /M

$0.41/M

Cache read /M

$0.14/M

TTFT

3.1s

Throughput

10 tps

DeepSeek V3.2 (Thinking)

deepseek/deepseek-v3.2:thinking:venice

Context

160k

Input /M

$0.28/M

Output /M

$0.41/M

Cache read /M

$0.14/M

TTFT

3.1s

Throughput

10 tps

DeepSeek V4 Flash

deepseek/deepseek-v4-flash:venice

Context

1M

Input /M

$0.10/M

Output /M

$0.20/M

Cache read /M

$0.02/M

TTFT

1.7s

Throughput

48 tps

DeepSeek V4 Flash (Thinking)

deepseek/deepseek-v4-flash:thinking:venice

Context

1M

Input /M

$0.10/M

Output /M

$0.20/M

Cache read /M

$0.02/M

TTFT

1.7s

Throughput

48 tps

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731:venice

Context

1M

Input /M

$0.14/M

Output /M

$0.27/M

Cache read /M

$0.03/M

TTFT

2.5s

Throughput

46 tps

DeepSeek V4 Flash 0731 (Thinking)

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

Context

1M

Input /M

$0.14/M

Output /M

$0.27/M

Cache read /M

$0.03/M

TTFT

2.5s

Throughput

46 tps

DeepSeek V4 Pro

deepseek/deepseek-v4-pro:venice

Context

1M

Input /M

$1.73/M

Output /M

$3.47/M

Cache read /M

$0.35/M

TTFT

1.6s

Throughput

31 tps

DeepSeek V4 Pro (Thinking)

deepseek/deepseek-v4-pro:thinking:venice

Context

1M

Input /M

$1.73/M

Output /M

$3.47/M

Cache read /M

$0.35/M

TTFT

1.6s

Throughput

31 tps

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813:venice

Context

1M

Input /M

$1.73/M

Output /M

$5.20/M

Cache read /M

$0.17/M

TTFT

2s

Throughput

27.5 tps

DeepSeek V4 Pro 0813 (Thinking)

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

Context

1M

Input /M

$1.73/M

Output /M

$5.20/M

Cache read /M

$0.17/M

TTFT

2s

Throughput

27.5 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:venice

Context

1M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.0079/M

TTFT

1s

Throughput

141 tps

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

1M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.0079/M

TTFT

1s

Throughput

141 tps

GLM 4.7

FP4

z-ai/glm-4.7:venice

Context

198k

Input /M

$0.42/M

Output /M

$2.03/M

Cache read /M

$0.08/M

TTFT

23.8s

Throughput

10 tps

GLM 4.7 (Thinking)

FP4

z-ai/glm-4.7:thinking:venice

Context

198k

Input /M

$0.42/M

Output /M

$2.03/M

Cache read /M

$0.08/M

TTFT

23.8s

Throughput

10 tps

GLM 5.1

FP8

z-ai/glm-5.1:venice

Context

200k

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

101.6s

Throughput

4.5 tps

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:venice

Context

200k

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

101.6s

Throughput

4.5 tps

GLM 5.2

FP8

z-ai/glm-5.2:venice

Context

1M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

1.7s

Throughput

48 tps

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:venice

Context

1M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

1.7s

Throughput

48 tps

GLM 5.3

z-ai/glm-5.3:venice

Context

1M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

3s

Throughput

44 tps

GLM 5.3 (Thinking)

z-ai/glm-5.3:thinking:venice

Context

1M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

3s

Throughput

44 tps

GLM 5.3 Flash

z-ai/glm-5.3-flash:venice

Context

1.0M

Input /M

$0.16/M

Output /M

$0.53/M

Cache read /M

$0.03/M

TTFT

0.8s

Throughput

82 tps

GPT OSS 120B

INT4

openai/gpt-oss-120b:venice

Context

128k

Input /M

$0.03/M

Output /M

$0.16/M

Cache read /M

$0.03/M

TTFT

2.5s

Throughput

16 tps

Kimi K2.5 Thinking

moonshotai/kimi-k2.5:thinking:venice

Context

256k

Input /M

$0.56/M

Output /M

$3.49/M

Cache read /M

$0.22/M

TTFT

1.4s

Throughput

24 tps

Kimi K2.7 Code

INT4

moonshotai/kimi-k2.7-code:venice

Context

256k

Input /M

$0.79/M

Output /M

$3.68/M

Cache read /M

$0.17/M

TTFT

2.1s

Throughput

16.5 tps

MiMo V2.5

FP8

xiaomi/mimo-v2.5:venice

Context

1M

Input /M

$0.42/M

Output /M

$2.10/M

Cache read /M

$0.08/M

TTFT

2.2s

Throughput

11 tps

MiMo V2.5 Thinking

FP8

xiaomi/mimo-v2.5:thinking:venice

Context

1M

Input /M

$0.42/M

Output /M

$2.10/M

Cache read /M

$0.08/M

TTFT

2.2s

Throughput

11 tps

MiMo V2.6 Flash

FP8

xiaomi/mimo-v2.6-flash:venice

Context

1M

Input /M

$0.18/M

Output /M

$0.37/M

Cache read /M

$0.0039/M

TTFT

101.3s

Throughput

2 tps

MiniMax M3

FP8

minimax/minimax-m3:venice

Context

524k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

TTFT

1.1s

Throughput

116 tps

MiniMax M3 Thinking

FP8

minimax/minimax-m3:thinking:venice

Context

524k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

TTFT

1.1s

Throughput

116 tps

Qwen 3.6 35B A3B

FP8

Qwen/Qwen3.6-35B-A3B:venice

Context

256k

Input /M

$0.10/M

Output /M

$1.05/M

Cache read /M

N/A

TTFT

0.7s

Throughput

123.5 tps

Qwen 3.6 35B A3B Thinking

FP8

Qwen/Qwen3.6-35B-A3B:thinking:venice

Context

256k

Input /M

$0.10/M

Output /M

$1.05/M

Cache read /M

N/A

TTFT

0.7s

Throughput

123.5 tps

Qwen3 235B A22B

FP8

qwen/qwen3-235b-a22b:venice

Context

128k

Input /M

$0.16/M

Output /M

$0.79/M

Cache read /M

N/A

TTFT

0.8s

Throughput

18 tps

Qwen3 235B A22B Thinking

FP8

Qwen/Qwen3-235B-A22B-Thinking-2507:venice

Context

128k

Input /M

$0.47/M

Output /M

$3.68/M

Cache read /M

N/A

TTFT

0.9s

Throughput

49 tps

Qwen3.5 35B A3B

qwen3.5-35b-a3b:venice

Context

256k

Input /M

$0.16/M

Output /M

$1.05/M

Cache read /M

$0.05/M

TTFT

0.9s

Throughput

84 tps

Qwen3.5 35B A3B Thinking

qwen3.5-35b-a3b:thinking:venice

Context

256k

Input /M

$0.16/M

Output /M

$1.05/M

Cache read /M

$0.05/M

TTFT

0.9s

Throughput

84 tps

Qwen3.5 397B

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

Context

128k

Input /M

$0.79/M

Output /M

$4.73/M

Cache read /M

N/A

TTFT

1s

Throughput

34 tps

Qwen3.5 397B Thinking

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

Context

128k

Input /M

$0.79/M

Output /M

$4.73/M

Cache read /M

N/A

TTFT

1s

Throughput

34 tps

Qwen3.5 9B

FP8

qwen/qwen3.5-9b:venice

Context

256k

Input /M

$0.10/M

Output /M

$0.16/M

Cache read /M

N/A

TTFT

0.5s

Throughput

84 tps

Qwen3.8 27B

FP8

qwen3.8-27b:venice

Context

262k

Input /M

$0.47/M

Output /M

$3.36/M

Cache read /M

N/A

TTFT

1.1s

Throughput

80 tps

Qwen3.8 27B Thinking

FP8

qwen3.8-27b:thinking:venice

Context

262k

Input /M

$0.47/M

Output /M

$3.36/M

Cache read /M

N/A

TTFT

1.1s

Throughput

80 tps

Qwen3.8 Max

qwen3.8-max:venice

Context

262k

Input /M

$2.10/M

Output /M

$6.30/M

Cache read /M

$0.26/M

TTFT

0.8s

Throughput

127 tps

Qwen3.8 Max Thinking

qwen3.8-max:thinking:venice

Context

262k

Input /M

$2.10/M

Output /M

$6.30/M

Cache read /M

$0.26/M

TTFT

0.8s

Throughput

127 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 Venice via the API

Call a model served by Venice 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-v3.2:venice",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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