DeepInfra

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 DeepInfra

Model name

69 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek R1-0528 FP4 deepseek-ai/DeepSeek-R1-0528:deepinfra	164k	$0.53/M	$2.26/M	$0.37/M	0.7s	25 tps
DeepSeek V3.1 FP4 deepseek-ai/DeepSeek-V3.1:deepinfra	164k	$0.26/M	$1.00/M	$0.14/M	6.4s	6 tps
DeepSeek V3.2 FP4 deepseek/deepseek-v3.2:deepinfra	164k	$0.27/M	$0.40/M	$0.14/M	2.3s	9 tps
DeepSeek V3.2 (Thinking) FP4 deepseek/deepseek-v3.2:thinking:deepinfra	164k	$0.27/M	$0.40/M	$0.14/M	2.3s	9 tps
DeepSeek V4 Flash FP8 deepseek/deepseek-v4-flash:deepinfra	1.0M	$0.09/M	$0.19/M	$0.02/M	8.2s	12 tps
DeepSeek V4 Flash (Thinking) FP8 deepseek/deepseek-v4-flash:thinking:deepinfra	1.0M	$0.09/M	$0.19/M	$0.02/M	8.2s	12 tps
DeepSeek V4 Flash 0731 FP8 deepseek/deepseek-v4-flash-0731:deepinfra	1.0M	$0.06/M	$0.19/M	$0.02/M	0.6s	37 tps
DeepSeek V4 Flash 0731 (Thinking) FP8 deepseek/deepseek-v4-flash-0731:thinking:deepinfra	1.0M	$0.06/M	$0.19/M	$0.02/M	0.6s	37 tps
DeepSeek V4 Flash Vision Exp FP8 deepseek/deepseek-v4-flash-vision-exp:deepinfra	1.0M	$0.23/M	$0.68/M	$0.0072/M	1.9s	43 tps
DeepSeek V4 Pro FP8 deepseek/deepseek-v4-pro:deepinfra	1.0M	$1.36/M	$2.73/M	$0.10/M	1.4s	36 tps
DeepSeek V4 Pro (Thinking) FP8 deepseek/deepseek-v4-pro:thinking:deepinfra	1.0M	$1.36/M	$2.73/M	$0.10/M	1.4s	36 tps
DeepSeek V4 Pro 0813 FP8 deepseek/deepseek-v4-pro-0813:deepinfra	1.0M	$1.36/M	$2.73/M	$0.10/M	1.5s	49 tps
DeepSeek V4 Pro 0813 (Thinking) FP8 deepseek/deepseek-v4-pro-0813:thinking:deepinfra	1.0M	$1.36/M	$2.73/M	$0.10/M	1.5s	49 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:deepinfra	1.0M	$0.15/M	$0.44/M	$0.0044/M	0.8s	57 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:deepinfra	1.0M	$0.15/M	$0.44/M	$0.0044/M	0.8s	57 tps
Gemma 4 26B A4B FP8 google/gemma-4-26b-a4b-it:deepinfra	262k	$0.07/M	$0.36/M	$0.01/M	0.5s	28 tps
Gemma 4 31B FP8 google/gemma-4-31b-it:deepinfra	262k	$0.21/M	$0.42/M	$0.02/M	1.2s	23 tps
GLM 4.6 FP4 z-ai/glm-4.6:deepinfra	203k	$0.53/M	$2.10/M	$0.10/M	1.1s	14 tps
GLM 4.6 (Thinking) FP4 z-ai/glm-4.6:thinking:deepinfra	203k	$0.53/M	$2.10/M	$0.10/M	1.1s	14 tps
GLM 4.7 FP4 z-ai/glm-4.7:deepinfra	203k	$0.42/M	$1.84/M	$0.08/M	2s	12 tps
GLM 4.7 (Thinking) FP4 z-ai/glm-4.7:thinking:deepinfra	203k	$0.42/M	$1.84/M	$0.08/M	2s	12 tps
GLM 5.2 FP4 z-ai/glm-5.2:deepinfra	1.0M	$0.59/M	$1.89/M	$0.11/M	1s	60 tps
GLM 5.2 (Thinking) FP4 z-ai/glm-5.2:thinking:deepinfra	1.0M	$0.59/M	$1.89/M	$0.11/M	1s	60 tps
GLM 5.3 FP4 z-ai/glm-5.3:deepinfra	1.0M	$0.59/M	$2.63/M	$0.13/M	46.2s	2.5 tps
GLM 5.3 (Thinking) FP4 z-ai/glm-5.3:thinking:deepinfra	1.0M	$0.59/M	$2.63/M	$0.13/M	46.2s	2.5 tps
GLM 5.3 Flash FP4 z-ai/glm-5.3-flash:deepinfra	1.0M	$0.08/M	$0.26/M	$0.02/M	1.9s	29 tps
GPT OSS 120B BF16 openai/gpt-oss-120b:deepinfra	131k	$0.04/M	$0.18/M	N/A	0.3s	56 tps
GPT OSS 20B BF16 openai/gpt-oss-20b:deepinfra	131k	$0.03/M	$0.15/M	N/A	0.3s	98 tps
Granite 4.2 8B BF16 ibm-granite/granite-4.2-8b:deepinfra	131k	$0.06/M	$0.26/M	$0.02/M	0.4s	138 tps
Hermes 3 70B FP8 nousresearch/hermes-3-llama-3.1-70b:deepinfra	131k	$0.73/M	$0.73/M	N/A	0.9s	28 tps
Inkling FP8 thinkingmachines/inkling:deepinfra	524k	$1.00/M	$4.25/M	$0.17/M	0.7s	65 tps
Inkling Small FP8 thinkingmachines/Inkling-Small:deepinfra	524k	$0.47/M	$1.26/M	$0.10/M	0.6s	146 tps
Inkling Small Thinking FP8 thinkingmachines/Inkling-Small:thinking:deepinfra	524k	$0.47/M	$1.26/M	$0.10/M	0.6s	146 tps
Inkling Thinking FP8 thinkingmachines/inkling:thinking:deepinfra	524k	$1.00/M	$4.25/M	$0.17/M	0.7s	65 tps
Kimi K2.6 FP4 moonshotai/kimi-k2.6:deepinfra	262k	$0.79/M	$3.68/M	$0.16/M	2s	11 tps
Kimi K3 MXFP4 moonshotai/kimi-k3:deepinfra	1.0M	$2.99/M	$14.96/M	$0.30/M	1.3s	27 tps
Llama 3.1 8B FP8 meta-llama/llama-3.1-8b-instruct:deepinfra	131k	$0.02/M	$0.04/M	N/A	0.5s	16 tps
Llama 3.3 70B Instruct FP8 meta-llama/llama-3.3-70b-instruct:deepinfra	131k	$0.10/M	$0.34/M	N/A	0.5s	13 tps
MiMo V2.6 Flash FP8 xiaomi/mimo-v2.6-flash:deepinfra	1.0M	$0.15/M	$0.29/M	$0.0029/M	N/A	N/A
MiMo V2.6 Pro FP8 xiaomi/mimo-v2.6-pro:deepinfra	1.0M	$0.45/M	$0.91/M	$0.0038/M	1.2s	30 tps
MiniMax M3 FP8 minimax/minimax-m3:deepinfra	524k	$0.29/M	$1.16/M	$0.06/M	0.9s	24 tps
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:deepinfra	524k	$0.29/M	$1.16/M	$0.06/M	0.9s	24 tps
Mistral Small 3 24B (2501) FP8 mistralai/mistral-small-24b-instruct-2501:deepinfra	33k	$0.05/M	$0.08/M	N/A	0.4s	51 tps
Nemotron 3.5 Content Safety BF16 nvidia/nemotron-3.5-content-safety:deepinfra	131k	$0.21/M	$0.21/M	N/A	0.3s	199.5 tps
Nvidia Nemotron 3 Super 120B BF16 nvidia/nemotron-3-super-120b-a12b:deepinfra	262k	$0.09/M	$0.42/M	N/A	0.8s	80 tps
Nvidia Nemotron 3 Super 120B Thinking BF16 nvidia/nemotron-3-super-120b-a12b:thinking:deepinfra	262k	$0.09/M	$0.42/M	N/A	0.8s	80 tps
Nvidia Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b:deepinfra	262k	$0.53/M	$2.31/M	$0.11/M	N/A	N/A
Nvidia Nemotron 3 Ultra 550B Thinking nvidia/nemotron-3-ultra-550b-a55b:thinking:deepinfra	262k	$0.53/M	$2.31/M	$0.11/M	N/A	N/A
Nvidia Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightning:deepinfra	262k	$0.06/M	$0.17/M	$0.03/M	N/A	N/A
Nvidia Nemotron 3.5 Lightning Thinking nvidia/nemotron-3.5-lightning:thinking:deepinfra	262k	$0.06/M	$0.17/M	$0.03/M	N/A	N/A
Qwen 2.5 72B Instruct FP8 qwen/qwen-2.5-72b-instruct:deepinfra	33k	$0.38/M	$0.42/M	N/A	0.4s	33 tps
Qwen 3.6 27B FP8 alibaba/qwen3.6-27b:deepinfra	262k	$0.34/M	$3.36/M	N/A	0.4s	74 tps
Qwen 3.6 27B Thinking FP8 alibaba/qwen3.6-27b:thinking:deepinfra	262k	$0.34/M	$3.36/M	N/A	0.4s	74 tps
Qwen 3.6 35B A3B FP8 Qwen/Qwen3.6-35B-A3B:deepinfra	262k	$0.10/M	$1.00/M	$0.10/M	1.3s	34 tps
Qwen 3.6 35B A3B Thinking FP8 Qwen/Qwen3.6-35B-A3B:thinking:deepinfra	262k	$0.10/M	$1.00/M	$0.10/M	1.3s	34 tps
Qwen3 14B FP8 qwen/qwen3-14b:deepinfra	41k	$0.13/M	$0.25/M	N/A	0.9s	62 tps
Qwen3 235B A22B FP8 qwen/qwen3-235b-a22b:deepinfra	262k	$0.09/M	$0.58/M	N/A	0.5s	14 tps
Qwen3 32B FP8 qwen/qwen3-32b:deepinfra	41k	$0.08/M	$0.29/M	N/A	0.4s	28 tps
Qwen3 Next 80B A3B Instruct FP8 Qwen/Qwen3-Next-80B-A3B-Instruct:deepinfra	262k	$0.09/M	$1.16/M	N/A	0.5s	119 tps
Qwen3.5 27B FP8 qwen3.5-27b:deepinfra	262k	$0.27/M	$2.73/M	N/A	0.3s	74.5 tps
Qwen3.5 27B Thinking FP8 qwen3.5-27b:thinking:deepinfra	262k	$0.27/M	$2.73/M	N/A	0.3s	74.5 tps
Qwen3.5 35B A3B FP8 qwen3.5-35b-a3b:deepinfra	262k	$0.15/M	$1.05/M	$0.05/M	0.4s	80 tps
Qwen3.5 35B A3B Thinking FP8 qwen3.5-35b-a3b:thinking:deepinfra	262k	$0.15/M	$1.05/M	$0.05/M	0.4s	80 tps
Qwen3.5 397B FP8 qwen/qwen3.5-397b-a17b:deepinfra	262k	$0.47/M	$3.15/M	$0.23/M	0.8s	26 tps
Qwen3.5 397B Thinking FP8 qwen/qwen3.5-397b-a17b-thinking:deepinfra	262k	$0.47/M	$3.15/M	$0.23/M	0.8s	26 tps
Qwen3.5 9B BF16 qwen/qwen3.5-9b:deepinfra	262k	$0.10/M	$0.16/M	N/A	1.2s	6 tps
Qwen3.8 27B BF16 qwen3.8-27b:deepinfra	262k	$0.16/M	$1.97/M	$0.04/M	46.5s	3 tps
Qwen3.8 27B Thinking BF16 qwen3.8-27b:thinking:deepinfra	262k	$0.16/M	$1.97/M	$0.04/M	46.5s	3 tps
Tencent Hy4 Preview FP8 tencent/hy4-preview:deepinfra	1.0M	$0.88/M	$2.63/M	$0.04/M	3.1s	9 tps

DeepSeek R1-0528

FP4

deepseek-ai/DeepSeek-R1-0528:deepinfra

Context

164k

Input /M

$0.53/M

Output /M

$2.26/M

Cache read /M

$0.37/M

TTFT

0.7s

Throughput

25 tps

DeepSeek V3.1

FP4

deepseek-ai/DeepSeek-V3.1:deepinfra

Context

164k

Input /M

$0.26/M

Output /M

$1.00/M

Cache read /M

$0.14/M

TTFT

6.4s

Throughput

6 tps

DeepSeek V3.2

FP4

deepseek/deepseek-v3.2:deepinfra

Context

164k

Input /M

$0.27/M

Output /M

$0.40/M

Cache read /M

$0.14/M

TTFT

2.3s

Throughput

9 tps

DeepSeek V3.2 (Thinking)

FP4

deepseek/deepseek-v3.2:thinking:deepinfra

Context

164k

Input /M

$0.27/M

Output /M

$0.40/M

Cache read /M

$0.14/M

TTFT

2.3s

Throughput

9 tps

DeepSeek V4 Flash

FP8

deepseek/deepseek-v4-flash:deepinfra

Context

1.0M

Input /M

$0.09/M

Output /M

$0.19/M

Cache read /M

$0.02/M

TTFT

8.2s

Throughput

12 tps

DeepSeek V4 Flash (Thinking)

FP8

deepseek/deepseek-v4-flash:thinking:deepinfra

Context

1.0M

Input /M

$0.09/M

Output /M

$0.19/M

Cache read /M

$0.02/M

TTFT

8.2s

Throughput

12 tps

DeepSeek V4 Flash 0731

FP8

deepseek/deepseek-v4-flash-0731:deepinfra

Context

1.0M

Input /M

$0.06/M

Output /M

$0.19/M

Cache read /M

$0.02/M

TTFT

0.6s

Throughput

37 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

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

Context

1.0M

Input /M

$0.06/M

Output /M

$0.19/M

Cache read /M

$0.02/M

TTFT

0.6s

Throughput

37 tps

DeepSeek V4 Flash Vision Exp

FP8

deepseek/deepseek-v4-flash-vision-exp:deepinfra

Context

1.0M

Input /M

$0.23/M

Output /M

$0.68/M

Cache read /M

$0.0072/M

TTFT

1.9s

Throughput

43 tps

DeepSeek V4 Pro

FP8

deepseek/deepseek-v4-pro:deepinfra

Context

1.0M

Input /M

$1.36/M

Output /M

$2.73/M

Cache read /M

$0.10/M

TTFT

1.4s

Throughput

36 tps

DeepSeek V4 Pro (Thinking)

FP8

deepseek/deepseek-v4-pro:thinking:deepinfra

Context

1.0M

Input /M

$1.36/M

Output /M

$2.73/M

Cache read /M

$0.10/M

TTFT

1.4s

Throughput

36 tps

DeepSeek V4 Pro 0813

FP8

deepseek/deepseek-v4-pro-0813:deepinfra

Context

1.0M

Input /M

$1.36/M

Output /M

$2.73/M

Cache read /M

$0.10/M

TTFT

1.5s

Throughput

49 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

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

Context

1.0M

Input /M

$1.36/M

Output /M

$2.73/M

Cache read /M

$0.10/M

TTFT

1.5s

Throughput

49 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:deepinfra

Context

1.0M

Input /M

$0.15/M

Output /M

$0.44/M

Cache read /M

$0.0044/M

TTFT

0.8s

Throughput

57 tps

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

1.0M

Input /M

$0.15/M

Output /M

$0.44/M

Cache read /M

$0.0044/M

TTFT

0.8s

Throughput

57 tps

Gemma 4 26B A4B

FP8

google/gemma-4-26b-a4b-it:deepinfra

Context

262k

Input /M

$0.07/M

Output /M

$0.36/M

Cache read /M

$0.01/M

TTFT

0.5s

Throughput

28 tps

Gemma 4 31B

FP8

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

Context

262k

Input /M

$0.21/M

Output /M

$0.42/M

Cache read /M

$0.02/M

TTFT

1.2s

Throughput

23 tps

GLM 4.6

FP4

z-ai/glm-4.6:deepinfra

Context

203k

Input /M

$0.53/M

Output /M

$2.10/M

Cache read /M

$0.10/M

TTFT

1.1s

Throughput

14 tps

GLM 4.6 (Thinking)

FP4

z-ai/glm-4.6:thinking:deepinfra

Context

203k

Input /M

$0.53/M

Output /M

$2.10/M

Cache read /M

$0.10/M

TTFT

1.1s

Throughput

14 tps

GLM 4.7

FP4

z-ai/glm-4.7:deepinfra

Context

203k

Input /M

$0.42/M

Output /M

$1.84/M

Cache read /M

$0.08/M

TTFT

2s

Throughput

12 tps

GLM 4.7 (Thinking)

FP4

z-ai/glm-4.7:thinking:deepinfra

Context

203k

Input /M

$0.42/M

Output /M

$1.84/M

Cache read /M

$0.08/M

TTFT

2s

Throughput

12 tps

GLM 5.2

FP4

z-ai/glm-5.2:deepinfra

Context

1.0M

Input /M

$0.59/M

Output /M

$1.89/M

Cache read /M

$0.11/M

TTFT

1s

Throughput

60 tps

GLM 5.2 (Thinking)

FP4

z-ai/glm-5.2:thinking:deepinfra

Context

1.0M

Input /M

$0.59/M

Output /M

$1.89/M

Cache read /M

$0.11/M

TTFT

1s

Throughput

60 tps

GLM 5.3

FP4

z-ai/glm-5.3:deepinfra

Context

1.0M

Input /M

$0.59/M

Output /M

$2.63/M

Cache read /M

$0.13/M

TTFT

46.2s

Throughput

2.5 tps

GLM 5.3 (Thinking)

FP4

z-ai/glm-5.3:thinking:deepinfra

Context

1.0M

Input /M

$0.59/M

Output /M

$2.63/M

Cache read /M

$0.13/M

TTFT

46.2s

Throughput

2.5 tps

GLM 5.3 Flash

FP4

z-ai/glm-5.3-flash:deepinfra

Context

1.0M

Input /M

$0.08/M

Output /M

$0.26/M

Cache read /M

$0.02/M

TTFT

1.9s

Throughput

29 tps

GPT OSS 120B

BF16

openai/gpt-oss-120b:deepinfra

Context

131k

Input /M

$0.04/M

Output /M

$0.18/M

Cache read /M

N/A

TTFT

0.3s

Throughput

56 tps

GPT OSS 20B

BF16

openai/gpt-oss-20b:deepinfra

Context

131k

Input /M

$0.03/M

Output /M

$0.15/M

Cache read /M

N/A

TTFT

0.3s

Throughput

98 tps

Granite 4.2 8B

BF16

ibm-granite/granite-4.2-8b:deepinfra

Context

131k

Input /M

$0.06/M

Output /M

$0.26/M

Cache read /M

$0.02/M

TTFT

0.4s

Throughput

138 tps

Hermes 3 70B

FP8

nousresearch/hermes-3-llama-3.1-70b:deepinfra

Context

131k

Input /M

$0.73/M

Output /M

$0.73/M

Cache read /M

N/A

TTFT

0.9s

Throughput

28 tps

Inkling

FP8

thinkingmachines/inkling:deepinfra

Context

524k

Input /M

$1.00/M

Output /M

$4.25/M

Cache read /M

$0.17/M

TTFT

0.7s

Throughput

65 tps

Inkling Small

FP8

thinkingmachines/Inkling-Small:deepinfra

Context

524k

Input /M

$0.47/M

Output /M

$1.26/M

Cache read /M

$0.10/M

TTFT

0.6s

Throughput

146 tps

Inkling Small Thinking

FP8

thinkingmachines/Inkling-Small:thinking:deepinfra

Context

524k

Input /M

$0.47/M

Output /M

$1.26/M

Cache read /M

$0.10/M

TTFT

0.6s

Throughput

146 tps

Inkling Thinking

FP8

thinkingmachines/inkling:thinking:deepinfra

Context

524k

Input /M

$1.00/M

Output /M

$4.25/M

Cache read /M

$0.17/M

TTFT

0.7s

Throughput

65 tps

Kimi K2.6

FP4

moonshotai/kimi-k2.6:deepinfra

Context

262k

Input /M

$0.79/M

Output /M

$3.68/M

Cache read /M

$0.16/M

TTFT

2s

Throughput

11 tps

Kimi K3

MXFP4

moonshotai/kimi-k3:deepinfra

Context

1.0M

Input /M

$2.99/M

Output /M

$14.96/M

Cache read /M

$0.30/M

TTFT

1.3s

Throughput

27 tps

Llama 3.1 8B

FP8

meta-llama/llama-3.1-8b-instruct:deepinfra

Context

131k

Input /M

$0.02/M

Output /M

$0.04/M

Cache read /M

N/A

TTFT

0.5s

Throughput

16 tps

Llama 3.3 70B Instruct

FP8

meta-llama/llama-3.3-70b-instruct:deepinfra

Context

131k

Input /M

$0.10/M

Output /M

$0.34/M

Cache read /M

N/A

TTFT

0.5s

Throughput

13 tps

MiMo V2.6 Flash

FP8

xiaomi/mimo-v2.6-flash:deepinfra

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.0029/M

TTFT

N/A

Throughput

N/A

MiMo V2.6 Pro

FP8

xiaomi/mimo-v2.6-pro:deepinfra

Context

1.0M

Input /M

$0.45/M

Output /M

$0.91/M

Cache read /M

$0.0038/M

TTFT

1.2s

Throughput

30 tps

MiniMax M3

FP8

minimax/minimax-m3:deepinfra

Context

524k

Input /M

$0.29/M

Output /M

$1.16/M

Cache read /M

$0.06/M

TTFT

0.9s

Throughput

24 tps

MiniMax M3 Thinking

FP8

minimax/minimax-m3:thinking:deepinfra

Context

524k

Input /M

$0.29/M

Output /M

$1.16/M

Cache read /M

$0.06/M

TTFT

0.9s

Throughput

24 tps

Mistral Small 3 24B (2501)

FP8

mistralai/mistral-small-24b-instruct-2501:deepinfra

Context

33k

Input /M

$0.05/M

Output /M

$0.08/M

Cache read /M

N/A

TTFT

0.4s

Throughput

51 tps

Nemotron 3.5 Content Safety

BF16

nvidia/nemotron-3.5-content-safety:deepinfra

Context

131k

Input /M

$0.21/M

Output /M

$0.21/M

Cache read /M

N/A

TTFT

0.3s

Throughput

199.5 tps

Nvidia Nemotron 3 Super 120B

BF16

nvidia/nemotron-3-super-120b-a12b:deepinfra

Context

262k

Input /M

$0.09/M

Output /M

$0.42/M

Cache read /M

N/A

TTFT

0.8s

Throughput

80 tps

Nvidia Nemotron 3 Super 120B Thinking

BF16

nvidia/nemotron-3-super-120b-a12b:thinking:deepinfra

Context

262k

Input /M

$0.09/M

Output /M

$0.42/M

Cache read /M

N/A

TTFT

0.8s

Throughput

80 tps

Nvidia Nemotron 3 Ultra 550B

nvidia/nemotron-3-ultra-550b-a55b:deepinfra

Context

262k

Input /M

$0.53/M

Output /M

$2.31/M

Cache read /M

$0.11/M

TTFT

N/A

Throughput

N/A

Nvidia Nemotron 3 Ultra 550B Thinking

nvidia/nemotron-3-ultra-550b-a55b:thinking:deepinfra

Context

262k

Input /M

$0.53/M

Output /M

$2.31/M

Cache read /M

$0.11/M

TTFT

N/A

Throughput

N/A

Nvidia Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightning:deepinfra

Context

262k

Input /M

$0.06/M

Output /M

$0.17/M

Cache read /M

$0.03/M

TTFT

N/A

Throughput

N/A

Nvidia Nemotron 3.5 Lightning Thinking

nvidia/nemotron-3.5-lightning:thinking:deepinfra

Context

262k

Input /M

$0.06/M

Output /M

$0.17/M

Cache read /M

$0.03/M

TTFT

N/A

Throughput

N/A

Qwen 2.5 72B Instruct

FP8

qwen/qwen-2.5-72b-instruct:deepinfra

Context

33k

Input /M

$0.38/M

Output /M

$0.42/M

Cache read /M

N/A

TTFT

0.4s

Throughput

33 tps

Qwen 3.6 27B

FP8

alibaba/qwen3.6-27b:deepinfra

Context

262k

Input /M

$0.34/M

Output /M

$3.36/M

Cache read /M

N/A

TTFT

0.4s

Throughput

74 tps

Qwen 3.6 27B Thinking

FP8

alibaba/qwen3.6-27b:thinking:deepinfra

Context

262k

Input /M

$0.34/M

Output /M

$3.36/M

Cache read /M

N/A

TTFT

0.4s

Throughput

74 tps

Qwen 3.6 35B A3B

FP8

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

Context

262k

Input /M

$0.10/M

Output /M

$1.00/M

Cache read /M

$0.10/M

TTFT

1.3s

Throughput

34 tps

Qwen 3.6 35B A3B Thinking

FP8

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

Context

262k

Input /M

$0.10/M

Output /M

$1.00/M

Cache read /M

$0.10/M

TTFT

1.3s

Throughput

34 tps

Qwen3 14B

FP8

qwen/qwen3-14b:deepinfra

Context

41k

Input /M

$0.13/M

Output /M

$0.25/M

Cache read /M

N/A

TTFT

0.9s

Throughput

62 tps

Qwen3 235B A22B

FP8

qwen/qwen3-235b-a22b:deepinfra

Context

262k

Input /M

$0.09/M

Output /M

$0.58/M

Cache read /M

N/A

TTFT

0.5s

Throughput

14 tps

Qwen3 32B

FP8

qwen/qwen3-32b:deepinfra

Context

41k

Input /M

$0.08/M

Output /M

$0.29/M

Cache read /M

N/A

TTFT

0.4s

Throughput

28 tps

Qwen3 Next 80B A3B Instruct

FP8

Qwen/Qwen3-Next-80B-A3B-Instruct:deepinfra

Context

262k

Input /M

$0.09/M

Output /M

$1.16/M

Cache read /M

N/A

TTFT

0.5s

Throughput

119 tps

Qwen3.5 27B

FP8

qwen3.5-27b:deepinfra

Context

262k

Input /M

$0.27/M

Output /M

$2.73/M

Cache read /M

N/A

TTFT

0.3s

Throughput

74.5 tps

Qwen3.5 27B Thinking

FP8

qwen3.5-27b:thinking:deepinfra

Context

262k

Input /M

$0.27/M

Output /M

$2.73/M

Cache read /M

N/A

TTFT

0.3s

Throughput

74.5 tps

Qwen3.5 35B A3B

FP8

qwen3.5-35b-a3b:deepinfra

Context

262k

Input /M

$0.15/M

Output /M

$1.05/M

Cache read /M

$0.05/M

TTFT

0.4s

Throughput

80 tps

Qwen3.5 35B A3B Thinking

FP8

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

Context

262k

Input /M

$0.15/M

Output /M

$1.05/M

Cache read /M

$0.05/M

TTFT

0.4s

Throughput

80 tps

Qwen3.5 397B

FP8

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

Context

262k

Input /M

$0.47/M

Output /M

$3.15/M

Cache read /M

$0.23/M

TTFT

0.8s

Throughput

26 tps

Qwen3.5 397B Thinking

FP8

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

Context

262k

Input /M

$0.47/M

Output /M

$3.15/M

Cache read /M

$0.23/M

TTFT

0.8s

Throughput

26 tps

Qwen3.5 9B

BF16

qwen/qwen3.5-9b:deepinfra

Context

262k

Input /M

$0.10/M

Output /M

$0.16/M

Cache read /M

N/A

TTFT

1.2s

Throughput

6 tps

Qwen3.8 27B

BF16

qwen3.8-27b:deepinfra

Context

262k

Input /M

$0.16/M

Output /M

$1.97/M

Cache read /M

$0.04/M

TTFT

46.5s

Throughput

3 tps

Qwen3.8 27B Thinking

BF16

qwen3.8-27b:thinking:deepinfra

Context

262k

Input /M

$0.16/M

Output /M

$1.97/M

Cache read /M

$0.04/M

TTFT

46.5s

Throughput

3 tps

Tencent Hy4 Preview

FP8

tencent/hy4-preview:deepinfra

Context

1.0M

Input /M

$0.88/M

Output /M

$2.63/M

Cache read /M

$0.04/M

TTFT

3.1s

Throughput

9 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 DeepInfra via the API

Call a model served by DeepInfra 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:deepinfra",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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