DeepInfra

73 models available

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

73 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek R1-0528 FP4	164k	$0.53/M	$2.26/M	$0.37/M	60.6%	0.7s	23 tps
DeepSeek V3.1 FP4	164k	$0.26/M	$1.00/M	$0.14/M	27.6%	0.7s	10 tps
DeepSeek V3.2 FP4	164k	$0.27/M	$0.40/M	$0.14/M	73.8%	1.8s	12 tps
DeepSeek V3.2 (Thinking) FP4	164k	$0.27/M	$0.40/M	$0.14/M	73.8%	1.8s	12 tps
DeepSeek V4 Flash FP8	1.0M	$0.09/M	$0.19/M	$0.02/M	58.9%	1.2s	33 tps
DeepSeek V4 Flash (Thinking) FP8	1.0M	$0.09/M	$0.19/M	$0.02/M	58.9%	1.2s	33 tps
DeepSeek V4 Flash 0731 FP8	1.0M	$0.06/M	$0.19/M	$0.02/M	81.3%	0.8s	38 tps
DeepSeek V4 Flash 0731 (Thinking) FP8	1.0M	$0.06/M	$0.19/M	$0.02/M	81.3%	0.8s	38 tps
DeepSeek V4 Flash Vision Exp FP8	1.0M	$0.23/M	$0.68/M	$0.0072/M	6.6%	1.4s	85 tps
DeepSeek V4 Pro FP8	1.0M	$1.36/M	$2.73/M	$0.10/M	3.1%	1.4s	42 tps
DeepSeek V4 Pro (Thinking) FP8	1.0M	$1.36/M	$2.73/M	$0.10/M	0%	1.4s	42 tps
DeepSeek V4 Pro 0813 FP8	1.0M	$1.36/M	$2.73/M	$0.10/M	N/A	6.5s	23 tps
DeepSeek V4 Pro 0813 (Thinking) FP8	1.0M	$1.36/M	$2.73/M	$0.10/M	N/A	6.5s	23 tps
DeepSeek V4.1 Flash FP8	1.0M	$0.15/M	$0.44/M	$0.0044/M	37.1%	1.1s	44 tps
DeepSeek V4.1 Flash (Thinking) FP8	1.0M	$0.15/M	$0.44/M	$0.0044/M	37.1%	1.1s	44 tps
Gemma 4 26B A4B FP8	262k	$0.07/M	$0.36/M	$0.01/M	0%	0.3s	48 tps
Gemma 4 31B FP8	262k	$0.21/M	$0.42/M	$0.02/M	0%	1.3s	20 tps
GLM 4.6 FP4	203k	$0.53/M	$2.10/M	$0.10/M	24.6%	0.7s	21 tps
GLM 4.6 (Thinking) FP4	203k	$0.53/M	$2.10/M	$0.10/M	0%	0.7s	21 tps
GLM 4.7 FP4	203k	$0.42/M	$1.84/M	$0.08/M	32.2%	2.1s	12 tps
GLM 4.7 (Thinking) FP4	203k	$0.42/M	$1.84/M	$0.08/M	40.6%	2.1s	12 tps
GLM 5.2 FP4	1.0M	$0.59/M	$1.89/M	$0.11/M	79.8%	0.9s	79 tps
GLM 5.2 (Thinking) FP4	1.0M	$0.59/M	$1.89/M	$0.11/M	79.8%	0.9s	79 tps
GLM 5.3 FP4	1.0M	$0.59/M	$2.63/M	$0.13/M	N/A	1.6s	46 tps
GLM 5.3 (Thinking) FP4	1.0M	$0.59/M	$2.63/M	$0.13/M	N/A	1.6s	46 tps
GLM 5.3 Flash FP4	1.0M	$0.08/M	$0.26/M	$0.02/M	79.6%	1.4s	37 tps
GPT OSS 120B BF16	128k	$0.16/M	$0.63/M	N/A	0%	0.4s	113 tps
GPT OSS 20B BF16	131k	$0.03/M	$0.15/M	N/A	N/A	0.3s	107 tps
Granite 4.2 8B BF16	131k	$0.06/M	$0.26/M	$0.02/M	N/A	0.2s	80 tps
Hermes 3 70B FP8	131k	$0.73/M	$0.73/M	N/A	0%	0.7s	28 tps
Inkling FP8	524k	$1.00/M	$4.25/M	$0.17/M	86%	0.6s	123.5 tps
Inkling Small FP8	524k	$0.47/M	$1.26/M	$0.10/M	0%	0.7s	131 tps
Inkling Small Thinking FP8	524k	$0.47/M	$1.26/M	$0.10/M	0%	0.7s	131 tps
Inkling Thinking FP8	524k	$1.00/M	$4.25/M	$0.17/M	86%	0.6s	123.5 tps
Kimi K2.6 FP4	262k	$0.79/M	$3.68/M	$0.16/M	N/A	1.3s	19 tps
Kimi K3 MXFP4	1.0M	$2.99/M	$14.96/M	$0.30/M	N/A	1.4s	36 tps
Llama 3.1 8B FP8	131k	$0.02/M	$0.04/M	N/A	0%	0.6s	33 tps
Llama 3.3 70B Instruct FP8	131k	$0.10/M	$0.34/M	N/A	0%	0.5s	17 tps
MiMo V2.5 Pro FP8	1.0M	$1.05/M	$3.15/M	$0.21/M	17.8%	3s	27.4 tps
MiMo V2.5 Pro Thinking FP8	1.0M	$1.05/M	$3.15/M	$0.21/M	17.8%	3s	27.4 tps
MiMo V2.6 Flash FP8	1.0M	$0.15/M	$0.29/M	$0.0029/M	18.7%	1.9s	42 tps
MiMo V2.6 Pro FP8	1.0M	$0.45/M	$0.91/M	$0.0038/M	66%	1.7s	40 tps
MiniMax M3 FP8	524k	$0.29/M	$1.16/M	$0.06/M	N/A	1.4s	13 tps
MiniMax M3 Thinking FP8	524k	$0.29/M	$1.16/M	$0.06/M	N/A	1.4s	13 tps
Mistral Small 3 24B (2501) FP8	33k	$0.05/M	$0.08/M	N/A	N/A	0.5s	42 tps
Nemotron 3.5 Content Safety BF16	131k	$0.21/M	$0.21/M	N/A	N/A	0.2s	154.5 tps
Nvidia Nemotron 3 Super 120B BF16	262k	$0.09/M	$0.42/M	N/A	0%	3.1s	46 tps
Nvidia Nemotron 3 Super 120B Thinking BF16	262k	$0.09/M	$0.42/M	N/A	0%	3.1s	46 tps
Nvidia Nemotron 3 Ultra 550B	262k	$0.53/M	$2.31/M	$0.11/M	0%	10.5s	131 tps
Nvidia Nemotron 3 Ultra 550B Thinking	262k	$0.53/M	$2.31/M	$0.11/M	0%	2.3s	60.5 tps
Nvidia Nemotron 3.5 Lightning	262k	$0.06/M	$0.17/M	$0.03/M	16.7%	0.6s	425.6 tps
Nvidia Nemotron 3.5 Lightning Thinking	262k	$0.06/M	$0.17/M	$0.03/M	0%	2.8s	226.5 tps
Qwen 2.5 72B Instruct FP8	33k	$0.38/M	$0.42/M	N/A	N/A	0.4s	22 tps
Qwen 3.6 27B FP8	262k	$0.34/M	$3.36/M	N/A	N/A	0.8s	49 tps
Qwen 3.6 27B Thinking FP8	262k	$0.34/M	$3.36/M	N/A	N/A	0.8s	49 tps
Qwen 3.6 35B A3B FP8	262k	$0.10/M	$1.00/M	$0.10/M	N/A	0.7s	10 tps
Qwen 3.6 35B A3B Thinking FP8	262k	$0.10/M	$1.00/M	$0.10/M	N/A	0.7s	10 tps
Qwen3 14B FP8	41k	$0.13/M	$0.25/M	N/A	N/A	0.8s	42 tps
Qwen3 235B A22B FP8	262k	$0.09/M	$0.58/M	N/A	0%	0.5s	13 tps
Qwen3 32B FP8	41k	$0.08/M	$0.29/M	N/A	0%	0.3s	29 tps
Qwen3 Next 80B A3B Instruct FP8	262k	$0.09/M	$1.16/M	N/A	0%	0.5s	64 tps
Qwen3.5 27B FP8	262k	$0.27/M	$2.73/M	N/A	N/A	0.6s	46 tps
Qwen3.5 27B Thinking FP8	262k	$0.27/M	$2.73/M	N/A	N/A	0.6s	46 tps
Qwen3.5 35B A3B FP8	262k	$0.15/M	$1.05/M	$0.05/M	N/A	0.6s	66 tps
Qwen3.5 35B A3B Thinking FP8	262k	$0.15/M	$1.05/M	$0.05/M	N/A	0.6s	66 tps
Qwen3.5 397B FP8	262k	$0.47/M	$3.15/M	$0.23/M	N/A	1.2s	40 tps
Qwen3.5 397B Thinking FP8	262k	$0.47/M	$3.15/M	$0.23/M	N/A	1.2s	40 tps
Qwen3.5 9B BF16	262k	$0.10/M	$0.16/M	N/A	0%	0.7s	13 tps
Qwen3.8 27B BF16	262k	$0.16/M	$1.97/M	$0.04/M	N/A	0.4s	46 tps
Qwen3.8 27B Thinking BF16	262k	$0.16/M	$1.97/M	$0.04/M	N/A	0.4s	46 tps
Qwen3.8 Max FP4	262k	$2.10/M	$6.30/M	$0.21/M	N/A	7.7s	26 tps
Qwen3.8 Max Thinking FP4	262k	$2.10/M	$6.30/M	$0.21/M	57%	7.7s	26 tps
Tencent Hy4 Preview FP8	1.0M	$0.88/M	$2.63/M	$0.04/M	N/A	3.8s	34 tps

DeepSeek R1-0528

FP4

Context: 164k
Input /M: $0.53/M
Output /M: $2.26/M
Cache read /M: $0.37/M
Cache hit: 60.6%
TTFT: 0.7s
Throughput: 23 tps

DeepSeek V3.1

FP4

Context: 164k
Input /M: $0.26/M
Output /M: $1.00/M
Cache read /M: $0.14/M
Cache hit: 27.6%
TTFT: 0.7s
Throughput: 10 tps

DeepSeek V3.2

FP4

Context: 164k
Input /M: $0.27/M
Output /M: $0.40/M
Cache read /M: $0.14/M
Cache hit: 73.8%
TTFT: 1.8s
Throughput: 12 tps

DeepSeek V3.2 (Thinking)

FP4

Context: 164k
Input /M: $0.27/M
Output /M: $0.40/M
Cache read /M: $0.14/M
Cache hit: 73.8%
TTFT: 1.8s
Throughput: 12 tps

DeepSeek V4 Flash

FP8

Context: 1.0M
Input /M: $0.09/M
Output /M: $0.19/M
Cache read /M: $0.02/M
Cache hit: 58.9%
TTFT: 1.2s
Throughput: 33 tps

DeepSeek V4 Flash (Thinking)

FP8

Context: 1.0M
Input /M: $0.09/M
Output /M: $0.19/M
Cache read /M: $0.02/M
Cache hit: 58.9%
TTFT: 1.2s
Throughput: 33 tps

DeepSeek V4 Flash 0731

FP8

Context: 1.0M
Input /M: $0.06/M
Output /M: $0.19/M
Cache read /M: $0.02/M
Cache hit: 81.3%
TTFT: 0.8s
Throughput: 38 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

Context: 1.0M
Input /M: $0.06/M
Output /M: $0.19/M
Cache read /M: $0.02/M
Cache hit: 81.3%
TTFT: 0.8s
Throughput: 38 tps

DeepSeek V4 Flash Vision Exp

FP8

Context: 1.0M
Input /M: $0.23/M
Output /M: $0.68/M
Cache read /M: $0.0072/M
Cache hit: 6.6%
TTFT: 1.4s
Throughput: 85 tps

DeepSeek V4 Pro

FP8

Context: 1.0M
Input /M: $1.36/M
Output /M: $2.73/M
Cache read /M: $0.10/M
Cache hit: 3.1%
TTFT: 1.4s
Throughput: 42 tps

DeepSeek V4 Pro (Thinking)

FP8

Context: 1.0M
Input /M: $1.36/M
Output /M: $2.73/M
Cache read /M: $0.10/M
Cache hit: 0%
TTFT: 1.4s
Throughput: 42 tps

DeepSeek V4 Pro 0813

FP8

Context: 1.0M
Input /M: $1.36/M
Output /M: $2.73/M
Cache read /M: $0.10/M
Cache hit: N/A
TTFT: 6.5s
Throughput: 23 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

Context: 1.0M
Input /M: $1.36/M
Output /M: $2.73/M
Cache read /M: $0.10/M
Cache hit: N/A
TTFT: 6.5s
Throughput: 23 tps

DeepSeek V4.1 Flash

FP8

Context: 1.0M
Input /M: $0.15/M
Output /M: $0.44/M
Cache read /M: $0.0044/M
Cache hit: 37.1%
TTFT: 1.1s
Throughput: 44 tps

DeepSeek V4.1 Flash (Thinking)

FP8

Context: 1.0M
Input /M: $0.15/M
Output /M: $0.44/M
Cache read /M: $0.0044/M
Cache hit: 37.1%
TTFT: 1.1s
Throughput: 44 tps

Gemma 4 26B A4B

FP8

Context: 262k
Input /M: $0.07/M
Output /M: $0.36/M
Cache read /M: $0.01/M
Cache hit: 0%
TTFT: 0.3s
Throughput: 48 tps

Gemma 4 31B

FP8

Context: 262k
Input /M: $0.21/M
Output /M: $0.42/M
Cache read /M: $0.02/M
Cache hit: 0%
TTFT: 1.3s
Throughput: 20 tps

GLM 4.6

FP4

Context: 203k
Input /M: $0.53/M
Output /M: $2.10/M
Cache read /M: $0.10/M
Cache hit: 24.6%
TTFT: 0.7s
Throughput: 21 tps

GLM 4.6 (Thinking)

FP4

Context: 203k
Input /M: $0.53/M
Output /M: $2.10/M
Cache read /M: $0.10/M
Cache hit: 0%
TTFT: 0.7s
Throughput: 21 tps

GLM 4.7

FP4

Context: 203k
Input /M: $0.42/M
Output /M: $1.84/M
Cache read /M: $0.08/M
Cache hit: 32.2%
TTFT: 2.1s
Throughput: 12 tps

GLM 4.7 (Thinking)

FP4

Context: 203k
Input /M: $0.42/M
Output /M: $1.84/M
Cache read /M: $0.08/M
Cache hit: 40.6%
TTFT: 2.1s
Throughput: 12 tps

GLM 5.2

FP4

Context: 1.0M
Input /M: $0.59/M
Output /M: $1.89/M
Cache read /M: $0.11/M
Cache hit: 79.8%
TTFT: 0.9s
Throughput: 79 tps

GLM 5.2 (Thinking)

FP4

Context: 1.0M
Input /M: $0.59/M
Output /M: $1.89/M
Cache read /M: $0.11/M
Cache hit: 79.8%
TTFT: 0.9s
Throughput: 79 tps

GLM 5.3

FP4

Context: 1.0M
Input /M: $0.59/M
Output /M: $2.63/M
Cache read /M: $0.13/M
Cache hit: N/A
TTFT: 1.6s
Throughput: 46 tps

GLM 5.3 (Thinking)

FP4

Context: 1.0M
Input /M: $0.59/M
Output /M: $2.63/M
Cache read /M: $0.13/M
Cache hit: N/A
TTFT: 1.6s
Throughput: 46 tps

GLM 5.3 Flash

FP4

Context: 1.0M
Input /M: $0.08/M
Output /M: $0.26/M
Cache read /M: $0.02/M
Cache hit: 79.6%
TTFT: 1.4s
Throughput: 37 tps

GPT OSS 120B

BF16

Context: 128k
Input /M: $0.16/M
Output /M: $0.63/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.4s
Throughput: 113 tps

GPT OSS 20B

BF16

Context: 131k
Input /M: $0.03/M
Output /M: $0.15/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.3s
Throughput: 107 tps

Granite 4.2 8B

BF16

Context: 131k
Input /M: $0.06/M
Output /M: $0.26/M
Cache read /M: $0.02/M
Cache hit: N/A
TTFT: 0.2s
Throughput: 80 tps

Hermes 3 70B

FP8

Context: 131k
Input /M: $0.73/M
Output /M: $0.73/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.7s
Throughput: 28 tps

Inkling

FP8

Context: 524k
Input /M: $1.00/M
Output /M: $4.25/M
Cache read /M: $0.17/M
Cache hit: 86%
TTFT: 0.6s
Throughput: 123.5 tps

Inkling Small

FP8

Context: 524k
Input /M: $0.47/M
Output /M: $1.26/M
Cache read /M: $0.10/M
Cache hit: 0%
TTFT: 0.7s
Throughput: 131 tps

Inkling Small Thinking

FP8

Context: 524k
Input /M: $0.47/M
Output /M: $1.26/M
Cache read /M: $0.10/M
Cache hit: 0%
TTFT: 0.7s
Throughput: 131 tps

Inkling Thinking

FP8

Context: 524k
Input /M: $1.00/M
Output /M: $4.25/M
Cache read /M: $0.17/M
Cache hit: 86%
TTFT: 0.6s
Throughput: 123.5 tps

Kimi K2.6

FP4

Context: 262k
Input /M: $0.79/M
Output /M: $3.68/M
Cache read /M: $0.16/M
Cache hit: N/A
TTFT: 1.3s
Throughput: 19 tps

Kimi K3

MXFP4

Context: 1.0M
Input /M: $2.99/M
Output /M: $14.96/M
Cache read /M: $0.30/M
Cache hit: N/A
TTFT: 1.4s
Throughput: 36 tps

Llama 3.1 8B

FP8

Context: 131k
Input /M: $0.02/M
Output /M: $0.04/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.6s
Throughput: 33 tps

Llama 3.3 70B Instruct

FP8

Context: 131k
Input /M: $0.10/M
Output /M: $0.34/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.5s
Throughput: 17 tps

MiMo V2.5 Pro

FP8

Context: 1.0M
Input /M: $1.05/M
Output /M: $3.15/M
Cache read /M: $0.21/M
Cache hit: 17.8%
TTFT: 3s
Throughput: 27.4 tps

MiMo V2.5 Pro Thinking

FP8

Context: 1.0M
Input /M: $1.05/M
Output /M: $3.15/M
Cache read /M: $0.21/M
Cache hit: 17.8%
TTFT: 3s
Throughput: 27.4 tps

MiMo V2.6 Flash

FP8

Context: 1.0M
Input /M: $0.15/M
Output /M: $0.29/M
Cache read /M: $0.0029/M
Cache hit: 18.7%
TTFT: 1.9s
Throughput: 42 tps

MiMo V2.6 Pro

FP8

Context: 1.0M
Input /M: $0.45/M
Output /M: $0.91/M
Cache read /M: $0.0038/M
Cache hit: 66%
TTFT: 1.7s
Throughput: 40 tps

MiniMax M3

FP8

Context: 524k
Input /M: $0.29/M
Output /M: $1.16/M
Cache read /M: $0.06/M
Cache hit: N/A
TTFT: 1.4s
Throughput: 13 tps

MiniMax M3 Thinking

FP8

Context: 524k
Input /M: $0.29/M
Output /M: $1.16/M
Cache read /M: $0.06/M
Cache hit: N/A
TTFT: 1.4s
Throughput: 13 tps

Mistral Small 3 24B (2501)

FP8

Context: 33k
Input /M: $0.05/M
Output /M: $0.08/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.5s
Throughput: 42 tps

Nemotron 3.5 Content Safety

BF16

Context: 131k
Input /M: $0.21/M
Output /M: $0.21/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.2s
Throughput: 154.5 tps

Nvidia Nemotron 3 Super 120B

BF16

Context: 262k
Input /M: $0.09/M
Output /M: $0.42/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 3.1s
Throughput: 46 tps

Nvidia Nemotron 3 Super 120B Thinking

BF16

Context: 262k
Input /M: $0.09/M
Output /M: $0.42/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 3.1s
Throughput: 46 tps

Nvidia Nemotron 3 Ultra 550B

Context: 262k
Input /M: $0.53/M
Output /M: $2.31/M
Cache read /M: $0.11/M
Cache hit: 0%
TTFT: 10.5s
Throughput: 131 tps

Nvidia Nemotron 3 Ultra 550B Thinking

Context: 262k
Input /M: $0.53/M
Output /M: $2.31/M
Cache read /M: $0.11/M
Cache hit: 0%
TTFT: 2.3s
Throughput: 60.5 tps

Nvidia Nemotron 3.5 Lightning

Context: 262k
Input /M: $0.06/M
Output /M: $0.17/M
Cache read /M: $0.03/M
Cache hit: 16.7%
TTFT: 0.6s
Throughput: 425.6 tps

Nvidia Nemotron 3.5 Lightning Thinking

Context: 262k
Input /M: $0.06/M
Output /M: $0.17/M
Cache read /M: $0.03/M
Cache hit: 0%
TTFT: 2.8s
Throughput: 226.5 tps

Qwen 2.5 72B Instruct

FP8

Context: 33k
Input /M: $0.38/M
Output /M: $0.42/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.4s
Throughput: 22 tps

Qwen 3.6 27B

FP8

Context: 262k
Input /M: $0.34/M
Output /M: $3.36/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.8s
Throughput: 49 tps

Qwen 3.6 27B Thinking

FP8

Context: 262k
Input /M: $0.34/M
Output /M: $3.36/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.8s
Throughput: 49 tps

Qwen 3.6 35B A3B

FP8

Context: 262k
Input /M: $0.10/M
Output /M: $1.00/M
Cache read /M: $0.10/M
Cache hit: N/A
TTFT: 0.7s
Throughput: 10 tps

Qwen 3.6 35B A3B Thinking

FP8

Context: 262k
Input /M: $0.10/M
Output /M: $1.00/M
Cache read /M: $0.10/M
Cache hit: N/A
TTFT: 0.7s
Throughput: 10 tps

Qwen3 14B

FP8

Context: 41k
Input /M: $0.13/M
Output /M: $0.25/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.8s
Throughput: 42 tps

Qwen3 235B A22B

FP8

Context: 262k
Input /M: $0.09/M
Output /M: $0.58/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.5s
Throughput: 13 tps

Qwen3 32B

FP8

Context: 41k
Input /M: $0.08/M
Output /M: $0.29/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.3s
Throughput: 29 tps

Qwen3 Next 80B A3B Instruct

FP8

Context: 262k
Input /M: $0.09/M
Output /M: $1.16/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.5s
Throughput: 64 tps

Qwen3.5 27B

FP8

Context: 262k
Input /M: $0.27/M
Output /M: $2.73/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.6s
Throughput: 46 tps

Qwen3.5 27B Thinking

FP8

Context: 262k
Input /M: $0.27/M
Output /M: $2.73/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.6s
Throughput: 46 tps

Qwen3.5 35B A3B

FP8

Context: 262k
Input /M: $0.15/M
Output /M: $1.05/M
Cache read /M: $0.05/M
Cache hit: N/A
TTFT: 0.6s
Throughput: 66 tps

Qwen3.5 35B A3B Thinking

FP8

Context: 262k
Input /M: $0.15/M
Output /M: $1.05/M
Cache read /M: $0.05/M
Cache hit: N/A
TTFT: 0.6s
Throughput: 66 tps

Qwen3.5 397B

FP8

Context: 262k
Input /M: $0.47/M
Output /M: $3.15/M
Cache read /M: $0.23/M
Cache hit: N/A
TTFT: 1.2s
Throughput: 40 tps

Qwen3.5 397B Thinking

FP8

Context: 262k
Input /M: $0.47/M
Output /M: $3.15/M
Cache read /M: $0.23/M
Cache hit: N/A
TTFT: 1.2s
Throughput: 40 tps

Qwen3.5 9B

BF16

Context: 262k
Input /M: $0.10/M
Output /M: $0.16/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.7s
Throughput: 13 tps

Qwen3.8 27B

BF16

Context: 262k
Input /M: $0.16/M
Output /M: $1.97/M
Cache read /M: $0.04/M
Cache hit: N/A
TTFT: 0.4s
Throughput: 46 tps

Qwen3.8 27B Thinking

BF16

Context: 262k
Input /M: $0.16/M
Output /M: $1.97/M
Cache read /M: $0.04/M
Cache hit: N/A
TTFT: 0.4s
Throughput: 46 tps

Qwen3.8 Max

FP4

Context: 262k
Input /M: $2.10/M
Output /M: $6.30/M
Cache read /M: $0.21/M
Cache hit: N/A
TTFT: 7.7s
Throughput: 26 tps

Qwen3.8 Max Thinking

FP4

Context: 262k
Input /M: $2.10/M
Output /M: $6.30/M
Cache read /M: $0.21/M
Cache hit: 57%
TTFT: 7.7s
Throughput: 26 tps

Tencent Hy4 Preview

FP8

Context: 1.0M
Input /M: $0.88/M
Output /M: $2.63/M
Cache read /M: $0.04/M
Cache hit: N/A
TTFT: 3.8s
Throughput: 34 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

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.

DeepInfra terms of use DeepInfra privacy policy