DeepInfra

75 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

75 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
Clef	66k	$0.252/M	Free	N/A	N/A	0.4s	N/A
Clef Flash	25k	$0.0399/M	Free	N/A	N/A	0.5s	N/A
DeepSeek R1-0528 FP4	164k	$0.525/M	$2.26/M	$0.367/M	40%	0.8s	19 tps
DeepSeek V3.1 FP4	164k	$0.263/M	$0.998/M	$0.136/M	82.5%	0.6s	24 tps
DeepSeek V3.2 FP4	164k	$0.273/M	$0.399/M	$0.136/M	78.3%	0.5s	37 tps
DeepSeek V3.2 (Thinking) FP4	164k	$0.273/M	$0.399/M	$0.136/M	25.3%	0.5s	37 tps
DeepSeek V4 Flash FP8	1.0M	$0.0945/M	$0.189/M	$0.0189/M	54.3%	0.8s	38 tps
DeepSeek V4 Flash (Thinking) FP8	1.0M	$0.0945/M	$0.189/M	$0.0189/M	54.3%	0.8s	38 tps
DeepSeek V4 Flash 0731 FP8	1.0M	$0.063/M	$0.189/M	$0.0158/M	6.5%	0.7s	38 tps
DeepSeek V4 Flash 0731 (Thinking) FP8	1.0M	$0.063/M	$0.189/M	$0.0158/M	6.5%	0.7s	38 tps
DeepSeek V4 Flash Vision Exp FP8	1.0M	$0.226/M	$0.679/M	$0.0072/M	0%	1.8s	15 tps
DeepSeek V4 Pro FP8	1.0M	$1.36/M	$2.73/M	$0.105/M	18.4%	1s	61 tps
DeepSeek V4 Pro (Thinking) FP8	1.0M	$1.36/M	$2.73/M	$0.105/M	18.4%	1s	61 tps
DeepSeek V4 Pro 0813 FP8	1.0M	$1.36/M	$2.73/M	$0.105/M	N/A	1.1s	52 tps
DeepSeek V4 Pro 0813 (Thinking) FP8	1.0M	$1.36/M	$2.73/M	$0.105/M	N/A	1.1s	52 tps
DeepSeek V4.1 Flash FP8	1.0M	$0.147/M	$0.441/M	$0.0044/M	18.6%	0.6s	78 tps
DeepSeek V4.1 Flash (Thinking) FP8	1.0M	$0.147/M	$0.441/M	$0.0044/M	18.6%	0.6s	78 tps
DeepSeek V4.1 Flash 1017 FP8	1.0M	$0.147/M	$0.441/M	$0.0044/M	62.4%	1.1s	51 tps
DeepSeek V4.1 Flash 1017 (Thinking) FP8	1.0M	$0.147/M	$0.441/M	$0.0044/M	23.6%	1.1s	51 tps
Doubao Seed 2.0 Pro	256k	$0.782/M	$3.88/M	N/A	N/A	N/A	N/A
Gemma 4 26B A4B FP8	262k	$0.0735/M	$0.357/M	$0.0105/M	N/A	0.4s	95 tps
Gemma 4 31B FP8	262k	$0.21/M	$0.42/M	$0.021/M	26.2%	0.8s	28 tps
GLM 4.6 FP4	203k	$0.525/M	$2.10/M	$0.105/M	0%	1.2s	22 tps
GLM 4.6 (Thinking) FP4	203k	$0.525/M	$2.10/M	$0.105/M	0%	1.2s	22 tps
GLM 4.7 FP4	203k	$0.42/M	$1.84/M	$0.084/M	30.6%	1.3s	22 tps
GLM 4.7 (Thinking) FP4	203k	$0.42/M	$1.84/M	$0.084/M	0%	1.3s	22 tps
GLM 5.2 FP4	1.0M	$0.591/M	$1.89/M	$0.11/M	7.6%	1.1s	41 tps
GLM 5.2 (Thinking) FP4	1.0M	$0.591/M	$1.89/M	$0.11/M	0%	1.1s	41 tps
GLM 5.3 FP4	1.0M	$0.591/M	$2.63/M	$0.131/M	0.1%	1.1s	69 tps
GLM 5.3 (Thinking) FP4	1.0M	$0.591/M	$2.63/M	$0.131/M	19.9%	1.1s	69 tps
GLM 5.3 Flash FP4	1.0M	$0.157/M	$0.525/M	$0.0315/M	72.8%	2.2s	23 tps
GPT OSS 120B BF16	131k	$0.0389/M	$0.178/M	N/A	N/A	0.5s	33 tps
GPT OSS 20B BF16	131k	$0.0315/M	$0.147/M	N/A	N/A	0.2s	109 tps
Granite 4.2 8B BF16	131k	$0.063/M	$0.263/M	$0.0158/M	N/A	1.5s	14 tps
Hermes 3 70B FP8	131k	$0.735/M	$0.735/M	N/A	0%	0.9s	29 tps
Inkling Small FP8	524k	$0.472/M	$1.26/M	$0.105/M	77.2%	1.2s	101 tps
Inkling Small Thinking FP8	524k	$0.472/M	$1.26/M	$0.105/M	77.2%	1.2s	101 tps
Kimi K2.6 FP4	262k	$0.787/M	$3.68/M	$0.157/M	N/A	1.1s	31 tps
Kimi K3 MXFP4	1.0M	$2.99/M	$14.96/M	$0.299/M	78.3%	1.9s	33 tps
Ling 3.1 Flash FP4	262k	$0.0787/M	$0.236/M	$0.0158/M	N/A	N/A	N/A
Llama 3.1 8B FP8	131k	$0.021/M	$0.042/M	N/A	N/A	0.7s	25 tps
Llama 3.3 70B Instruct FP8	131k	$0.105/M	$0.336/M	N/A	0%	0.7s	11 tps
MiMo V2.6 Flash FP8	1.0M	$0.147/M	$0.294/M	$0.0029/M	21%	47.4s	3 tps
MiMo V2.6 Pro FP8	1.0M	$0.406/M	$0.822/M	$0.0034/M	46%	1.2s	29 tps
MiniMax M3 FP8	524k	$0.294/M	$1.16/M	$0.0588/M	69.7%	0.9s	32 tps
MiniMax M3 Thinking FP8	524k	$0.294/M	$1.16/M	$0.0588/M	33.4%	0.9s	32 tps
Mistral Small 3 24B (2501) FP8	33k	$0.0525/M	$0.084/M	N/A	N/A	0.5s	48 tps
Nemotron 3.5 Content Safety BF16	131k	$0.21/M	$0.21/M	N/A	N/A	0.4s	171.5 tps
Nvidia Nemotron 3 Super 120B BF16	262k	$0.0892/M	$0.42/M	N/A	0%	1.2s	64.5 tps
Nvidia Nemotron 3 Super 120B Thinking BF16	262k	$0.0892/M	$0.42/M	N/A	0%	1.2s	64.5 tps
Nvidia Nemotron 3 Ultra 550B	262k	$0.525/M	$2.31/M	$0.105/M	0%	6.2s	63.2 tps
Nvidia Nemotron 3 Ultra 550B Thinking	262k	$0.525/M	$2.31/M	$0.105/M	46.9%	1.9s	64.4 tps
Nvidia Nemotron 3.5 Lightning	262k	$0.063/M	$0.168/M	$0.0315/M	0%	0.9s	111.6 tps
Nvidia Nemotron 3.5 Lightning Thinking	262k	$0.063/M	$0.168/M	$0.0315/M	0%	1.6s	144.9 tps
Nvidia Nemotron 3.5 Super VL FP4	262k	$0.157/M	$0.525/M	$0.021/M	17%	7.7s	798.3 tps
Qwen 2.5 72B Instruct FP8	33k	$0.378/M	$0.42/M	N/A	N/A	0.7s	18 tps
Qwen 3.6 27B FP8	262k	$0.336/M	$3.36/M	N/A	N/A	0.4s	60 tps
Qwen 3.6 27B Thinking FP8	262k	$0.336/M	$3.36/M	N/A	N/A	0.4s	60 tps
Qwen 3.6 35B A3B FP8	262k	$0.105/M	$0.998/M	$0.105/M	N/A	1.1s	18 tps
Qwen 3.6 35B A3B Thinking FP8	262k	$0.105/M	$0.998/M	$0.105/M	N/A	1.1s	18 tps
Qwen3 14B FP8	41k	$0.126/M	$0.252/M	N/A	0%	0.3s	90 tps
Qwen3 235B A22B FP8	262k	$0.0945/M	$0.578/M	N/A	0%	0.5s	15 tps
Qwen3 32B FP8	41k	$0.084/M	$0.294/M	N/A	0%	0.5s	24 tps
Qwen3 Next 80B A3B Instruct FP8	262k	$0.0945/M	$1.16/M	N/A	0%	0.5s	31 tps
Qwen3.5 27B FP8	262k	$0.273/M	$2.73/M	N/A	N/A	0.6s	57 tps
Qwen3.5 27B Thinking FP8	262k	$0.273/M	$2.73/M	N/A	N/A	0.6s	57 tps
Qwen3.5 35B A3B FP8	262k	$0.147/M	$1.05/M	$0.0525/M	N/A	0.5s	88 tps
Qwen3.5 35B A3B Thinking FP8	262k	$0.147/M	$1.05/M	$0.0525/M	N/A	0.5s	88 tps
Qwen3.5 397B FP8	262k	$0.472/M	$3.15/M	$0.231/M	0%	0.6s	35 tps
Qwen3.5 397B Thinking FP8	262k	$0.472/M	$3.15/M	$0.231/M	0%	0.6s	35 tps
Qwen3.5 9B BF16	262k	$0.105/M	$0.157/M	N/A	N/A	0.7s	21 tps
Qwen3.8 27B BF16	262k	$0.157/M	$1.97/M	$0.0394/M	N/A	0.9s	53 tps
Qwen3.8 27B Thinking BF16	262k	$0.157/M	$1.97/M	$0.0394/M	N/A	0.9s	53 tps
Step 5 Preview FP8	1.0M	$1.05/M	$2.84/M	$0.0525/M	N/A	N/A	N/A
Tencent Hy4 Preview FP4	1.0M	$0.832/M	$2.49/M	$0.0419/M	N/A	1.5s	32 tps

Clef

Context: 66k
Input /M: $0.252/M
Output /M: Free
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.4s
Throughput: N/A

Clef Flash

Context: 25k
Input /M: $0.0399/M
Output /M: Free
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.5s
Throughput: N/A

DeepSeek R1-0528

FP4

Context: 164k
Input /M: $0.525/M
Output /M: $2.26/M
Cache read /M: $0.367/M
Cache hit: 40%
TTFT: 0.8s
Throughput: 19 tps

DeepSeek V3.1

FP4

Context: 164k
Input /M: $0.263/M
Output /M: $0.998/M
Cache read /M: $0.136/M
Cache hit: 82.5%
TTFT: 0.6s
Throughput: 24 tps

DeepSeek V3.2

FP4

Context: 164k
Input /M: $0.273/M
Output /M: $0.399/M
Cache read /M: $0.136/M
Cache hit: 78.3%
TTFT: 0.5s
Throughput: 37 tps

DeepSeek V3.2 (Thinking)

FP4

Context: 164k
Input /M: $0.273/M
Output /M: $0.399/M
Cache read /M: $0.136/M
Cache hit: 25.3%
TTFT: 0.5s
Throughput: 37 tps

DeepSeek V4 Flash

FP8

Context: 1.0M
Input /M: $0.0945/M
Output /M: $0.189/M
Cache read /M: $0.0189/M
Cache hit: 54.3%
TTFT: 0.8s
Throughput: 38 tps

DeepSeek V4 Flash (Thinking)

FP8

Context: 1.0M
Input /M: $0.0945/M
Output /M: $0.189/M
Cache read /M: $0.0189/M
Cache hit: 54.3%
TTFT: 0.8s
Throughput: 38 tps

DeepSeek V4 Flash 0731

FP8

Context: 1.0M
Input /M: $0.063/M
Output /M: $0.189/M
Cache read /M: $0.0158/M
Cache hit: 6.5%
TTFT: 0.7s
Throughput: 38 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

Context: 1.0M
Input /M: $0.063/M
Output /M: $0.189/M
Cache read /M: $0.0158/M
Cache hit: 6.5%
TTFT: 0.7s
Throughput: 38 tps

DeepSeek V4 Flash Vision Exp

FP8

Context: 1.0M
Input /M: $0.226/M
Output /M: $0.679/M
Cache read /M: $0.0072/M
Cache hit: 0%
TTFT: 1.8s
Throughput: 15 tps

DeepSeek V4 Pro

FP8

Context: 1.0M
Input /M: $1.36/M
Output /M: $2.73/M
Cache read /M: $0.105/M
Cache hit: 18.4%
TTFT: 1s
Throughput: 61 tps

DeepSeek V4 Pro (Thinking)

FP8

Context: 1.0M
Input /M: $1.36/M
Output /M: $2.73/M
Cache read /M: $0.105/M
Cache hit: 18.4%
TTFT: 1s
Throughput: 61 tps

DeepSeek V4 Pro 0813

FP8

Context: 1.0M
Input /M: $1.36/M
Output /M: $2.73/M
Cache read /M: $0.105/M
Cache hit: N/A
TTFT: 1.1s
Throughput: 52 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

Context: 1.0M
Input /M: $1.36/M
Output /M: $2.73/M
Cache read /M: $0.105/M
Cache hit: N/A
TTFT: 1.1s
Throughput: 52 tps

DeepSeek V4.1 Flash

FP8

Context: 1.0M
Input /M: $0.147/M
Output /M: $0.441/M
Cache read /M: $0.0044/M
Cache hit: 18.6%
TTFT: 0.6s
Throughput: 78 tps

DeepSeek V4.1 Flash (Thinking)

FP8

Context: 1.0M
Input /M: $0.147/M
Output /M: $0.441/M
Cache read /M: $0.0044/M
Cache hit: 18.6%
TTFT: 0.6s
Throughput: 78 tps

DeepSeek V4.1 Flash 1017

FP8

Context: 1.0M
Input /M: $0.147/M
Output /M: $0.441/M
Cache read /M: $0.0044/M
Cache hit: 62.4%
TTFT: 1.1s
Throughput: 51 tps

DeepSeek V4.1 Flash 1017 (Thinking)

FP8

Context: 1.0M
Input /M: $0.147/M
Output /M: $0.441/M
Cache read /M: $0.0044/M
Cache hit: 23.6%
TTFT: 1.1s
Throughput: 51 tps

Doubao Seed 2.0 Pro

Context: 256k
Input /M: $0.782/M
Output /M: $3.88/M
Cache read /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Gemma 4 26B A4B

FP8

Context: 262k
Input /M: $0.0735/M
Output /M: $0.357/M
Cache read /M: $0.0105/M
Cache hit: N/A
TTFT: 0.4s
Throughput: 95 tps

Gemma 4 31B

FP8

Context: 262k
Input /M: $0.21/M
Output /M: $0.42/M
Cache read /M: $0.021/M
Cache hit: 26.2%
TTFT: 0.8s
Throughput: 28 tps

GLM 4.6

FP4

Context: 203k
Input /M: $0.525/M
Output /M: $2.10/M
Cache read /M: $0.105/M
Cache hit: 0%
TTFT: 1.2s
Throughput: 22 tps

GLM 4.6 (Thinking)

FP4

Context: 203k
Input /M: $0.525/M
Output /M: $2.10/M
Cache read /M: $0.105/M
Cache hit: 0%
TTFT: 1.2s
Throughput: 22 tps

GLM 4.7

FP4

Context: 203k
Input /M: $0.42/M
Output /M: $1.84/M
Cache read /M: $0.084/M
Cache hit: 30.6%
TTFT: 1.3s
Throughput: 22 tps

GLM 4.7 (Thinking)

FP4

Context: 203k
Input /M: $0.42/M
Output /M: $1.84/M
Cache read /M: $0.084/M
Cache hit: 0%
TTFT: 1.3s
Throughput: 22 tps

GLM 5.2

FP4

Context: 1.0M
Input /M: $0.591/M
Output /M: $1.89/M
Cache read /M: $0.11/M
Cache hit: 7.6%
TTFT: 1.1s
Throughput: 41 tps

GLM 5.2 (Thinking)

FP4

Context: 1.0M
Input /M: $0.591/M
Output /M: $1.89/M
Cache read /M: $0.11/M
Cache hit: 0%
TTFT: 1.1s
Throughput: 41 tps

GLM 5.3

FP4

Context: 1.0M
Input /M: $0.591/M
Output /M: $2.63/M
Cache read /M: $0.131/M
Cache hit: 0.1%
TTFT: 1.1s
Throughput: 69 tps

GLM 5.3 (Thinking)

FP4

Context: 1.0M
Input /M: $0.591/M
Output /M: $2.63/M
Cache read /M: $0.131/M
Cache hit: 19.9%
TTFT: 1.1s
Throughput: 69 tps

GLM 5.3 Flash

FP4

Context: 1.0M
Input /M: $0.157/M
Output /M: $0.525/M
Cache read /M: $0.0315/M
Cache hit: 72.8%
TTFT: 2.2s
Throughput: 23 tps

GPT OSS 120B

BF16

Context: 131k
Input /M: $0.0389/M
Output /M: $0.178/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.5s
Throughput: 33 tps

GPT OSS 20B

BF16

Context: 131k
Input /M: $0.0315/M
Output /M: $0.147/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.2s
Throughput: 109 tps

Granite 4.2 8B

BF16

Context: 131k
Input /M: $0.063/M
Output /M: $0.263/M
Cache read /M: $0.0158/M
Cache hit: N/A
TTFT: 1.5s
Throughput: 14 tps

Hermes 3 70B

FP8

Context: 131k
Input /M: $0.735/M
Output /M: $0.735/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.9s
Throughput: 29 tps

Inkling Small

FP8

Context: 524k
Input /M: $0.472/M
Output /M: $1.26/M
Cache read /M: $0.105/M
Cache hit: 77.2%
TTFT: 1.2s
Throughput: 101 tps

Inkling Small Thinking

FP8

Context: 524k
Input /M: $0.472/M
Output /M: $1.26/M
Cache read /M: $0.105/M
Cache hit: 77.2%
TTFT: 1.2s
Throughput: 101 tps

Kimi K2.6

FP4

Context: 262k
Input /M: $0.787/M
Output /M: $3.68/M
Cache read /M: $0.157/M
Cache hit: N/A
TTFT: 1.1s
Throughput: 31 tps

Kimi K3

MXFP4

Context: 1.0M
Input /M: $2.99/M
Output /M: $14.96/M
Cache read /M: $0.299/M
Cache hit: 78.3%
TTFT: 1.9s
Throughput: 33 tps

Ling 3.1 Flash

FP4

Context: 262k
Input /M: $0.0787/M
Output /M: $0.236/M
Cache read /M: $0.0158/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Llama 3.1 8B

FP8

Context: 131k
Input /M: $0.021/M
Output /M: $0.042/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.7s
Throughput: 25 tps

Llama 3.3 70B Instruct

FP8

Context: 131k
Input /M: $0.105/M
Output /M: $0.336/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.7s
Throughput: 11 tps

MiMo V2.6 Flash

FP8

Context: 1.0M
Input /M: $0.147/M
Output /M: $0.294/M
Cache read /M: $0.0029/M
Cache hit: 21%
TTFT: 47.4s
Throughput: 3 tps

MiMo V2.6 Pro

FP8

Context: 1.0M
Input /M: $0.406/M
Output /M: $0.822/M
Cache read /M: $0.0034/M
Cache hit: 46%
TTFT: 1.2s
Throughput: 29 tps

MiniMax M3

FP8

Context: 524k
Input /M: $0.294/M
Output /M: $1.16/M
Cache read /M: $0.0588/M
Cache hit: 69.7%
TTFT: 0.9s
Throughput: 32 tps

MiniMax M3 Thinking

FP8

Context: 524k
Input /M: $0.294/M
Output /M: $1.16/M
Cache read /M: $0.0588/M
Cache hit: 33.4%
TTFT: 0.9s
Throughput: 32 tps

Mistral Small 3 24B (2501)

FP8

Context: 33k
Input /M: $0.0525/M
Output /M: $0.084/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.5s
Throughput: 48 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: 0.4s
Throughput: 171.5 tps

Nvidia Nemotron 3 Super 120B

BF16

Context: 262k
Input /M: $0.0892/M
Output /M: $0.42/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 1.2s
Throughput: 64.5 tps

Nvidia Nemotron 3 Super 120B Thinking

BF16

Context: 262k
Input /M: $0.0892/M
Output /M: $0.42/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 1.2s
Throughput: 64.5 tps

Nvidia Nemotron 3 Ultra 550B

Context: 262k
Input /M: $0.525/M
Output /M: $2.31/M
Cache read /M: $0.105/M
Cache hit: 0%
TTFT: 6.2s
Throughput: 63.2 tps

Nvidia Nemotron 3 Ultra 550B Thinking

Context: 262k
Input /M: $0.525/M
Output /M: $2.31/M
Cache read /M: $0.105/M
Cache hit: 46.9%
TTFT: 1.9s
Throughput: 64.4 tps

Nvidia Nemotron 3.5 Lightning

Context: 262k
Input /M: $0.063/M
Output /M: $0.168/M
Cache read /M: $0.0315/M
Cache hit: 0%
TTFT: 0.9s
Throughput: 111.6 tps

Nvidia Nemotron 3.5 Lightning Thinking

Context: 262k
Input /M: $0.063/M
Output /M: $0.168/M
Cache read /M: $0.0315/M
Cache hit: 0%
TTFT: 1.6s
Throughput: 144.9 tps

Nvidia Nemotron 3.5 Super VL

FP4

Context: 262k
Input /M: $0.157/M
Output /M: $0.525/M
Cache read /M: $0.021/M
Cache hit: 17%
TTFT: 7.7s
Throughput: 798.3 tps

Qwen 2.5 72B Instruct

FP8

Context: 33k
Input /M: $0.378/M
Output /M: $0.42/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.7s
Throughput: 18 tps

Qwen 3.6 27B

FP8

Context: 262k
Input /M: $0.336/M
Output /M: $3.36/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.4s
Throughput: 60 tps

Qwen 3.6 27B Thinking

FP8

Context: 262k
Input /M: $0.336/M
Output /M: $3.36/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.4s
Throughput: 60 tps

Qwen 3.6 35B A3B

FP8

Context: 262k
Input /M: $0.105/M
Output /M: $0.998/M
Cache read /M: $0.105/M
Cache hit: N/A
TTFT: 1.1s
Throughput: 18 tps

Qwen 3.6 35B A3B Thinking

FP8

Context: 262k
Input /M: $0.105/M
Output /M: $0.998/M
Cache read /M: $0.105/M
Cache hit: N/A
TTFT: 1.1s
Throughput: 18 tps

Qwen3 14B

FP8

Context: 41k
Input /M: $0.126/M
Output /M: $0.252/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.3s
Throughput: 90 tps

Qwen3 235B A22B

FP8

Context: 262k
Input /M: $0.0945/M
Output /M: $0.578/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.5s
Throughput: 15 tps

Qwen3 32B

FP8

Context: 41k
Input /M: $0.084/M
Output /M: $0.294/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.5s
Throughput: 24 tps

Qwen3 Next 80B A3B Instruct

FP8

Context: 262k
Input /M: $0.0945/M
Output /M: $1.16/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 0.5s
Throughput: 31 tps

Qwen3.5 27B

FP8

Context: 262k
Input /M: $0.273/M
Output /M: $2.73/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.6s
Throughput: 57 tps

Qwen3.5 27B Thinking

FP8

Context: 262k
Input /M: $0.273/M
Output /M: $2.73/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.6s
Throughput: 57 tps

Qwen3.5 35B A3B

FP8

Context: 262k
Input /M: $0.147/M
Output /M: $1.05/M
Cache read /M: $0.0525/M
Cache hit: N/A
TTFT: 0.5s
Throughput: 88 tps

Qwen3.5 35B A3B Thinking

FP8

Context: 262k
Input /M: $0.147/M
Output /M: $1.05/M
Cache read /M: $0.0525/M
Cache hit: N/A
TTFT: 0.5s
Throughput: 88 tps

Qwen3.5 397B

FP8

Context: 262k
Input /M: $0.472/M
Output /M: $3.15/M
Cache read /M: $0.231/M
Cache hit: 0%
TTFT: 0.6s
Throughput: 35 tps

Qwen3.5 397B Thinking

FP8

Context: 262k
Input /M: $0.472/M
Output /M: $3.15/M
Cache read /M: $0.231/M
Cache hit: 0%
TTFT: 0.6s
Throughput: 35 tps

Qwen3.5 9B

BF16

Context: 262k
Input /M: $0.105/M
Output /M: $0.157/M
Cache read /M: N/A
Cache hit: N/A
TTFT: 0.7s
Throughput: 21 tps

Qwen3.8 27B

BF16

Context: 262k
Input /M: $0.157/M
Output /M: $1.97/M
Cache read /M: $0.0394/M
Cache hit: N/A
TTFT: 0.9s
Throughput: 53 tps

Qwen3.8 27B Thinking

BF16

Context: 262k
Input /M: $0.157/M
Output /M: $1.97/M
Cache read /M: $0.0394/M
Cache hit: N/A
TTFT: 0.9s
Throughput: 53 tps

Step 5 Preview

FP8

Context: 1.0M
Input /M: $1.05/M
Output /M: $2.84/M
Cache read /M: $0.0525/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Tencent Hy4 Preview

FP4

Context: 1.0M
Input /M: $0.832/M
Output /M: $2.49/M
Cache read /M: $0.0419/M
Cache hit: N/A
TTFT: 1.5s
Throughput: 32 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": "cloudflare/clef: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