Novita

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 Novita

73 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek R1 FP8	128k	$0.73/M	$2.63/M	N/A	1.2s	24 tps
DeepSeek R1-0528 FP8	164k	$0.73/M	$2.63/M	$0.37/M	1.2s	24 tps
DeepSeek V4 Flash 0731 FP8	1.0M	$0.43/M	$1.29/M	$0.03/M	2.1s	67 tps
DeepSeek V4 Flash 0731 (Thinking) FP8	1.0M	$0.43/M	$1.29/M	$0.03/M	2.1s	67 tps
DeepSeek V4 Pro FP8	1.0M	$1.68/M	$3.36/M	$0.14/M	2.1s	66 tps
DeepSeek V4 Pro 0813 FP8	1.0M	$1.04/M	$3.12/M	$0.03/M	1.1s	46 tps
DeepSeek V4 Pro 0813 (Thinking) FP8	1.0M	$1.04/M	$3.12/M	$0.03/M	1.1s	46 tps
DeepSeek V4.1 Flash FP8	1.0M	$0.20/M	$0.82/M	$0.0041/M	1.3s	119 tps
DeepSeek V4.1 Flash (Thinking) FP8	1.0M	$0.20/M	$0.82/M	$0.0041/M	1.3s	119 tps
Gemma 4 26B A4B BF16	262k	$0.14/M	$0.42/M	N/A	0.7s	31 tps
Gemma 4 26B A4B (Thinking) BF16	262k	$0.14/M	$0.42/M	N/A	0.7s	31 tps
Gemma 4 31B BF16	262k	$0.15/M	$0.42/M	N/A	1.3s	22 tps
Gemma 4 31B (Thinking) BF16	262k	$0.15/M	$0.42/M	N/A	1.3s	22 tps
GLM 4.5 Air BF16	131k	$0.14/M	$0.89/M	$0.03/M	0.7s	50 tps
GLM 4.5 Air (Thinking) BF16	131k	$0.14/M	$0.89/M	$0.03/M	0.7s	50 tps
GLM 4.6 BF16	205k	$0.58/M	$2.31/M	$0.12/M	4.9s	24 tps
GLM 4.6 (Thinking) BF16	205k	$0.58/M	$2.31/M	$0.12/M	4.9s	24 tps
GLM 4.7 FP8	205k	$0.57/M	$2.08/M	$0.10/M	4.6s	23 tps
GLM 4.7 (Thinking) FP8	205k	$0.57/M	$2.08/M	$0.10/M	4.6s	23 tps
GLM 4.7 Flash BF16	200k	$0.07/M	$0.42/M	$0.01/M	1s	56.5 tps
GLM 4.7 Flash (Thinking) BF16	200k	$0.07/M	$0.42/M	$0.01/M	1s	56.5 tps
GLM 5 FP8	203k	$1.05/M	$3.36/M	$0.21/M	1.4s	47 tps
GLM 5 (Thinking) FP8	203k	$1.05/M	$3.36/M	$0.21/M	1.4s	47 tps
GLM 5.1 FP8	205k	$1.45/M	$4.62/M	$0.27/M	3s	39 tps
GLM 5.1 (Thinking) FP8	205k	$1.45/M	$4.62/M	$0.27/M	3s	39 tps
GLM 5.2 FP8	1.0M	$1.47/M	$4.62/M	$0.27/M	1.3s	66 tps
GLM 5.2 (Thinking) FP8	1.0M	$1.47/M	$4.62/M	$0.27/M	1.3s	66 tps
GLM 5.3 FP8	1.0M	$0.73/M	$2.31/M	$0.14/M	2.5s	62 tps
GLM 5.3 (Thinking) FP8	1.0M	$0.73/M	$2.31/M	$0.14/M	2.5s	62 tps
GLM 5.3 Flash FP8	1.0M	$0.09/M	$0.29/M	$0.02/M	2s	40 tps
GPT OSS 120B FP4	131k	$0.05/M	$0.26/M	N/A	0.6s	151 tps
Kimi K2 Thinking BF16	262k	$0.63/M	$2.63/M	$0.16/M	1.7s	43 tps
Kimi K2.5	262k	$0.63/M	$3.15/M	$0.11/M	1.2s	40 tps
Kimi K2.5 Thinking	262k	$0.63/M	$3.15/M	$0.11/M	1.2s	40 tps
Kimi K2.6	262k	$0.84/M	$3.57/M	$0.17/M	1.9s	28 tps
Kimi K2.6 Thinking	262k	$0.84/M	$3.57/M	$0.17/M	1.9s	28 tps
Kimi K2.7 Code INT4	262k	$1.00/M	$4.20/M	$0.20/M	2.2s	60 tps
Kimi K3	1.0M	$3.15/M	$15.75/M	$0.31/M	N/A	N/A
Ling 3.0 Flash	262k	$0.07/M	$0.22/M	$0.02/M	N/A	N/A
Ling 3.0 Flash Thinking	262k	$0.07/M	$0.22/M	$0.02/M	N/A	N/A
Ling 3.0 Flash VL	262k	$0.06/M	$0.18/M	$0.01/M	N/A	N/A
Ling 3.1 Flash	262k	$0.07/M	$0.22/M	$0.02/M	N/A	N/A
Llama 3.1 8B FP8	16k	$0.02/M	$0.05/M	N/A	0.5s	103 tps
Llama 3.3 70B Instruct BF16	12k	$0.14/M	$0.42/M	N/A	0.8s	40 tps
Llama 4 Maverick FP8	1.0M	$0.28/M	$0.89/M	N/A	0.5s	37 tps
MiMo V2.5 FP8	1.0M	$0.18/M	$0.35/M	$0.0036/M	4s	17 tps
MiMo V2.5 Pro	1.0M	$0.55/M	$1.10/M	$0.0045/M	2.4s	25 tps
MiMo V2.5 Pro Thinking	1.0M	$0.55/M	$1.10/M	$0.0045/M	2.4s	25 tps
MiMo V2.5 Thinking FP8	1.0M	$0.18/M	$0.35/M	$0.0036/M	4s	17 tps
MiMo V2.6 Flash FP8	1.0M	$0.15/M	$0.29/M	$0.0029/M	4.3s	21 tps
MiMo V2.6 Pro FP8	1.0M	$0.46/M	$0.91/M	$0.0038/M	5.4s	30 tps
MiniMax M2.5 FP8	205k	$0.31/M	$1.26/M	$0.03/M	1.2s	56 tps
MiniMax M2.7 FP8	205k	$0.31/M	$1.26/M	$0.06/M	1.5s	44 tps
MiniMax M3 FP8	1M	$0.31/M	$1.26/M	$0.06/M	1.6s	95 tps
>524k tokens		$0.63/M	$2.52/M	$0.13/M
MiniMax M3 Thinking FP8	1M	$0.31/M	$1.26/M	$0.06/M	1.6s	95 tps
>524k tokens		$0.63/M	$2.52/M	$0.13/M
Qwen 3.6 27B	262k	$0.63/M	$3.78/M	N/A	N/A	N/A
Qwen 3.6 27B Thinking	262k	$0.63/M	$3.78/M	N/A	N/A	N/A
Qwen3.5 122B A10B BF16	262k	$0.42/M	$3.36/M	N/A	1.1s	73.5 tps
Qwen3.5 122B A10B Thinking BF16	262k	$0.42/M	$3.36/M	N/A	1.1s	73.5 tps
Qwen3.5 27B BF16	262k	$0.31/M	$2.52/M	N/A	2.9s	42 tps
Qwen3.5 27B Thinking BF16	262k	$0.31/M	$2.52/M	N/A	2.9s	42 tps
Qwen3.5 35B A3B	262k	$0.26/M	$2.10/M	N/A	N/A	N/A
Qwen3.5 35B A3B Thinking	262k	$0.26/M	$2.10/M	N/A	N/A	N/A
Qwen3.5 397B	262k	$0.63/M	$3.78/M	N/A	1.3s	33 tps
Qwen3.5 397B Thinking	262k	$0.63/M	$3.78/M	N/A	1.3s	33 tps
Qwen3.8 27B	1M	$0.44/M	$3.15/M	$0.09/M	1.6s	44 tps
Qwen3.8 27B Thinking	1M	$0.44/M	$3.15/M	$0.09/M	1.6s	44 tps
Qwen3.8 Max	1M	$2.10/M	$6.30/M	$0.26/M	1.9s	36 tps
Qwen3.8 Max Thinking	1M	$2.10/M	$6.30/M	$0.26/M	1.9s	36 tps
Step 3.7 Flash Thinking FP8	262k	$0.21/M	$1.21/M	$0.04/M	N/A	N/A
Step 5 Preview	1M	$1.05/M	$2.84/M	$0.11/M	N/A	N/A
Tencent Hy3	262k	$0.07/M	$0.26/M	$0.03/M	N/A	N/A
Tencent Hy4 Preview FP8	1M	$0.88/M	$2.63/M	$0.04/M	7s	33 tps

DeepSeek R1

FP8

Context: 128k
Input /M: $0.73/M
Output /M: $2.63/M
Cache read /M: N/A
TTFT: 1.2s
Throughput: 24 tps

DeepSeek R1-0528

FP8

Context: 164k
Input /M: $0.73/M
Output /M: $2.63/M
Cache read /M: $0.37/M
TTFT: 1.2s
Throughput: 24 tps

DeepSeek V4 Flash 0731

FP8

Context: 1.0M
Input /M: $0.43/M
Output /M: $1.29/M
Cache read /M: $0.03/M
TTFT: 2.1s
Throughput: 67 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

Context: 1.0M
Input /M: $0.43/M
Output /M: $1.29/M
Cache read /M: $0.03/M
TTFT: 2.1s
Throughput: 67 tps

DeepSeek V4 Pro

FP8

Context: 1.0M
Input /M: $1.68/M
Output /M: $3.36/M
Cache read /M: $0.14/M
TTFT: 2.1s
Throughput: 66 tps

DeepSeek V4 Pro 0813

FP8

Context: 1.0M
Input /M: $1.04/M
Output /M: $3.12/M
Cache read /M: $0.03/M
TTFT: 1.1s
Throughput: 46 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

Context: 1.0M
Input /M: $1.04/M
Output /M: $3.12/M
Cache read /M: $0.03/M
TTFT: 1.1s
Throughput: 46 tps

DeepSeek V4.1 Flash

FP8

Context: 1.0M
Input /M: $0.20/M
Output /M: $0.82/M
Cache read /M: $0.0041/M
TTFT: 1.3s
Throughput: 119 tps

DeepSeek V4.1 Flash (Thinking)

FP8

Context: 1.0M
Input /M: $0.20/M
Output /M: $0.82/M
Cache read /M: $0.0041/M
TTFT: 1.3s
Throughput: 119 tps

Gemma 4 26B A4B

BF16

Context: 262k
Input /M: $0.14/M
Output /M: $0.42/M
Cache read /M: N/A
TTFT: 0.7s
Throughput: 31 tps

Gemma 4 26B A4B (Thinking)

BF16

Context: 262k
Input /M: $0.14/M
Output /M: $0.42/M
Cache read /M: N/A
TTFT: 0.7s
Throughput: 31 tps

Gemma 4 31B

BF16

Context: 262k
Input /M: $0.15/M
Output /M: $0.42/M
Cache read /M: N/A
TTFT: 1.3s
Throughput: 22 tps

Gemma 4 31B (Thinking)

BF16

Context: 262k
Input /M: $0.15/M
Output /M: $0.42/M
Cache read /M: N/A
TTFT: 1.3s
Throughput: 22 tps

GLM 4.5 Air

BF16

Context: 131k
Input /M: $0.14/M
Output /M: $0.89/M
Cache read /M: $0.03/M
TTFT: 0.7s
Throughput: 50 tps

GLM 4.5 Air (Thinking)

BF16

Context: 131k
Input /M: $0.14/M
Output /M: $0.89/M
Cache read /M: $0.03/M
TTFT: 0.7s
Throughput: 50 tps

GLM 4.6

BF16

Context: 205k
Input /M: $0.58/M
Output /M: $2.31/M
Cache read /M: $0.12/M
TTFT: 4.9s
Throughput: 24 tps

GLM 4.6 (Thinking)

BF16

Context: 205k
Input /M: $0.58/M
Output /M: $2.31/M
Cache read /M: $0.12/M
TTFT: 4.9s
Throughput: 24 tps

GLM 4.7

FP8

Context: 205k
Input /M: $0.57/M
Output /M: $2.08/M
Cache read /M: $0.10/M
TTFT: 4.6s
Throughput: 23 tps

GLM 4.7 (Thinking)

FP8

Context: 205k
Input /M: $0.57/M
Output /M: $2.08/M
Cache read /M: $0.10/M
TTFT: 4.6s
Throughput: 23 tps

GLM 4.7 Flash

BF16

Context: 200k
Input /M: $0.07/M
Output /M: $0.42/M
Cache read /M: $0.01/M
TTFT: 1s
Throughput: 56.5 tps

GLM 4.7 Flash (Thinking)

BF16

Context: 200k
Input /M: $0.07/M
Output /M: $0.42/M
Cache read /M: $0.01/M
TTFT: 1s
Throughput: 56.5 tps

GLM 5

FP8

Context: 203k
Input /M: $1.05/M
Output /M: $3.36/M
Cache read /M: $0.21/M
TTFT: 1.4s
Throughput: 47 tps

GLM 5 (Thinking)

FP8

Context: 203k
Input /M: $1.05/M
Output /M: $3.36/M
Cache read /M: $0.21/M
TTFT: 1.4s
Throughput: 47 tps

GLM 5.1

FP8

Context: 205k
Input /M: $1.45/M
Output /M: $4.62/M
Cache read /M: $0.27/M
TTFT: 3s
Throughput: 39 tps

GLM 5.1 (Thinking)

FP8

Context: 205k
Input /M: $1.45/M
Output /M: $4.62/M
Cache read /M: $0.27/M
TTFT: 3s
Throughput: 39 tps

GLM 5.2

FP8

Context: 1.0M
Input /M: $1.47/M
Output /M: $4.62/M
Cache read /M: $0.27/M
TTFT: 1.3s
Throughput: 66 tps

GLM 5.2 (Thinking)

FP8

Context: 1.0M
Input /M: $1.47/M
Output /M: $4.62/M
Cache read /M: $0.27/M
TTFT: 1.3s
Throughput: 66 tps

GLM 5.3

FP8

Context: 1.0M
Input /M: $0.73/M
Output /M: $2.31/M
Cache read /M: $0.14/M
TTFT: 2.5s
Throughput: 62 tps

GLM 5.3 (Thinking)

FP8

Context: 1.0M
Input /M: $0.73/M
Output /M: $2.31/M
Cache read /M: $0.14/M
TTFT: 2.5s
Throughput: 62 tps

GLM 5.3 Flash

FP8

Context: 1.0M
Input /M: $0.09/M
Output /M: $0.29/M
Cache read /M: $0.02/M
TTFT: 2s
Throughput: 40 tps

GPT OSS 120B

FP4

Context: 131k
Input /M: $0.05/M
Output /M: $0.26/M
Cache read /M: N/A
TTFT: 0.6s
Throughput: 151 tps

Kimi K2 Thinking

BF16

Context: 262k
Input /M: $0.63/M
Output /M: $2.63/M
Cache read /M: $0.16/M
TTFT: 1.7s
Throughput: 43 tps

Kimi K2.5

Context: 262k
Input /M: $0.63/M
Output /M: $3.15/M
Cache read /M: $0.11/M
TTFT: 1.2s
Throughput: 40 tps

Kimi K2.5 Thinking

Context: 262k
Input /M: $0.63/M
Output /M: $3.15/M
Cache read /M: $0.11/M
TTFT: 1.2s
Throughput: 40 tps

Kimi K2.6

Context: 262k
Input /M: $0.84/M
Output /M: $3.57/M
Cache read /M: $0.17/M
TTFT: 1.9s
Throughput: 28 tps

Kimi K2.6 Thinking

Context: 262k
Input /M: $0.84/M
Output /M: $3.57/M
Cache read /M: $0.17/M
TTFT: 1.9s
Throughput: 28 tps

Kimi K2.7 Code

INT4

Context: 262k
Input /M: $1.00/M
Output /M: $4.20/M
Cache read /M: $0.20/M
TTFT: 2.2s
Throughput: 60 tps

Kimi K3

Context: 1.0M
Input /M: $3.15/M
Output /M: $15.75/M
Cache read /M: $0.31/M
TTFT: N/A
Throughput: N/A

Ling 3.0 Flash

Context: 262k
Input /M: $0.07/M
Output /M: $0.22/M
Cache read /M: $0.02/M
TTFT: N/A
Throughput: N/A

Ling 3.0 Flash Thinking

Context: 262k
Input /M: $0.07/M
Output /M: $0.22/M
Cache read /M: $0.02/M
TTFT: N/A
Throughput: N/A

Ling 3.0 Flash VL

Context: 262k
Input /M: $0.06/M
Output /M: $0.18/M
Cache read /M: $0.01/M
TTFT: N/A
Throughput: N/A

Ling 3.1 Flash

Context: 262k
Input /M: $0.07/M
Output /M: $0.22/M
Cache read /M: $0.02/M
TTFT: N/A
Throughput: N/A

Llama 3.1 8B

FP8

Context: 16k
Input /M: $0.02/M
Output /M: $0.05/M
Cache read /M: N/A
TTFT: 0.5s
Throughput: 103 tps

Llama 3.3 70B Instruct

BF16

Context: 12k
Input /M: $0.14/M
Output /M: $0.42/M
Cache read /M: N/A
TTFT: 0.8s
Throughput: 40 tps

Llama 4 Maverick

FP8

Context: 1.0M
Input /M: $0.28/M
Output /M: $0.89/M
Cache read /M: N/A
TTFT: 0.5s
Throughput: 37 tps

MiMo V2.5

FP8

Context: 1.0M
Input /M: $0.18/M
Output /M: $0.35/M
Cache read /M: $0.0036/M
TTFT: 4s
Throughput: 17 tps

MiMo V2.5 Pro

Context: 1.0M
Input /M: $0.55/M
Output /M: $1.10/M
Cache read /M: $0.0045/M
TTFT: 2.4s
Throughput: 25 tps

MiMo V2.5 Pro Thinking

Context: 1.0M
Input /M: $0.55/M
Output /M: $1.10/M
Cache read /M: $0.0045/M
TTFT: 2.4s
Throughput: 25 tps

MiMo V2.5 Thinking

FP8

Context: 1.0M
Input /M: $0.18/M
Output /M: $0.35/M
Cache read /M: $0.0036/M
TTFT: 4s
Throughput: 17 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
TTFT: 4.3s
Throughput: 21 tps

MiMo V2.6 Pro

FP8

Context: 1.0M
Input /M: $0.46/M
Output /M: $0.91/M
Cache read /M: $0.0038/M
TTFT: 5.4s
Throughput: 30 tps

MiniMax M2.5

FP8

Context: 205k
Input /M: $0.31/M
Output /M: $1.26/M
Cache read /M: $0.03/M
TTFT: 1.2s
Throughput: 56 tps

MiniMax M2.7

FP8

Context: 205k
Input /M: $0.31/M
Output /M: $1.26/M
Cache read /M: $0.06/M
TTFT: 1.5s
Throughput: 44 tps

MiniMax M3

FP8

Context: 1M
Input /M: $0.31/M
Output /M: $1.26/M
Cache read /M: $0.06/M
TTFT: 1.6s
Throughput: 95 tps

Above 524k tokens: in $0.63/M · out $2.52/M · cache read $0.13/M

MiniMax M3 Thinking

FP8

Context: 1M
Input /M: $0.31/M
Output /M: $1.26/M
Cache read /M: $0.06/M
TTFT: 1.6s
Throughput: 95 tps

Above 524k tokens: in $0.63/M · out $2.52/M · cache read $0.13/M

Qwen 3.6 27B

Context: 262k
Input /M: $0.63/M
Output /M: $3.78/M
Cache read /M: N/A
TTFT: N/A
Throughput: N/A

Qwen 3.6 27B Thinking

Context: 262k
Input /M: $0.63/M
Output /M: $3.78/M
Cache read /M: N/A
TTFT: N/A
Throughput: N/A

Qwen3.5 122B A10B

BF16

Context: 262k
Input /M: $0.42/M
Output /M: $3.36/M
Cache read /M: N/A
TTFT: 1.1s
Throughput: 73.5 tps

Qwen3.5 122B A10B Thinking

BF16

Context: 262k
Input /M: $0.42/M
Output /M: $3.36/M
Cache read /M: N/A
TTFT: 1.1s
Throughput: 73.5 tps

Qwen3.5 27B

BF16

Context: 262k
Input /M: $0.31/M
Output /M: $2.52/M
Cache read /M: N/A
TTFT: 2.9s
Throughput: 42 tps

Qwen3.5 27B Thinking

BF16

Context: 262k
Input /M: $0.31/M
Output /M: $2.52/M
Cache read /M: N/A
TTFT: 2.9s
Throughput: 42 tps

Qwen3.5 35B A3B

Context: 262k
Input /M: $0.26/M
Output /M: $2.10/M
Cache read /M: N/A
TTFT: N/A
Throughput: N/A

Qwen3.5 35B A3B Thinking

Context: 262k
Input /M: $0.26/M
Output /M: $2.10/M
Cache read /M: N/A
TTFT: N/A
Throughput: N/A

Qwen3.5 397B

Context: 262k
Input /M: $0.63/M
Output /M: $3.78/M
Cache read /M: N/A
TTFT: 1.3s
Throughput: 33 tps

Qwen3.5 397B Thinking

Context: 262k
Input /M: $0.63/M
Output /M: $3.78/M
Cache read /M: N/A
TTFT: 1.3s
Throughput: 33 tps

Qwen3.8 27B

Context: 1M
Input /M: $0.44/M
Output /M: $3.15/M
Cache read /M: $0.09/M
TTFT: 1.6s
Throughput: 44 tps

Qwen3.8 27B Thinking

Context: 1M
Input /M: $0.44/M
Output /M: $3.15/M
Cache read /M: $0.09/M
TTFT: 1.6s
Throughput: 44 tps

Qwen3.8 Max

Context: 1M
Input /M: $2.10/M
Output /M: $6.30/M
Cache read /M: $0.26/M
TTFT: 1.9s
Throughput: 36 tps

Qwen3.8 Max Thinking

Context: 1M
Input /M: $2.10/M
Output /M: $6.30/M
Cache read /M: $0.26/M
TTFT: 1.9s
Throughput: 36 tps

Step 3.7 Flash Thinking

FP8

Context: 262k
Input /M: $0.21/M
Output /M: $1.21/M
Cache read /M: $0.04/M
TTFT: N/A
Throughput: N/A

Step 5 Preview

Context: 1M
Input /M: $1.05/M
Output /M: $2.84/M
Cache read /M: $0.11/M
TTFT: N/A
Throughput: N/A

Tencent Hy3

Context: 262k
Input /M: $0.07/M
Output /M: $0.26/M
Cache read /M: $0.03/M
TTFT: N/A
Throughput: N/A

Tencent Hy4 Preview

FP8

Context: 1M
Input /M: $0.88/M
Output /M: $2.63/M
Cache read /M: $0.04/M
TTFT: 7s
Throughput: 33 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 Novita via the API

Call a model served by Novita 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-r1:novita",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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

Novita terms of use Novita privacy policy