Novita

68 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

68 models

Model	Context	Input /M	Output /M	Cache read /M	Cache write /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash 0731 FP8	1.0M	$0.43/M	$1.29/M	$0.0273/M	N/A	54.4%	1.1s	69 tps
DeepSeek V4 Flash 0731 (Thinking) FP8	1.0M	$0.43/M	$1.29/M	$0.0273/M	N/A	54.4%	1.1s	69 tps
DeepSeek V4 Pro FP8	1.0M	$1.68/M	$3.36/M	$0.142/M	N/A	N/A	2.2s	54 tps
DeepSeek V4 Pro 0813 FP8	1.0M	$1.04/M	$3.12/M	$0.0346/M	N/A	84.5%	2.1s	49 tps
DeepSeek V4 Pro 0813 (Thinking) FP8	1.0M	$1.04/M	$3.12/M	$0.0346/M	N/A	19.9%	2.1s	49 tps
DeepSeek V4.1 Flash FP8	1.0M	$0.205/M	$0.819/M	$0.0041/M	N/A	N/A	1s	112 tps
DeepSeek V4.1 Flash (Thinking) FP8	1.0M	$0.205/M	$0.819/M	$0.0041/M	N/A	99%	1s	112 tps
DeepSeek V4.1 Flash 1017 FP8	1.0M	$0.205/M	$0.819/M	$0.0041/M	N/A	88.7%	2.9s	78 tps
DeepSeek V4.1 Flash 1017 (Thinking) FP8	1.0M	$0.205/M	$0.819/M	$0.0041/M	N/A	88.7%	2.9s	78 tps
Gemma 4 26B A4B BF16	262k	$0.136/M	$0.42/M	N/A	N/A	N/A	0.9s	161 tps
Gemma 4 26B A4B (Thinking) BF16	262k	$0.136/M	$0.42/M	N/A	N/A	N/A	0.9s	161 tps
Gemma 4 31B BF16	262k	$0.147/M	$0.42/M	N/A	N/A	N/A	1s	20 tps
Gemma 4 31B (Thinking) BF16	262k	$0.147/M	$0.42/M	N/A	N/A	N/A	1s	20 tps
GLM 4.5 Air BF16	131k	$0.136/M	$0.893/M	$0.0262/M	N/A	45.6%	1.8s	45 tps
GLM 4.5 Air (Thinking) BF16	131k	$0.136/M	$0.893/M	$0.0262/M	N/A	45.6%	1.8s	45 tps
GLM 4.6 BF16	205k	$0.578/M	$2.31/M	$0.116/M	N/A	82.5%	4.8s	26 tps
GLM 4.6 (Thinking) BF16	205k	$0.578/M	$2.31/M	$0.116/M	N/A	43.7%	4.8s	26 tps
GLM 4.7 FP8	205k	$0.567/M	$2.08/M	$0.104/M	N/A	30.4%	4.3s	23 tps
GLM 4.7 (Thinking) FP8	205k	$0.567/M	$2.08/M	$0.104/M	N/A	30.4%	4.3s	23 tps
GLM 4.7 Flash BF16	200k	$0.0735/M	$0.42/M	$0.0105/M	N/A	70.5%	1.4s	48 tps
GLM 4.7 Flash (Thinking) BF16	200k	$0.0735/M	$0.42/M	$0.0105/M	N/A	<0.1%	1.4s	48 tps
GLM 5 FP8	203k	$1.05/M	$3.36/M	$0.21/M	N/A	N/A	1.7s	37 tps
GLM 5 (Thinking) FP8	203k	$1.05/M	$3.36/M	$0.21/M	N/A	N/A	1.7s	37 tps
GLM 5.1 FP8	205k	$1.45/M	$4.62/M	$0.273/M	N/A	59.3%	3.7s	33 tps
GLM 5.1 (Thinking) FP8	205k	$1.45/M	$4.62/M	$0.273/M	N/A	59.3%	3.7s	33 tps
GLM 5.2 FP8	1.0M	$1.47/M	$4.62/M	$0.273/M	N/A	33.4%	3.7s	44 tps
GLM 5.2 (Thinking) FP8	1.0M	$1.47/M	$4.62/M	$0.273/M	N/A	72.2%	3.7s	44 tps
GLM 5.3 FP8	1.0M	$0.662/M	$2.08/M	$0.123/M	N/A	76.7%	2s	73 tps
GLM 5.3 (Thinking) FP8	1.0M	$0.662/M	$2.08/M	$0.123/M	N/A	76.7%	2s	73 tps
GLM 5.3 Flash FP8	1.0M	$0.0882/M	$0.294/M	$0.0176/M	N/A	78.5%	3.1s	36 tps
GPT OSS 120B FP4	131k	$0.0525/M	$0.263/M	N/A	N/A	N/A	0.7s	151 tps
Kimi K2 Thinking BF16	262k	$0.63/M	$2.63/M	$0.157/M	N/A	65.7%	1.1s	46 tps
Kimi K2.5	262k	$0.63/M	$3.15/M	$0.105/M	N/A	83.8%	2.4s	40 tps
Kimi K2.5 Thinking	262k	$0.63/M	$3.15/M	$0.105/M	N/A	72%	2.4s	40 tps
Kimi K2.6	262k	$0.84/M	$3.57/M	$0.168/M	N/A	91.5%	3.2s	38 tps
Kimi K2.6 Thinking	262k	$0.84/M	$3.57/M	$0.168/M	N/A	91.5%	3.2s	38 tps
Kimi K2.7 Code INT4	262k	$0.998/M	$4.20/M	$0.20/M	N/A	N/A	3.2s	28.5 tps
Kimi K3	1.0M	$3.15/M	$15.75/M	$0.315/M	$3.15/M	N/A	N/A	N/A
Ling 3.0 Flash	262k	$0.075/M	$0.22/M	$0.015/M	N/A	N/A	N/A	N/A
Ling 3.0 Flash Thinking	262k	$0.075/M	$0.22/M	$0.015/M	N/A	N/A	N/A	N/A
Ling 3.0 Flash VL	262k	$0.06/M	$0.18/M	$0.012/M	N/A	N/A	N/A	N/A
Llama 3.1 8B FP8	16k	$0.021/M	$0.0525/M	N/A	N/A	N/A	0.5s	104 tps
Llama 3.3 70B Instruct BF16	12k	$0.142/M	$0.42/M	N/A	N/A	N/A	1.3s	39 tps
MiMo V2.6 Flash FP8	1.0M	$0.147/M	$0.294/M	$0.0029/M	N/A	N/A	3.7s	28 tps
MiMo V2.6 Pro FP8	1.0M	$0.457/M	$0.913/M	$0.0038/M	N/A	15.1%	4.9s	33 tps
MiniMax M2.5 FP8	205k	$0.315/M	$1.26/M	$0.0315/M	N/A	N/A	1s	45.5 tps
MiniMax M2.7 FP8	205k	$0.315/M	$1.26/M	$0.063/M	N/A	N/A	1.3s	28 tps
MiniMax M3 FP8	1M	$0.315/M	$1.26/M	$0.063/M	N/A	N/A	2.5s	80.5 tps
>524k tokens		$0.63/M	$2.52/M	$0.126/M	N/A
MiniMax M3 Thinking FP8	1M	$0.315/M	$1.26/M	$0.063/M	N/A	N/A	2.5s	80.5 tps
>524k tokens		$0.63/M	$2.52/M	$0.126/M	N/A
MiniMax M3.1 Flash	1M	$0.157/M	$0.63/M	$0.0158/M	N/A	23%	2.6s	88.1 tps
Qwen 3.6 27B	262k	$0.63/M	$3.78/M	N/A	N/A	N/A	N/A	N/A
Qwen 3.6 27B Thinking	262k	$0.63/M	$3.78/M	N/A	N/A	N/A	N/A	N/A
Qwen3.5 122B A10B BF16	262k	$0.42/M	$3.36/M	N/A	N/A	N/A	4.7s	62 tps
Qwen3.5 122B A10B Thinking BF16	262k	$0.42/M	$3.36/M	N/A	N/A	N/A	4.7s	62 tps
Qwen3.5 27B BF16	262k	$0.315/M	$2.52/M	N/A	N/A	N/A	2s	46 tps
Qwen3.5 27B Thinking BF16	262k	$0.315/M	$2.52/M	N/A	N/A	N/A	2s	46 tps
Qwen3.5 35B A3B	262k	$0.263/M	$2.10/M	N/A	N/A	N/A	N/A	N/A
Qwen3.5 35B A3B Thinking	262k	$0.263/M	$2.10/M	N/A	N/A	N/A	N/A	N/A
Qwen3.5 397B	262k	$0.63/M	$3.78/M	N/A	N/A	N/A	1.8s	53 tps
Qwen3.5 397B Thinking	262k	$0.63/M	$3.78/M	N/A	N/A	0%	1.8s	53 tps
Qwen3.8 27B	1M	$0.441/M	$3.15/M	$0.0892/M	N/A	N/A	3.9s	39 tps
Qwen3.8 27B Thinking	1M	$0.441/M	$3.15/M	$0.0892/M	N/A	N/A	3.9s	39 tps
Qwen3.8 Max	1M	$2.10/M	$6.30/M	$0.263/M	N/A	N/A	2.6s	40 tps
Qwen3.8 Max Thinking	1M	$2.10/M	$6.30/M	$0.263/M	N/A	N/A	2.6s	40 tps
Step 3.7 Flash Thinking FP8	262k	$0.21/M	$1.21/M	$0.042/M	N/A	<0.1%	5.6s	32 tps
Step 5 Preview	1M	$1.05/M	$2.84/M	$0.105/M	N/A	N/A	N/A	N/A
Tencent Hy3	262k	$0.066/M	$0.26/M	$0.029/M	N/A	N/A	N/A	N/A
Tencent Hy4 Preview FP8	1M	$0.876/M	$2.63/M	$0.0441/M	N/A	N/A	3.9s	39 tps

DeepSeek V4 Flash 0731

FP8

Context: 1.0M
Input /M: $0.43/M
Output /M: $1.29/M
Cache read /M: $0.0273/M
Cache write /M: N/A
Cache hit: 54.4%
TTFT: 1.1s
Throughput: 69 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

Context: 1.0M
Input /M: $0.43/M
Output /M: $1.29/M
Cache read /M: $0.0273/M
Cache write /M: N/A
Cache hit: 54.4%
TTFT: 1.1s
Throughput: 69 tps

DeepSeek V4 Pro

FP8

Context: 1.0M
Input /M: $1.68/M
Output /M: $3.36/M
Cache read /M: $0.142/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 2.2s
Throughput: 54 tps

DeepSeek V4 Pro 0813

FP8

Context: 1.0M
Input /M: $1.04/M
Output /M: $3.12/M
Cache read /M: $0.0346/M
Cache write /M: N/A
Cache hit: 84.5%
TTFT: 2.1s
Throughput: 49 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

Context: 1.0M
Input /M: $1.04/M
Output /M: $3.12/M
Cache read /M: $0.0346/M
Cache write /M: N/A
Cache hit: 19.9%
TTFT: 2.1s
Throughput: 49 tps

DeepSeek V4.1 Flash

FP8

Context: 1.0M
Input /M: $0.205/M
Output /M: $0.819/M
Cache read /M: $0.0041/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 1s
Throughput: 112 tps

DeepSeek V4.1 Flash (Thinking)

FP8

Context: 1.0M
Input /M: $0.205/M
Output /M: $0.819/M
Cache read /M: $0.0041/M
Cache write /M: N/A
Cache hit: 99%
TTFT: 1s
Throughput: 112 tps

DeepSeek V4.1 Flash 1017

FP8

Context: 1.0M
Input /M: $0.205/M
Output /M: $0.819/M
Cache read /M: $0.0041/M
Cache write /M: N/A
Cache hit: 88.7%
TTFT: 2.9s
Throughput: 78 tps

DeepSeek V4.1 Flash 1017 (Thinking)

FP8

Context: 1.0M
Input /M: $0.205/M
Output /M: $0.819/M
Cache read /M: $0.0041/M
Cache write /M: N/A
Cache hit: 88.7%
TTFT: 2.9s
Throughput: 78 tps

Gemma 4 26B A4B

BF16

Context: 262k
Input /M: $0.136/M
Output /M: $0.42/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 0.9s
Throughput: 161 tps

Gemma 4 26B A4B (Thinking)

BF16

Context: 262k
Input /M: $0.136/M
Output /M: $0.42/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 0.9s
Throughput: 161 tps

Gemma 4 31B

BF16

Context: 262k
Input /M: $0.147/M
Output /M: $0.42/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 1s
Throughput: 20 tps

Gemma 4 31B (Thinking)

BF16

Context: 262k
Input /M: $0.147/M
Output /M: $0.42/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 1s
Throughput: 20 tps

GLM 4.5 Air

BF16

Context: 131k
Input /M: $0.136/M
Output /M: $0.893/M
Cache read /M: $0.0262/M
Cache write /M: N/A
Cache hit: 45.6%
TTFT: 1.8s
Throughput: 45 tps

GLM 4.5 Air (Thinking)

BF16

Context: 131k
Input /M: $0.136/M
Output /M: $0.893/M
Cache read /M: $0.0262/M
Cache write /M: N/A
Cache hit: 45.6%
TTFT: 1.8s
Throughput: 45 tps

GLM 4.6

BF16

Context: 205k
Input /M: $0.578/M
Output /M: $2.31/M
Cache read /M: $0.116/M
Cache write /M: N/A
Cache hit: 82.5%
TTFT: 4.8s
Throughput: 26 tps

GLM 4.6 (Thinking)

BF16

Context: 205k
Input /M: $0.578/M
Output /M: $2.31/M
Cache read /M: $0.116/M
Cache write /M: N/A
Cache hit: 43.7%
TTFT: 4.8s
Throughput: 26 tps

GLM 4.7

FP8

Context: 205k
Input /M: $0.567/M
Output /M: $2.08/M
Cache read /M: $0.104/M
Cache write /M: N/A
Cache hit: 30.4%
TTFT: 4.3s
Throughput: 23 tps

GLM 4.7 (Thinking)

FP8

Context: 205k
Input /M: $0.567/M
Output /M: $2.08/M
Cache read /M: $0.104/M
Cache write /M: N/A
Cache hit: 30.4%
TTFT: 4.3s
Throughput: 23 tps

GLM 4.7 Flash

BF16

Context: 200k
Input /M: $0.0735/M
Output /M: $0.42/M
Cache read /M: $0.0105/M
Cache write /M: N/A
Cache hit: 70.5%
TTFT: 1.4s
Throughput: 48 tps

GLM 4.7 Flash (Thinking)

BF16

Context: 200k
Input /M: $0.0735/M
Output /M: $0.42/M
Cache read /M: $0.0105/M
Cache write /M: N/A
Cache hit: <0.1%
TTFT: 1.4s
Throughput: 48 tps

GLM 5

FP8

Context: 203k
Input /M: $1.05/M
Output /M: $3.36/M
Cache read /M: $0.21/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 1.7s
Throughput: 37 tps

GLM 5 (Thinking)

FP8

Context: 203k
Input /M: $1.05/M
Output /M: $3.36/M
Cache read /M: $0.21/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 1.7s
Throughput: 37 tps

GLM 5.1

FP8

Context: 205k
Input /M: $1.45/M
Output /M: $4.62/M
Cache read /M: $0.273/M
Cache write /M: N/A
Cache hit: 59.3%
TTFT: 3.7s
Throughput: 33 tps

GLM 5.1 (Thinking)

FP8

Context: 205k
Input /M: $1.45/M
Output /M: $4.62/M
Cache read /M: $0.273/M
Cache write /M: N/A
Cache hit: 59.3%
TTFT: 3.7s
Throughput: 33 tps

GLM 5.2

FP8

Context: 1.0M
Input /M: $1.47/M
Output /M: $4.62/M
Cache read /M: $0.273/M
Cache write /M: N/A
Cache hit: 33.4%
TTFT: 3.7s
Throughput: 44 tps

GLM 5.2 (Thinking)

FP8

Context: 1.0M
Input /M: $1.47/M
Output /M: $4.62/M
Cache read /M: $0.273/M
Cache write /M: N/A
Cache hit: 72.2%
TTFT: 3.7s
Throughput: 44 tps

GLM 5.3

FP8

Context: 1.0M
Input /M: $0.662/M
Output /M: $2.08/M
Cache read /M: $0.123/M
Cache write /M: N/A
Cache hit: 76.7%
TTFT: 2s
Throughput: 73 tps

GLM 5.3 (Thinking)

FP8

Context: 1.0M
Input /M: $0.662/M
Output /M: $2.08/M
Cache read /M: $0.123/M
Cache write /M: N/A
Cache hit: 76.7%
TTFT: 2s
Throughput: 73 tps

GLM 5.3 Flash

FP8

Context: 1.0M
Input /M: $0.0882/M
Output /M: $0.294/M
Cache read /M: $0.0176/M
Cache write /M: N/A
Cache hit: 78.5%
TTFT: 3.1s
Throughput: 36 tps

GPT OSS 120B

FP4

Context: 131k
Input /M: $0.0525/M
Output /M: $0.263/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 0.7s
Throughput: 151 tps

Kimi K2 Thinking

BF16

Context: 262k
Input /M: $0.63/M
Output /M: $2.63/M
Cache read /M: $0.157/M
Cache write /M: N/A
Cache hit: 65.7%
TTFT: 1.1s
Throughput: 46 tps

Kimi K2.5

Context: 262k
Input /M: $0.63/M
Output /M: $3.15/M
Cache read /M: $0.105/M
Cache write /M: N/A
Cache hit: 83.8%
TTFT: 2.4s
Throughput: 40 tps

Kimi K2.5 Thinking

Context: 262k
Input /M: $0.63/M
Output /M: $3.15/M
Cache read /M: $0.105/M
Cache write /M: N/A
Cache hit: 72%
TTFT: 2.4s
Throughput: 40 tps

Kimi K2.6

Context: 262k
Input /M: $0.84/M
Output /M: $3.57/M
Cache read /M: $0.168/M
Cache write /M: N/A
Cache hit: 91.5%
TTFT: 3.2s
Throughput: 38 tps

Kimi K2.6 Thinking

Context: 262k
Input /M: $0.84/M
Output /M: $3.57/M
Cache read /M: $0.168/M
Cache write /M: N/A
Cache hit: 91.5%
TTFT: 3.2s
Throughput: 38 tps

Kimi K2.7 Code

INT4

Context: 262k
Input /M: $0.998/M
Output /M: $4.20/M
Cache read /M: $0.20/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 3.2s
Throughput: 28.5 tps

Kimi K3

Context: 1.0M
Input /M: $3.15/M
Output /M: $15.75/M
Cache read /M: $0.315/M
Cache write /M: $3.15/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Ling 3.0 Flash

Context: 262k
Input /M: $0.075/M
Output /M: $0.22/M
Cache read /M: $0.015/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Ling 3.0 Flash Thinking

Context: 262k
Input /M: $0.075/M
Output /M: $0.22/M
Cache read /M: $0.015/M
Cache write /M: N/A
Cache hit: N/A
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: $0.012/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Llama 3.1 8B

FP8

Context: 16k
Input /M: $0.021/M
Output /M: $0.0525/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 0.5s
Throughput: 104 tps

Llama 3.3 70B Instruct

BF16

Context: 12k
Input /M: $0.142/M
Output /M: $0.42/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 1.3s
Throughput: 39 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 write /M: N/A
Cache hit: N/A
TTFT: 3.7s
Throughput: 28 tps

MiMo V2.6 Pro

FP8

Context: 1.0M
Input /M: $0.457/M
Output /M: $0.913/M
Cache read /M: $0.0038/M
Cache write /M: N/A
Cache hit: 15.1%
TTFT: 4.9s
Throughput: 33 tps

MiniMax M2.5

FP8

Context: 205k
Input /M: $0.315/M
Output /M: $1.26/M
Cache read /M: $0.0315/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 1s
Throughput: 45.5 tps

MiniMax M2.7

FP8

Context: 205k
Input /M: $0.315/M
Output /M: $1.26/M
Cache read /M: $0.063/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 1.3s
Throughput: 28 tps

MiniMax M3

FP8

Context: 1M
Input /M: $0.315/M
Output /M: $1.26/M
Cache read /M: $0.063/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 2.5s
Throughput: 80.5 tps

Above 524k tokens: in $0.63/M · out $2.52/M · cache read $0.126/M

MiniMax M3 Thinking

FP8

Context: 1M
Input /M: $0.315/M
Output /M: $1.26/M
Cache read /M: $0.063/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 2.5s
Throughput: 80.5 tps

Above 524k tokens: in $0.63/M · out $2.52/M · cache read $0.126/M

MiniMax M3.1 Flash

Context: 1M
Input /M: $0.157/M
Output /M: $0.63/M
Cache read /M: $0.0158/M
Cache write /M: N/A
Cache hit: 23%
TTFT: 2.6s
Throughput: 88.1 tps

Qwen 3.6 27B

Context: 262k
Input /M: $0.63/M
Output /M: $3.78/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: 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
Cache write /M: N/A
Cache hit: 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
Cache write /M: N/A
Cache hit: N/A
TTFT: 4.7s
Throughput: 62 tps

Qwen3.5 122B A10B Thinking

BF16

Context: 262k
Input /M: $0.42/M
Output /M: $3.36/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 4.7s
Throughput: 62 tps

Qwen3.5 27B

BF16

Context: 262k
Input /M: $0.315/M
Output /M: $2.52/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 2s
Throughput: 46 tps

Qwen3.5 27B Thinking

BF16

Context: 262k
Input /M: $0.315/M
Output /M: $2.52/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: 2s
Throughput: 46 tps

Qwen3.5 35B A3B

Context: 262k
Input /M: $0.263/M
Output /M: $2.10/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Qwen3.5 35B A3B Thinking

Context: 262k
Input /M: $0.263/M
Output /M: $2.10/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: 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
Cache write /M: N/A
Cache hit: N/A
TTFT: 1.8s
Throughput: 53 tps

Qwen3.5 397B Thinking

Context: 262k
Input /M: $0.63/M
Output /M: $3.78/M
Cache read /M: N/A
Cache write /M: N/A
Cache hit: 0%
TTFT: 1.8s
Throughput: 53 tps

Qwen3.8 27B

Context: 1M
Input /M: $0.441/M
Output /M: $3.15/M
Cache read /M: $0.0892/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 3.9s
Throughput: 39 tps

Qwen3.8 27B Thinking

Context: 1M
Input /M: $0.441/M
Output /M: $3.15/M
Cache read /M: $0.0892/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 3.9s
Throughput: 39 tps

Qwen3.8 Max

Context: 1M
Input /M: $2.10/M
Output /M: $6.30/M
Cache read /M: $0.263/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 2.6s
Throughput: 40 tps

Qwen3.8 Max Thinking

Context: 1M
Input /M: $2.10/M
Output /M: $6.30/M
Cache read /M: $0.263/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 2.6s
Throughput: 40 tps

Step 3.7 Flash Thinking

FP8

Context: 262k
Input /M: $0.21/M
Output /M: $1.21/M
Cache read /M: $0.042/M
Cache write /M: N/A
Cache hit: <0.1%
TTFT: 5.6s
Throughput: 32 tps

Step 5 Preview

Context: 1M
Input /M: $1.05/M
Output /M: $2.84/M
Cache read /M: $0.105/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Tencent Hy3

Context: 262k
Input /M: $0.066/M
Output /M: $0.26/M
Cache read /M: $0.029/M
Cache write /M: N/A
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Tencent Hy4 Preview

FP8

Context: 1M
Input /M: $0.876/M
Output /M: $2.63/M
Cache read /M: $0.0441/M
Cache write /M: N/A
Cache hit: N/A
TTFT: 3.9s
Throughput: 39 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/deepseek-v4-flash-0731: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