OpenAI compatible API. Attested gateway. Public status.

Novita AI

Novita AI models on TrustedRouter with prices, routes, policy notes, and source links.

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`novita`

No provider claim

All providers

Provider	Novita AI
Models	105 public models
Prepaid routes	86
BYOK routes	105
Zero data retention	not claimed
Confidential compute	not claimed
Provider E2EE	not claimed
Policy note	No provider-ZDR claim is tracked here. Novita's privacy policy says personal information is not used for model training; customer-content processing is governed by customer agreements. Policy source

Measured performance

308 samples

Continuously sampled across Novita AI's routed models — p50 TTFT, throughput, and success rate. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	1155 ms
Throughput	29 tok/s
Uptime	58.12%

Model	p50 TTFT	p50 TTFB	Throughput	Uptime	Config excluded	Samples
moonshotai/kimi-k2.6	582 ms	580 ms	—	40.00%	—	5
meta-llama/llama-3.3-70b-instruct	596 ms	594 ms	—	25.00%	—	4
qwen/qwen3-vl-8b-instruct	600 ms	599 ms	—	50.00%	—	2
sao10k/l3-8b-lunaris	705 ms	704 ms	—	33.33%	—	3
sao10k/l31-70b-euryale-v2.2	798 ms	797 ms	—	50.00%	—	4
qwen/qwen-2.5-72b-instruct	813 ms	812 ms	—	66.67%	—	3
deepseek/deepseek-ocr-2	863 ms	862 ms	—	33.33%	—	3
openai/gpt-oss-20b	914 ms	911 ms	—	83.33%	—	6
meta-llama/llama-4-scout-17b-16e-instruct	915 ms	812 ms	—	40.00%	—	5
qwen/qwen3-vl-30b-a3b-instruct	958 ms	957 ms	—	66.67%	—	3
meta-llama/llama-3.1-8b-instruct	972 ms	971 ms	—	33.33%	—	3
qwen/qwen3-vl-30b-a3b-thinking	996 ms	995 ms	—	100.00%	—	1
Sao10K/L3-8B-Stheno-v3.2	1006 ms	999 ms	—	75.00%	—	4
moonshotai/kimi-k2.7-code	1049 ms	1048 ms	29 tok/s	100.00%	—	54
qwen/qwen3.6-27b	1079 ms	1058 ms	—	100.00%	—	3
qwen/qwen-mt-plus	1081 ms	978 ms	—	75.00%	—	4
qwen/qwen3-vl-235b-a22b-instruct	1082 ms	978 ms	—	57.14%	—	7
qwen/qwen3.5-397b-a17b	1099 ms	1096 ms	—	20.00%	—	5
inclusionai/ling-2.6-1t	1116 ms	1114 ms	—	100.00%	—	2
qwen/qwen3-235b-a22b-instruct-2507	1143 ms	1141 ms	—	66.67%	—	3
deepseek/deepseek-v3.2	1147 ms	1145 ms	—	100.00%	—	2
moonshotai/kimi-k2-thinking	1155 ms	1052 ms	—	40.00%	—	5
minimax/minimax-m2.1	1185 ms	1184 ms	—	33.33%	—	3
qwen/qwen3-omni-30b-a3b-instruct	1202 ms	1201 ms	—	100.00%	—	1
openai/gpt-oss-120b	1224 ms	1121 ms	—	50.00%	—	2
qwen/qwen3.5-122b-a10b	1244 ms	1141 ms	—	100.00%	—	1
qwen/qwen3-coder-next	1253 ms	1252 ms	—	80.00%	—	5
google/gemma-4-26b-a4b-it	1354 ms	1250 ms	—	100.00%	—	2
qwen/qwen3.5-35b-a3b	1417 ms	1314 ms	—	75.00%	—	4
inclusionai/ling-2.6-flash	1457 ms	1354 ms	—	60.00%	—	5
qwen/qwen3-coder-480b-a35b-instruct	1460 ms	1459 ms	10 tok/s	63.64%	—	11
minimax/minimax-m2.7	1465 ms	1463 ms	—	33.33%	—	3
zai-org/glm-4.5	1472 ms	1369 ms	—	50.00%	—	2
inclusionai/ring-2.6-1t	1476 ms	1374 ms	—	50.00%	—	2
qwen/qwen3.5-27b	1547 ms	1442 ms	—	60.00%	—	5
deepseek/deepseek-v4-pro	1557 ms	1453 ms	—	75.00%	—	4
qwen/qwen3.6-35b-a3b	1597 ms	1595 ms	—	100.00%	—	4
deepseek/deepseek-ocr	1611 ms	1508 ms	—	40.00%	—	5
deepseek/deepseek-r1-turbo	1622 ms	1620 ms	—	100.00%	—	1
microsoft/wizardlm-2-8x22b	1635 ms	1533 ms	—	50.00%	—	2
zai-org/glm-4.7	1640 ms	1639 ms	—	66.67%	—	3
moonshotai/kimi-k2.5	1652 ms	1548 ms	—	66.67%	—	3
qwen/qwen3-coder-30b-a3b-instruct	1663 ms	1561 ms	—	75.00%	—	4
minimaxai/minimax-m1-80k	1673 ms	1570 ms	—	60.00%	—	5
baidu/ernie-4.5-vl-424b-a47b	1682 ms	1577 ms	—	66.67%	—	3
moonshotai/kimi-k2-instruct	1682 ms	1681 ms	—	100.00%	—	1
qwen/qwen3-235b-a22b-fp8	1714 ms	1712 ms	—	100.00%	—	1
deepseek/deepseek-v3-0324	1752 ms	1649 ms	—	16.67%	—	6
zai-org/glm-4.5v	1796 ms	1692 ms	—	33.33%	—	3
zai-org/glm-4.5-air	1852 ms	1749 ms	—	100.00%	—	1
qwen/qwen3-max	1852 ms	1748 ms	—	100.00%	—	1
qwen/qwen3-next-80b-a3b-thinking	1893 ms	1791 ms	—	75.00%	—	4
minimax/minimax-m2	2041 ms	1936 ms	—	50.00%	—	4
meta-llama/llama-3-70b-instruct	2092 ms	1990 ms	—	100.00%	—	3
deepseek/deepseek-r1-0528	2105 ms	2002 ms	19 tok/s	42.86%	—	7
google/gemma-4-31b-it	2138 ms	2036 ms	—	100.00%	—	1
deepseek/deepseek-v3.1-terminus	2140 ms	2138 ms	—	100.00%	—	2
deepseek/deepseek-v3.1	2147 ms	2145 ms	—	33.33%	—	3
zai-org/glm-4.6	2236 ms	2234 ms	—	50.00%	—	2
minimax/minimax-m2.5-highspeed	2330 ms	2226 ms	—	100.00%	—	5
meta-llama/llama-4-maverick-17b-128e-instruct-fp8	2392 ms	2289 ms	—	50.00%	—	6
qwen/qwen3-vl-235b-a22b-thinking	—	—	—	0.00%	—	2
deepseek/deepseek-prover-v2-671b	—	—	—	0.00%	—	2
zai-org/glm-5	—	—	—	0.00%	—	2
zai-org/glm-5.1	—	—	—	0.00%	—	3
google/gemma-3-12b-it	—	—	—	0.00%	—	2
zai-org/autoglm-phone-9b-multilingual	—	—	—	0.00%	—	1
deepseek/deepseek-v3-turbo	—	—	—	0.00%	—	1
zai-org/glm-4.6v	—	—	—	0.00%	—	4
moonshotai/kimi-k2-0905	—	—	—	0.00%	—	1
deepseek/deepseek-r1-distill-llama-70b	—	—	—	0.00%	—	2
baidu/ernie-4.5-21B-a3b	—	—	—	0.00%	—	3
deepseek/deepseek-v3.2-exp	—	—	—	0.00%	—	2
minimax/minimax-m2.5	—	—	—	0.00%	—	1
mistralai/mistral-nemo	—	—	—	0.00%	—	3
qwen/qwen3-235b-a22b-thinking-2507	—	—	—	0.00%	—	4
baidu/ernie-4.5-vl-28b-a3b	—	—	—	0.00%	—	4
kwaipilot/kat-coder-pro	—	—	—	0.00%	—	3
deepseek/deepseek-v4-flash	—	—	—	0.00%	—	2
baichuan/baichuan-m2-32b	—	—	—	0.00%	—	2
elephant	—	—	—	0.00%	—	3

Full provider & model leaderboard.

Provider models

Models served by Novita AI.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	Context	Endpoints	Prompt	Completion	Routes
`Sao10K/L3-8B-Stheno-v3.2` L3 8B Stheno V3.2 benchmarks performance api	8,192	2	$0.055/1M	$0.055/1M	prepaid BYOK
`baichuan/baichuan-m2-32b` BaiChuan M2 32B benchmarks performance api	131,072	2	$0.077/1M	$0.077/1M	prepaid BYOK
`baidu/ernie-4.5-21B-a3b` ERNIE 4.5 21B A3B benchmarks performance api	120,000	2	$0.077/1M	$0.308/1M	prepaid BYOK
`baidu/ernie-4.5-21B-a3b-thinking` ERNIE-4.5-21B-A3B-Thinking benchmarks performance api	131,072	1	$0.077/1M	$0.308/1M	BYOK
`baidu/ernie-4.5-300b-a47b-paddle` ERNIE 4.5 300B A47B benchmarks performance api	123,000	1	$0.308/1M	$1.21/1M	BYOK
`baidu/ernie-4.5-vl-28b-a3b` ERNIE 4.5 VL 28B A3B benchmarks performance api	30,000	2	$0.154/1M	$0.616/1M	prepaid BYOK
`baidu/ernie-4.5-vl-28b-a3b-thinking` ERNIE-4.5-VL-28B-A3B-Thinking benchmarks performance api	131,072	1	$0.429/1M	$0.429/1M	BYOK
`baidu/ernie-4.5-vl-424b-a47b` ERNIE 4.5 VL 424B A47B benchmarks performance api	123,000	2	$0.462/1M	$1.375/1M	prepaid BYOK
`deepseek/deepseek-ocr` DeepSeek-OCR benchmarks performance api	8,192	2	$0.033/1M	$0.033/1M	prepaid BYOK
`deepseek/deepseek-ocr-2` DeepSeek-OCR 2 benchmarks performance api	8,192	2	$0.033/1M	$0.033/1M	prepaid BYOK
`deepseek/deepseek-prover-v2-671b` Deepseek Prover V2 671B benchmarks performance api	160,000	2	$0.77/1M	$2.75/1M	prepaid BYOK
`deepseek/deepseek-r1-0528` DeepSeek R1 0528 benchmarks performance api	163,840	2	$0.77/1M	$2.75/1M	prepaid BYOK
`deepseek/deepseek-r1-0528-qwen3-8b` DeepSeek R1 0528 Qwen3 8B benchmarks performance api	128,000	1	$0.066/1M	$0.099/1M	BYOK
`deepseek/deepseek-r1-distill-llama-70b` DeepSeek R1 Distill LLama 70B benchmarks performance api	8,192	2	$0.88/1M	$0.88/1M	prepaid BYOK
`deepseek/deepseek-r1-distill-qwen-14b` DeepSeek R1 Distill Qwen 14B benchmarks performance api	32,768	1	$0.165/1M	$0.165/1M	BYOK
`deepseek/deepseek-r1-distill-qwen-32b` DeepSeek R1 Distill Qwen 32B benchmarks performance api	64,000	1	$0.33/1M	$0.33/1M	BYOK
`deepseek/deepseek-r1-turbo` DeepSeek R1 (Turbo) benchmarks performance api	64,000	2	$0.77/1M	$2.75/1M	prepaid BYOK
`deepseek/deepseek-v3-0324` DeepSeek V3 0324 benchmarks performance api	163,840	2	$0.297/1M	$1.232/1M	prepaid BYOK
`deepseek/deepseek-v3-turbo` DeepSeek V3 (Turbo) benchmarks performance api	64,000	2	$0.44/1M	$1.43/1M	prepaid BYOK
`deepseek/deepseek-v3.1` DeepSeek V3.1 benchmarks performance api	131,072	2	$0.297/1M	$1.1/1M	prepaid BYOK
`deepseek/deepseek-v3.1-terminus` Deepseek V3.1 Terminus benchmarks performance api	131,072	2	$0.297/1M	$1.1/1M	prepaid BYOK
`deepseek/deepseek-v3.2` DeepSeek: DeepSeek V3.2 benchmarks performance api	163,840	2	$0.2959/1M	$0.44/1M	prepaid BYOK
`deepseek/deepseek-v3.2-exp` Deepseek V3.2 Exp benchmarks performance api	163,840	2	$0.297/1M	$0.451/1M	prepaid BYOK
`deepseek/deepseek-v4-flash` DeepSeek: DeepSeek V4 Flash benchmarks performance api	1,048,576	2	$0.154/1M	$0.308/1M	prepaid BYOK
`deepseek/deepseek-v4-pro` DeepSeek: DeepSeek V4 Pro benchmarks performance api	1,048,576	2	$1.859/1M	$3.718/1M	prepaid BYOK
`elephant` Ling-2.6-flash benchmarks performance api	262,144	2	$0.11/1M	$0.33/1M	prepaid BYOK
`google/gemma-3-12b-it` Google: Gemma 3 12B benchmarks performance api	131,072	2	$0.055/1M	$0.11/1M	prepaid BYOK
`google/gemma-3-27b-it` Google: Gemma 3 27B benchmarks performance api	131,072	2	$0.1309/1M	$0.22/1M	prepaid BYOK
`google/gemma-4-26b-a4b-it` Google: Gemma 4 26B A4B benchmarks performance api	262,144	2	$0.143/1M	$0.44/1M	prepaid BYOK
`google/gemma-4-31b-it` Google: Gemma 4 31B benchmarks performance api	262,144	2	$0.154/1M	$0.44/1M	prepaid BYOK
`gryphe/mythomax-l2-13b` Mythomax L2 13B benchmarks performance api	4,096	1	$0.099/1M	$0.099/1M	BYOK
`inclusionai/ling-2.6-1t` Ling-2.6-1T benchmarks performance api	262,144	2	$0.33/1M	$2.75/1M	prepaid BYOK
`inclusionai/ling-2.6-flash` Ling-2.6-flash benchmarks performance api	262,144	2	$0.11/1M	$0.33/1M	prepaid BYOK
`inclusionai/ring-2.6-1t` Ring-2.6-1T benchmarks performance api	262,144	2	$0.01/1M	$0.01/1M	prepaid BYOK
`kwaipilot/kat-coder-pro` Kat Coder Pro benchmarks performance api	256,000	2	$0.33/1M	$1.32/1M	prepaid BYOK
`meta-llama/llama-3-70b-instruct` Llama3 70B Instruct benchmarks performance api	8,192	2	$0.561/1M	$0.814/1M	prepaid BYOK
`meta-llama/llama-3-8b-instruct` Llama 3 8B Instruct benchmarks performance api	8,192	1	$0.044/1M	$0.044/1M	BYOK
`meta-llama/llama-3.1-8b-instruct` Meta: Llama 3.1 8B Instruct benchmarks performance api	131,072	2	$0.022/1M	$0.055/1M	prepaid BYOK
`meta-llama/llama-3.2-3b-instruct` Llama 3.2 3B Instruct benchmarks performance api	32,768	1	$0.033/1M	$0.055/1M	BYOK
`meta-llama/llama-3.3-70b-instruct` Meta: Llama 3.3 70B Instruct benchmarks performance api	131,072	2	$0.1485/1M	$0.44/1M	prepaid BYOK
`meta-llama/llama-4-maverick-17b-128e-instruct-fp8` Llama 4 Maverick Instruct benchmarks performance api	1,048,576	2	$0.297/1M	$0.935/1M	prepaid BYOK
`meta-llama/llama-4-scout-17b-16e-instruct` Llama 4 Scout Instruct benchmarks performance api	131,072	2	$0.198/1M	$0.649/1M	prepaid BYOK
`microsoft/wizardlm-2-8x22b` Wizardlm 2 8x22B benchmarks performance api	65,535	2	$0.682/1M	$0.682/1M	prepaid BYOK
`minimax/minimax-m2` MiniMax M2 benchmarks performance api	204,800	2	$0.33/1M	$1.32/1M	prepaid BYOK
`minimax/minimax-m2.1` MiniMax M2.1 benchmarks performance api	204,800	2	$0.33/1M	$1.32/1M	prepaid BYOK
`minimax/minimax-m2.5` MiniMax: MiniMax M2.5 benchmarks performance api	204,800	2	$0.33/1M	$1.32/1M	prepaid BYOK
`minimax/minimax-m2.5-highspeed` MiniMax M2.5 highspeed benchmarks performance api	204,800	2	$0.66/1M	$2.64/1M	prepaid BYOK
`minimax/minimax-m2.7` MiniMax M2.7 benchmarks performance api	204,800	2	$0.33/1M	$1.32/1M	prepaid BYOK
`minimaxai/minimax-m1-80k` MiniMax M1 benchmarks performance api	1,000,000	2	$0.605/1M	$2.42/1M	prepaid BYOK
`mistralai/mistral-nemo` Mistral: Mistral Nemo benchmarks performance api	131,072	2	$0.044/1M	$0.187/1M	prepaid BYOK
`moonshotai/kimi-k2-0905` Kimi K2 0905 benchmarks performance api	262,144	2	$0.66/1M	$2.75/1M	prepaid BYOK
`moonshotai/kimi-k2-instruct` Kimi K2 Instruct benchmarks performance api	131,072	2	$0.627/1M	$2.53/1M	prepaid BYOK
`moonshotai/kimi-k2-thinking` Kimi K2 Thinking benchmarks performance api	262,144	2	$0.66/1M	$2.75/1M	prepaid BYOK
`moonshotai/kimi-k2.5` MoonshotAI: Kimi K2.5 benchmarks performance api	262,144	2	$0.66/1M	$3.3/1M	prepaid BYOK
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks performance api	262,144	2	$0.88/1M	$3.74/1M	prepaid BYOK
`moonshotai/kimi-k2.7-code` MoonshotAI: Kimi K2.7 Code benchmarks performance api	262,144	2	$1.045/1M	$4.4/1M	prepaid BYOK
`nousresearch/hermes-2-pro-llama-3-8b` Hermes 2 Pro Llama 3 8B benchmarks performance api	8,192	1	$0.154/1M	$0.154/1M	BYOK
`openai/gpt-oss-120b` OpenAI: gpt-oss-120b benchmarks performance api	131,072	2	$0.055/1M	$0.275/1M	prepaid BYOK
`openai/gpt-oss-20b` OpenAI: gpt-oss-20b benchmarks performance api	131,072	2	$0.044/1M	$0.165/1M	prepaid BYOK
`paddlepaddle/paddleocr-vl` PaddleOCR-VL benchmarks performance api	16,384	1	$0.022/1M	$0.022/1M	BYOK
`qwen/qwen-2.5-72b-instruct` Qwen2.5 72B Instruct benchmarks performance api	131,072	2	$0.418/1M	$0.44/1M	prepaid BYOK
`qwen/qwen-mt-plus` Qwen MT Plus benchmarks performance api	16,384	2	$0.275/1M	$0.825/1M	prepaid BYOK
`qwen/qwen2.5-7b-instruct` Qwen2.5 7B Instruct benchmarks performance api	32,000	1	$0.077/1M	$0.077/1M	BYOK
`qwen/qwen2.5-vl-72b-instruct` Qwen: Qwen2.5 VL 72B Instruct benchmarks performance api	131,072	1	$0.88/1M	$0.88/1M	BYOK
`qwen/qwen3-235b-a22b-fp8` Qwen3 235B A22B benchmarks performance api	40,960	2	$0.22/1M	$0.88/1M	prepaid BYOK
`qwen/qwen3-235b-a22b-instruct-2507` Qwen3 235B A22B Instruct 2507 benchmarks performance api	131,072	2	$0.099/1M	$0.638/1M	prepaid BYOK
`qwen/qwen3-235b-a22b-thinking-2507` Qwen: Qwen3 235B A22B Thinking 2507 benchmarks performance api	262,144	2	$0.33/1M	$3.3/1M	prepaid BYOK
`qwen/qwen3-30b-a3b-fp8` Qwen3 30B A3B benchmarks performance api	40,960	1	$0.099/1M	$0.495/1M	BYOK
`qwen/qwen3-32b-fp8` Qwen3 32B benchmarks performance api	40,960	1	$0.11/1M	$0.495/1M	BYOK
`qwen/qwen3-4b-fp8` Qwen3 4B benchmarks performance api	128,000	1	$0.033/1M	$0.033/1M	BYOK
`qwen/qwen3-8b-fp8` Qwen3 8B benchmarks performance api	128,000	1	$0.0385/1M	$0.1518/1M	BYOK
`qwen/qwen3-coder-30b-a3b-instruct` Qwen3 Coder 30b A3B Instruct benchmarks performance api	160,000	2	$0.077/1M	$0.297/1M	prepaid BYOK
`qwen/qwen3-coder-480b-a35b-instruct` Qwen3 Coder 480B A35B Instruct benchmarks performance api	262,144	2	$0.418/1M	$1.705/1M	prepaid BYOK
`qwen/qwen3-coder-next` Qwen: Qwen3 Coder Next benchmarks performance api	262,144	2	$0.22/1M	$1.65/1M	prepaid BYOK
`qwen/qwen3-max` Qwen3 Max benchmarks performance api	262,144	2	$2.321/1M	$9.295/1M	prepaid BYOK
`qwen/qwen3-next-80b-a3b-instruct` Qwen: Qwen3 Next 80B A3B Instruct benchmarks performance api	262,144	2	$0.165/1M	$1.65/1M	prepaid BYOK
`qwen/qwen3-next-80b-a3b-thinking` Qwen3 Next 80B A3B Thinking benchmarks performance api	131,072	2	$0.165/1M	$1.65/1M	prepaid BYOK
`qwen/qwen3-omni-30b-a3b-instruct` Qwen3 Omni 30B A3B Instruct benchmarks performance api	65,536	2	$0.01/1M	$0.01/1M	prepaid BYOK
`qwen/qwen3-omni-30b-a3b-thinking` Qwen3 Omni 30B A3B Thinking benchmarks performance api	65,536	2	$0.01/1M	$0.01/1M	prepaid BYOK
`qwen/qwen3-vl-235b-a22b-instruct` Qwen: Qwen3 VL 235B A22B Instruct benchmarks performance api	262,144	2	$0.33/1M	$1.65/1M	prepaid BYOK
`qwen/qwen3-vl-235b-a22b-thinking` Qwen3 VL 235B A22B Thinking benchmarks performance api	131,072	2	$1.078/1M	$4.345/1M	prepaid BYOK
`qwen/qwen3-vl-30b-a3b-instruct` Qwen: Qwen3 VL 30B A3B Instruct benchmarks performance api	262,144	2	$0.22/1M	$0.77/1M	prepaid BYOK
`qwen/qwen3-vl-30b-a3b-thinking` qwen/qwen3-vl-30b-a3b-thinking benchmarks performance api	131,072	2	$0.22/1M	$1.1/1M	prepaid BYOK
`qwen/qwen3-vl-8b-instruct` Qwen: Qwen3 VL 8B Instruct benchmarks performance api	262,144	2	$0.088/1M	$0.55/1M	prepaid BYOK
`qwen/qwen3.5-122b-a10b` Qwen3.5-122B-A10B benchmarks performance api	262,144	2	$0.44/1M	$3.52/1M	prepaid BYOK
`qwen/qwen3.5-27b` Qwen: Qwen3.5-27B benchmarks performance api	262,144	2	$0.33/1M	$2.64/1M	prepaid BYOK
`qwen/qwen3.5-35b-a3b` Qwen: Qwen3.5-35B-A3B benchmarks performance api	262,144	2	$0.275/1M	$2.2/1M	prepaid BYOK
`qwen/qwen3.5-397b-a17b` Qwen: Qwen3.5 397B A17B benchmarks performance api	262,144	2	$0.66/1M	$3.96/1M	prepaid BYOK
`qwen/qwen3.6-27b` Qwen: Qwen3.6 27B benchmarks performance api	262,144	2	$0.66/1M	$3.96/1M	prepaid BYOK
`qwen/qwen3.6-35b-a3b` Qwen: Qwen3.6 35B A3B benchmarks performance api	262,144	2	$0.2728/1M	$1.6335/1M	prepaid BYOK
`sao10k/l3-70b-euryale-v2.1` L3 70B Euryale V2.1 benchmarks performance api	8,192	1	$1.628/1M	$1.628/1M	BYOK
`sao10k/l3-8b-lunaris` Sao10k L3 8B Lunaris benchmarks performance api	8,192	2	$0.055/1M	$0.055/1M	prepaid BYOK
`sao10k/l31-70b-euryale-v2.2` L31 70B Euryale V2.2 benchmarks performance api	8,192	2	$1.628/1M	$1.628/1M	prepaid BYOK
`xiaomimimo/mimo-v2-flash` XiaomiMiMo/MiMo-V2-Flash benchmarks performance api	262,144	1	$0.11/1M	$0.33/1M	BYOK
`xiaomimimo/mimo-v2.5-pro` XiaomiMiMo/MiMo-V2.5-Pro benchmarks performance api	1,048,576	2	$2.2/1M	$6.6/1M	prepaid BYOK
`zai-org/autoglm-phone-9b-multilingual` AutoGLM-Phone-9B-Multilingual benchmarks performance api	65,536	2	$0.0385/1M	$0.1518/1M	prepaid BYOK
`zai-org/glm-4.5` GLM-4.5 benchmarks performance api	131,072	2	$0.66/1M	$2.42/1M	prepaid BYOK
`zai-org/glm-4.5-air` zai-org/glm-4.5-air benchmarks performance api	131,072	2	$0.143/1M	$0.935/1M	prepaid BYOK
`zai-org/glm-4.5v` GLM 4.5V benchmarks performance api	65,536	2	$0.66/1M	$1.98/1M	prepaid BYOK
`zai-org/glm-4.6` GLM 4.6 benchmarks performance api	204,800	2	$0.605/1M	$2.42/1M	prepaid BYOK
`zai-org/glm-4.6v` GLM 4.6V benchmarks performance api	131,072	2	$0.33/1M	$0.99/1M	prepaid BYOK
`zai-org/glm-4.7` GLM-4.7 benchmarks performance api	204,800	2	$0.66/1M	$2.42/1M	prepaid BYOK
`zai-org/glm-4.7-flash` GLM-4.7-Flash benchmarks performance api	200,000	2	$0.077/1M	$0.44/1M	prepaid BYOK
`zai-org/glm-5` GLM-5 benchmarks performance api	202,800	2	$1.1/1M	$3.52/1M	prepaid BYOK
`zai-org/glm-5.1` GLM-5.1 benchmarks performance api	204,800	2	$1.518/1M	$4.84/1M	prepaid BYOK