ZERNO · Модели

Сколько стоит миллион токенов

Claude, GPT, Gemini и ещё сотни моделей — по одному ключу и с рублёвого счёта, без абонплаты и зарубежной карты. В таблице цена за миллион токенов по курсу ЦБ.

В таблице наша цена в рублях — та, по которой спишутся деньги. Абонплаты нет, списываем по факту токенов. Рядом показываем цены других сервисов доступа: есть с чем сравнить. Цены обновлены 2026-09-07, курс 86.59 ₽ за доллар на 05.09.2026, по данным ЦБ.

Загружаем цены…

Создать аккаунт ВойтиКлюч выдаётся сразу после регистрации, абонплаты нет.

api.zerno.one · логи запросовВыгрузить CSV

Время	Модель	Вход	Выход	Стоимость	Задержка	Код
14:02:19	gpt-5.2	8 460	1 104	3,78 ₽	2 870 мс	200
14:02:23	claude-sonnet-5	5 240	418	1,83 ₽	1 320 мс	200
14:02:28	gpt-5.2	8 460	—	1,85 ₽	180 мс	429
14:02:29	gpt-5.2	8 460	964	3,54 ₽	2 410 мс	200
14:02:35	deepseek-v4-pro	21 400	3 180	4,59 ₽	5 240 мс	200
14:02:41	gemini-2.5-pro	9 880	1 460	3,37 ₽	3 120 мс	200
14:02:47	claude-opus-5	6 420	594	5,87 ₽	2 180 мс	200
14:02:52	gemini-2.5-flash	2 240	186	0,14 ₽	480 мс	200

Раздел «Логи» в кабинете шлюза: стоимость каждой строки считается из этих же цен за миллион токенов.

Разброс цен

Миллион токенов стоит от 0.52 ₽ до 34 093 ₽

Разница между моделями — это счёт в конце месяца. По горизонтали цена за миллион токенов при обычном диалоге: три токена вопроса на один токен ответа. У моделей без ответа в токенах — эмбеддингов и реранкеров — это цена входа: смешивать им нечего.

В разброс не вошли 31 бесплатных моделей; 107 моделей, у которых счёт идёт не в токенах: распознавание речи считают по минутам аудио, синтез — по символам, картинки и видео — по кадрам.

Сравнить цены сервисов

$1.00 — $1.47 /M47 моделей в этой вилке · здесь медиана каталога

$0.00$0.01$0.10$1$10$1000

Дешевле всех0.52 ₽Perplexity: Embed V1 0.6B

Медиана каталога97.41 ₽Google: Gemini 3.8 Flash (batch)

Дороже всех34 093 ₽OpenAI: o1-pro

Модель	Вход, ₽ / 1Mцена ZERNO	Выход, ₽ / 1Mцена ZERNO	Дешевле всего у	Контекст
Perplexity: Embed V1 0.6Bperplexity/pplx-embed-v1-0.6b	0.520	0	0.520ZERNO	32 000
BAAI: bge-base-en-v1.5baai/bge-base-en-v1.5	0.649	0	0.649ZERNO	512
Intfloat: E5-Base-v2intfloat/e5-base-v2	0.649	0	0.649ZERNO	512
Sentence Transformers: all-MiniLM-L12-v2sentence-transformers/all-minilm-l12-v2	0.649	0	0.649ZERNO	512
Sentence Transformers: all-MiniLM-L6-v2sentence-transformers/all-minilm-l6-v2	0.649	0	0.649ZERNO	512
Sentence Transformers: all-mpnet-base-v2sentence-transformers/all-mpnet-base-v2	0.649	0	0.649ZERNO	512
Sentence Transformers: multi-qa-mpnet-base-dot-v1sentence-transformers/multi-qa-mpnet-base-dot-v1	0.649	0	0.649ZERNO	512
Sentence Transformers: paraphrase-MiniLM-L6-v2sentence-transformers/paraphrase-minilm-l6-v2	0.649	0	0.649ZERNO	512
Thenlper: GTE-Basethenlper/gte-base	0.649	0	0.649ZERNO	512
BAAI: bge-large-en-v1.5baai/bge-large-en-v1.5	1.30	0	1.30ZERNO	512
BAAI: bge-m3baai/bge-m3	1.30	0	1.30ZERNO	8 194
inclusionAI: Ling-2.6-flashinclusionai/ling-2.6-flash	1.30	3.90	1.30ZERNO	262 144
Intfloat: E5-Large-v2intfloat/e5-large-v2	1.30	0	1.30ZERNO	512
Intfloat: Multilingual-E5-Largeintfloat/multilingual-e5-large	1.30	0	1.30ZERNO	512
OpenAI: Text Embedding 3 Small (batch)openai/text-embedding-3-small:batch	1.30	0	1.30ZERNO	8 192
Qwen: Qwen3 Embedding 8Bqwen/qwen3-embedding-8b	1.30	0	1.30ZERNO	32 768
Thenlper: GTE-Largethenlper/gte-large	1.30	0	1.30ZERNO	512
IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro	2.21	14.55	2.21ZERNO	131 000
Mistral: Mistral Nemomistralai/mistral-nemo	2.47	3.90	3.89AITunnel	131 072
OpenAI: Text Embedding 3 Smallopenai/text-embedding-3-small	2.60	0	2.60ZERNO	8 192
Qwen: Qwen3 Embedding 4Bqwen/qwen3-embedding-4b	2.60	0	2.60ZERNO	32 768
VoyageAI by MongoDB: voyage-4-litevoyageai/voyage-4-lite	2.60	0	2.60ZERNO	32 000
inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash	2.73	8.18	2.73ZERNO	262 144
Nex AGI: Nex-N2-Mininex-agi/nex-n2-mini	3.25	12.99	3.25ZERNO	262 144
OpenAI: GPT-5 Nano (batch)openai/gpt-5-nano:batch	3.25	25.98	4.15BotHub	400 000
Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct	3.51	26.11	5.53AITunnel	60 000
OpenAI: gpt-oss-20bopenai/gpt-oss-20b	3.90	16.88	4.86BotHub	131 072
Perplexity: Embed V1 4Bperplexity/pplx-embed-v1-4b	3.90	0	3.90ZERNO	32 000
Qwen: Qwen3.7 Flashqwen/qwen3.7-flash	3.90	16.88	6.14AITunnel	1 000 000
Upstage: Solar Pro 4upstage/solar-pro4	3.90	15.59	3.90ZERNO	524 288
Amazon: Nova Micro 1.0amazon/nova-micro-v1	4.55	18.18	49.16VseGPT	128 000
OpenAI: gpt-oss-120bopenai/gpt-oss-120b	4.81	22.08	6.26BotHub	131 072
Cohere: Command R7B (12-2024)cohere/command-r7b-12-2024	4.87	19.48	40.97VseGPT	128 000
Inception: Mercury 2.5 Previewinception/mercury-2.5-preview	5.20	19.48	5.20ZERNO	260 000
Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b	5.20	6.49	5.20ZERNO	8 192
Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8b	5.71	22.99	5.71ZERNO	8 192
DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest	5.84	11.69	5.84ZERNO	1 310 720
Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507	6.25	25.07	123VseGPT	262 144
Google: Gemini 2.5 Flash Lite (batch)google/gemini-2.5-flash-lite:batch	6.49	25.98	8.30BotHub	1 048 576
Google: Gemma 3 12Bgoogle/gemma-3-12b-it	6.49	19.48	8.30BotHub	131 072
Google: Gemma 3 4Bgoogle/gemma-3-4b-it	6.49	12.99	8.30BotHub	131 072
IBM: Granite 4.1 8Bibm-granite/granite-4.1-8b	6.49	12.99	6.49ZERNO	131 072
Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct	6.49	10.39	111VseGPT	131 072
Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct	6.49	42.86	10.24AITunnel	131 072
Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501	6.49	10.39	6.49ZERNO	32 768
NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b	6.49	25.98	6.49ZERNO	262 144
OpenAI: GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batch	6.49	25.98	8.30BotHub	1 047 576
OpenAI: GPT-5 Nanoopenai/gpt-5-nano	6.49	51.95	10.24AITunnel	400 000
OpenAI: gpt-oss-20b (batch)openai/gpt-oss-20b:batch	6.49	25.98	8.19BotHub	131 072
OpenAI: Text Embedding Ada 002 (batch)openai/text-embedding-ada-002:batch	6.49	0	6.49ZERNO	8 192
Amazon: Nova Lite 1.0amazon/nova-lite-v1	7.79	31.17	81.93VseGPT	300 000
Google: Gemma 3n 4Bgoogle/gemma-3n-e4b-it	7.79	15.59	10.10BotHub	32 768
MythoMax 13Bgryphe/mythomax-l2-13b	7.79	7.79	164VseGPT	8 192
inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fin	7.79	23.38	7.79ZERNO	262 144
Poolside: Laguna XS 2.1poolside/laguna-xs-2.1	7.79	15.59	7.79ZERNO	262 144
VoyageAI by MongoDB: voyage-4voyageai/voyage-4	7.79	0	7.79ZERNO	32 000
Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash	7.79	51.95	12.29AITunnel	202 752
OpenAI: Text Embedding 3 Large (batch)openai/text-embedding-3-large:batch	8.44	0	8.44ZERNO	8 192
Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23	8.44	33.77	13.31AITunnel	1 000 000
Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it	9.09	44.16	11.61BotHub	262 144
Microsoft: Phi 4microsoft/phi-4	9.09	18.18	9.09ZERNO	16 384
Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct	9.09	36.37	14.00AITunnel	262 144
Tencent: Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b	9.61	38.31	9.61ZERNO	8 192
Tencent: Hy-MT2-7Btencent/hy-mt2-7b	9.61	38.31	9.61ZERNO	8 192
ByteDance Seed: Seed 1.6 Flashbytedance-seed/seed-1.6-flash	9.74	38.96	9.74ZERNO	262 144
inclusionAI: Ling-2.6-1Tinclusionai/ling-2.6-1t	9.74	81.17	9.74ZERNO	262 144
inclusionAI: Ring-2.6-1Tinclusionai/ring-2.6-1t	9.74	81.17	9.74ZERNO	262 144
Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct	9.74	25.98	15.36AITunnel	131 072
OpenAI: GPT-4o-mini (batch)openai/gpt-4o-mini:batch	9.74	38.96	12.44BotHub	128 000
OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b	9.74	38.96	12.44BotHub	131 072
Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash	9.74	32.47	15.41AITunnel	1 310 720
Z.ai: GLM Flash Latest~z-ai/glm-flash-latest	9.74	32.47	9.74ZERNO	1 310 720
Google: Gemma 3 27Bgoogle/gemma-3-27b-it	10.39	58.45	12.96BotHub	131 072
NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning	10.39	25.98	10.39ZERNO	262 144
Qwen: Qwen3 32Bqwen/qwen3-32b	10.39	36.37	61.45VseGPT	131 072
NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b	11.04	51.95	11.04ZERNO	1 000 000
DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash	11.67	23.34	13.53AITunnel	1 048 576
Google: Gemma 4 31Bgoogle/gemma-4-31b-it	11.69	44.16	14.58BotHub	262 144
Poolside: Laguna S 2.1poolside/laguna-s-2.1	11.69	23.38	11.69ZERNO	1 048 576
Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507	11.69	71.43	17.70AITunnel	262 144
ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-mini	12.99	51.95	12.99ZERNO	262 144
ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7b	12.99	25.98	12.99ZERNO	128 000
Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite	12.99	51.95	16.59BotHub	1 048 576
Google: Gemini Embedding 2 (batch)google/gemini-embedding-2:batch	12.99	0	12.99ZERNO	8 192
IBM: Granite 4.2 8Bibm-granite/granite-4.2-8b	12.99	19.48	12.99ZERNO	131 072
Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct	12.99	41.56	19.93AITunnel	131 072
Meta: Llama 4 Scoutmeta-llama/llama-4-scout	12.99	38.96	19.93AITunnel	1 310 720
Meta: Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributor	12.99	25.98	16.92BotHub	1 048 576
Meta: Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor	12.99	25.98	16.12BotHub	1 048 576
Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512	12.99	12.99	12.99ZERNO	131 072
Mistral: Mistral Embed 2312mistralai/mistral-embed-2312	12.99	0	12.99ZERNO	8 192
Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507	12.99	38.96	12.99ZERNO	32 768
OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nano	12.99	51.95	16.59BotHub	1 047 576
OpenAI: GPT-5.4 Nano (batch)openai/gpt-5.4-nano:batch	12.99	81.17	16.20BotHub	400 000
OpenAI: GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batch	12.99	77.93	16.59BotHub	1 050 000
OpenAI: GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batch	12.99	77.93	16.59BotHub	1 050 000
OpenAI: Text Embedding Ada 002openai/text-embedding-ada-002	12.99	0	12.99ZERNO	8 192
Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct	12.99	25.98	12.99ZERNO	32 768
Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct	12.99	143	12.99ZERNO	262 144
Qwen: Qwen3.5-9Bqwen/qwen3.5-9b	12.99	19.48	20.48AITunnel	262 144

Загружаем каталог моделей…

Доступ к моделям

Один ключ на весь каталог

OpenAI-совместимый ключ ко всем моделям из таблицы: адрес шлюза подставляется как base_url, ключ — как api_key, менять код не нужно. Списываем по факту запросов с рублёвого счёта — без абонплаты и без зарубежной карты.

Создать аккаунт ВойтиКлюч выдаётся сразу после регистрации, абонплаты нет.

Модель	Вход, ₽ / 1Mцена ZERNO	Выход, ₽ / 1Mцена ZERNO	Дешевле всего у	Контекст
Perplexity: Embed V1 0.6Bperplexity/pplx-embed-v1-0.6b	0.520	0	0.520ZERNO	32 000
BAAI: bge-base-en-v1.5baai/bge-base-en-v1.5	0.649	0	0.649ZERNO	512
Intfloat: E5-Base-v2intfloat/e5-base-v2	0.649	0	0.649ZERNO	512
Sentence Transformers: all-MiniLM-L12-v2sentence-transformers/all-minilm-l12-v2	0.649	0	0.649ZERNO	512
Sentence Transformers: all-MiniLM-L6-v2sentence-transformers/all-minilm-l6-v2	0.649	0	0.649ZERNO	512
Sentence Transformers: all-mpnet-base-v2sentence-transformers/all-mpnet-base-v2	0.649	0	0.649ZERNO	512
Sentence Transformers: multi-qa-mpnet-base-dot-v1sentence-transformers/multi-qa-mpnet-base-dot-v1	0.649	0	0.649ZERNO	512
Sentence Transformers: paraphrase-MiniLM-L6-v2sentence-transformers/paraphrase-minilm-l6-v2	0.649	0	0.649ZERNO	512
Thenlper: GTE-Basethenlper/gte-base	0.649	0	0.649ZERNO	512
BAAI: bge-large-en-v1.5baai/bge-large-en-v1.5	1.30	0	1.30ZERNO	512
BAAI: bge-m3baai/bge-m3	1.30	0	1.30ZERNO	8 194
inclusionAI: Ling-2.6-flashinclusionai/ling-2.6-flash	1.30	3.90	1.30ZERNO	262 144
Intfloat: E5-Large-v2intfloat/e5-large-v2	1.30	0	1.30ZERNO	512
Intfloat: Multilingual-E5-Largeintfloat/multilingual-e5-large	1.30	0	1.30ZERNO	512
OpenAI: Text Embedding 3 Small (batch)openai/text-embedding-3-small:batch	1.30	0	1.30ZERNO	8 192
Qwen: Qwen3 Embedding 8Bqwen/qwen3-embedding-8b	1.30	0	1.30ZERNO	32 768
Thenlper: GTE-Largethenlper/gte-large	1.30	0	1.30ZERNO	512
IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro	2.21	14.55	2.21ZERNO	131 000
Mistral: Mistral Nemomistralai/mistral-nemo	2.47	3.90	3.89AITunnel	131 072
OpenAI: Text Embedding 3 Smallopenai/text-embedding-3-small	2.60	0	2.60ZERNO	8 192
Qwen: Qwen3 Embedding 4Bqwen/qwen3-embedding-4b	2.60	0	2.60ZERNO	32 768
VoyageAI by MongoDB: voyage-4-litevoyageai/voyage-4-lite	2.60	0	2.60ZERNO	32 000
inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash	2.73	8.18	2.73ZERNO	262 144
Nex AGI: Nex-N2-Mininex-agi/nex-n2-mini	3.25	12.99	3.25ZERNO	262 144
OpenAI: GPT-5 Nano (batch)openai/gpt-5-nano:batch	3.25	25.98	4.15BotHub	400 000
Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct	3.51	26.11	5.53AITunnel	60 000
OpenAI: gpt-oss-20bopenai/gpt-oss-20b	3.90	16.88	4.86BotHub	131 072
Perplexity: Embed V1 4Bperplexity/pplx-embed-v1-4b	3.90	0	3.90ZERNO	32 000
Qwen: Qwen3.7 Flashqwen/qwen3.7-flash	3.90	16.88	6.14AITunnel	1 000 000
Upstage: Solar Pro 4upstage/solar-pro4	3.90	15.59	3.90ZERNO	524 288
Amazon: Nova Micro 1.0amazon/nova-micro-v1	4.55	18.18	49.16VseGPT	128 000
OpenAI: gpt-oss-120bopenai/gpt-oss-120b	4.81	22.08	6.26BotHub	131 072
Cohere: Command R7B (12-2024)cohere/command-r7b-12-2024	4.87	19.48	40.97VseGPT	128 000
Inception: Mercury 2.5 Previewinception/mercury-2.5-preview	5.20	19.48	5.20ZERNO	260 000
Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b	5.20	6.49	5.20ZERNO	8 192
Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8b	5.71	22.99	5.71ZERNO	8 192
DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest	5.84	11.69	5.84ZERNO	1 310 720
Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507	6.25	25.07	123VseGPT	262 144
Google: Gemini 2.5 Flash Lite (batch)google/gemini-2.5-flash-lite:batch	6.49	25.98	8.30BotHub	1 048 576
Google: Gemma 3 12Bgoogle/gemma-3-12b-it	6.49	19.48	8.30BotHub	131 072
Google: Gemma 3 4Bgoogle/gemma-3-4b-it	6.49	12.99	8.30BotHub	131 072
IBM: Granite 4.1 8Bibm-granite/granite-4.1-8b	6.49	12.99	6.49ZERNO	131 072
Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct	6.49	10.39	111VseGPT	131 072
Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct	6.49	42.86	10.24AITunnel	131 072
Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501	6.49	10.39	6.49ZERNO	32 768
NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b	6.49	25.98	6.49ZERNO	262 144
OpenAI: GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batch	6.49	25.98	8.30BotHub	1 047 576
OpenAI: GPT-5 Nanoopenai/gpt-5-nano	6.49	51.95	10.24AITunnel	400 000
OpenAI: gpt-oss-20b (batch)openai/gpt-oss-20b:batch	6.49	25.98	8.19BotHub	131 072
OpenAI: Text Embedding Ada 002 (batch)openai/text-embedding-ada-002:batch	6.49	0	6.49ZERNO	8 192
Amazon: Nova Lite 1.0amazon/nova-lite-v1	7.79	31.17	81.93VseGPT	300 000
Google: Gemma 3n 4Bgoogle/gemma-3n-e4b-it	7.79	15.59	10.10BotHub	32 768
MythoMax 13Bgryphe/mythomax-l2-13b	7.79	7.79	164VseGPT	8 192
inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fin	7.79	23.38	7.79ZERNO	262 144
Poolside: Laguna XS 2.1poolside/laguna-xs-2.1	7.79	15.59	7.79ZERNO	262 144
VoyageAI by MongoDB: voyage-4voyageai/voyage-4	7.79	0	7.79ZERNO	32 000
Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash	7.79	51.95	12.29AITunnel	202 752
OpenAI: Text Embedding 3 Large (batch)openai/text-embedding-3-large:batch	8.44	0	8.44ZERNO	8 192
Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23	8.44	33.77	13.31AITunnel	1 000 000
Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it	9.09	44.16	11.61BotHub	262 144
Microsoft: Phi 4microsoft/phi-4	9.09	18.18	9.09ZERNO	16 384
Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct	9.09	36.37	14.00AITunnel	262 144
Tencent: Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b	9.61	38.31	9.61ZERNO	8 192
Tencent: Hy-MT2-7Btencent/hy-mt2-7b	9.61	38.31	9.61ZERNO	8 192
ByteDance Seed: Seed 1.6 Flashbytedance-seed/seed-1.6-flash	9.74	38.96	9.74ZERNO	262 144
inclusionAI: Ling-2.6-1Tinclusionai/ling-2.6-1t	9.74	81.17	9.74ZERNO	262 144
inclusionAI: Ring-2.6-1Tinclusionai/ring-2.6-1t	9.74	81.17	9.74ZERNO	262 144
Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct	9.74	25.98	15.36AITunnel	131 072
OpenAI: GPT-4o-mini (batch)openai/gpt-4o-mini:batch	9.74	38.96	12.44BotHub	128 000
OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b	9.74	38.96	12.44BotHub	131 072
Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash	9.74	32.47	15.41AITunnel	1 310 720
Z.ai: GLM Flash Latest~z-ai/glm-flash-latest	9.74	32.47	9.74ZERNO	1 310 720
Google: Gemma 3 27Bgoogle/gemma-3-27b-it	10.39	58.45	12.96BotHub	131 072
NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning	10.39	25.98	10.39ZERNO	262 144
Qwen: Qwen3 32Bqwen/qwen3-32b	10.39	36.37	61.45VseGPT	131 072
NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b	11.04	51.95	11.04ZERNO	1 000 000
DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash	11.67	23.34	13.53AITunnel	1 048 576
Google: Gemma 4 31Bgoogle/gemma-4-31b-it	11.69	44.16	14.58BotHub	262 144
Poolside: Laguna S 2.1poolside/laguna-s-2.1	11.69	23.38	11.69ZERNO	1 048 576
Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507	11.69	71.43	17.70AITunnel	262 144
ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-mini	12.99	51.95	12.99ZERNO	262 144
ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7b	12.99	25.98	12.99ZERNO	128 000
Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite	12.99	51.95	16.59BotHub	1 048 576
Google: Gemini Embedding 2 (batch)google/gemini-embedding-2:batch	12.99	0	12.99ZERNO	8 192
IBM: Granite 4.2 8Bibm-granite/granite-4.2-8b	12.99	19.48	12.99ZERNO	131 072
Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct	12.99	41.56	19.93AITunnel	131 072
Meta: Llama 4 Scoutmeta-llama/llama-4-scout	12.99	38.96	19.93AITunnel	1 310 720
Meta: Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributor	12.99	25.98	16.92BotHub	1 048 576
Meta: Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor	12.99	25.98	16.12BotHub	1 048 576
Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512	12.99	12.99	12.99ZERNO	131 072
Mistral: Mistral Embed 2312mistralai/mistral-embed-2312	12.99	0	12.99ZERNO	8 192
Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507	12.99	38.96	12.99ZERNO	32 768
OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nano	12.99	51.95	16.59BotHub	1 047 576
OpenAI: GPT-5.4 Nano (batch)openai/gpt-5.4-nano:batch	12.99	81.17	16.20BotHub	400 000
OpenAI: GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batch	12.99	77.93	16.59BotHub	1 050 000
OpenAI: GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batch	12.99	77.93	16.59BotHub	1 050 000
OpenAI: Text Embedding Ada 002openai/text-embedding-ada-002	12.99	0	12.99ZERNO	8 192
Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct	12.99	25.98	12.99ZERNO	32 768
Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct	12.99	143	12.99ZERNO	262 144
Qwen: Qwen3.5-9Bqwen/qwen3.5-9b	12.99	19.48	20.48AITunnel	262 144