ZERNO · Модели
Сколько стоит миллион токенов
Цена первоисточника, пересчитанная в рубли по курсу ЦБ. Мы не прячем, откуда берём цифры, и не показываем те, которых у нас пока нет.
Источник цен — краулер ZERNO: openrouter.ai и российские перепродавцы, снято 2026-08-17. Курс 84.54 ₽ за доллар на 15.08.2026, по данным ЦБ. Наценки в этих ценах нет: доступ к моделям мы ещё не продаём.
Разброс цен
Миллион токенов стоит от 0.25 ₽ до 22 827 123 ₽
Выбор модели под задачу — не вопрос вкуса, а вопрос счёта в конце месяца. По горизонтали смешанная цена 3:1: три токена входа на один выхода, средний профиль обращения к чату. Шкала логарифмическая, иначе весь каталог слипся бы в первый столбец.
В шкалу не попали 83 бесплатных моделей и 0 маршрутизаторов, у которых цена зависит от того, куда уйдёт запрос.
$0.68 — $1.00 /M49 моделей в этой вилке · здесь медиана каталога
$0.00$0.01$0.10$1$10$100$1000$10000$1000000
Дешевле всех0.25 ₽Perplexity: Embed V1 0.6B
Медиана каталога73.98 ₽Z.ai: GLM 4.6
Дороже всех22 827 123 ₽Microsoft: MAI-Transcribe 1.5
| Модель | Вход, ₽ / 1M | Выход, ₽ / 1M | Дешевле всего у | Контекст |
|---|---|---|---|---|
| Auto Routeropenrouter/auto | -84544900.000 | -84544900.000 | — | 2 000 000 |
| Auto Router (Beta)openrouter/auto-beta | -84544900.000 | -84544900.000 | — | 2 000 000 |
| Body Builder (beta)openrouter/bodybuilder | -84544900.000 | -84544900.000 | — | 128 000 |
| OpenRouter: Fusionopenrouter/fusion | -84544900.000 | -84544900.000 | — | 1 000 000 |
| Pareto Code Routeropenrouter/pareto-code | -84544900.000 | -84544900.000 | — | 2 000 000 |
| Perplexity: Embed V1 0.6Bperplexity/pplx-embed-v1-0.6b | 0.338 | 0 | — | 32 000 |
| BAAI: bge-base-en-v1.5baai/bge-base-en-v1.5 | 0.423 | 0 | — | 512 |
| Intfloat: E5-Base-v2intfloat/e5-base-v2 | 0.423 | 0 | — | 512 |
| Sentence Transformers: all-MiniLM-L12-v2sentence-transformers/all-minilm-l12-v2 | 0.423 | 0 | — | 512 |
| Sentence Transformers: all-MiniLM-L6-v2sentence-transformers/all-minilm-l6-v2 | 0.423 | 0 | — | 512 |
| Sentence Transformers: all-mpnet-base-v2sentence-transformers/all-mpnet-base-v2 | 0.423 | 0 | — | 512 |
| Sentence Transformers: multi-qa-mpnet-base-dot-v1sentence-transformers/multi-qa-mpnet-base-dot-v1 | 0.423 | 0 | — | 512 |
| Sentence Transformers: paraphrase-MiniLM-L6-v2sentence-transformers/paraphrase-minilm-l6-v2 | 0.423 | 0 | — | 512 |
| Thenlper: GTE-Basethenlper/gte-base | 0.423 | 0 | — | 512 |
| BAAI: bge-large-en-v1.5baai/bge-large-en-v1.5 | 0.845 | 0 | — | 512 |
| BAAI: bge-m3baai/bge-m3 | 0.845 | 0 | — | 8 194 |
| inclusionAI: Ling-2.6-flashinclusionai/ling-2.6-flash | 0.845 | 2.54 | — | 262 144 |
| Intfloat: E5-Large-v2intfloat/e5-large-v2 | 0.845 | 0 | — | 512 |
| Intfloat: Multilingual-E5-Largeintfloat/multilingual-e5-large | 0.845 | 0 | — | 512 |
| Qwen: Qwen3 Embedding 8Bqwen/qwen3-embedding-8b | 0.845 | 0 | — | 32 768 |
| Thenlper: GTE-Largethenlper/gte-large | 0.845 | 0 | — | 512 |
| IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro | 1.44 | 9.47 | — | 131 000 |
| Mistral: Mistral Nemomistralai/mistral-nemo | 1.61 | 2.54 | 3.80AITunnel | 131 072 |
| OpenAI: Text Embedding 3 Smallopenai/text-embedding-3-small | 1.69 | 0 | — | 8 192 |
| Qwen: Qwen3 Embedding 4Bqwen/qwen3-embedding-4b | 1.69 | 0 | — | 32 768 |
| VoyageAI by MongoDB: voyage-4-litevoyageai/voyage-4-lite | 1.69 | 0 | — | 32 000 |
| Ling-3.0-flashinclusionai/ling-3.0-flash | 1.78 | 5.33 | — | 262 144 |
| Nex AGI: Nex-N2-Mininex-agi/nex-n2-mini | 2.11 | 8.45 | — | 262 144 |
| OpenAI: GPT-5 Nano (batch)openai/gpt-5-nano:batch | 2.11 | 16.91 | 4.05BotHub | 400 000 |
| Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct | 2.28 | 16.99 | 5.40AITunnel | 60 000 |
| OpenAI: gpt-oss-120bopenai/gpt-oss-120b | 2.54 | 14.37 | 4.86BotHub | 131 072 |
| OpenAI: gpt-oss-20bopenai/gpt-oss-20b | 2.54 | 10.99 | 4.86BotHub | 131 072 |
| Perplexity: Embed V1 4Bperplexity/pplx-embed-v1-4b | 2.54 | 0 | — | 32 000 |
| Qwen: Qwen3.7 Flashqwen/qwen3.7-flash | 2.54 | 10.99 | 6.00AITunnel | 1 000 000 |
| Upstage: Solar Pro 4upstage/solar-pro4 | 2.54 | 10.15 | — | 524 288 |
| Amazon: Nova Micro 1.0amazon/nova-micro-v1 | 2.96 | 11.84 | 48.00VseGPT | 128 000 |
| Cohere: Command R7B (12-2024)cohere/command-r7b-12-2024 | 3.17 | 12.68 | 40.00VseGPT | 128 000 |
| Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b | 3.38 | 4.23 | — | 8 192 |
| Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | 4.07 | 16.32 | 120VseGPT | 262 144 |
| Google: Gemini 2.5 Flash Lite (batch)google/gemini-2.5-flash-lite:batch | 4.23 | 16.91 | 8.10BotHub | 1 048 576 |
| Google: Gemma 3 12Bgoogle/gemma-3-12b-it | 4.23 | 12.68 | 8.10BotHub | 131 072 |
| Google: Gemma 3 4Bgoogle/gemma-3-4b-it | 4.23 | 8.45 | 8.10BotHub | 131 072 |
| IBM: Granite 4.1 8Bibm-granite/granite-4.1-8b | 4.23 | 8.45 | — | 131 072 |
| Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | 4.23 | 6.76 | 108VseGPT | 131 072 |
| Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct | 4.23 | 27.90 | 10.00AITunnel | 131 072 |
| Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501 | 4.23 | 6.76 | — | 32 768 |
| NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | 4.23 | 16.91 | — | 262 144 |
| OpenAI: GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batch | 4.23 | 16.91 | 8.10BotHub | 1 047 576 |
| OpenAI: GPT-5 Nanoopenai/gpt-5-nano | 4.23 | 33.82 | 10.00AITunnel | 400 000 |
| OpenAI: Text Embedding Ada 002 (batch)openai/text-embedding-ada-002:batch | 4.23 | 0 | — | 8 192 |
| Amazon: Nova Lite 1.0amazon/nova-lite-v1 | 5.07 | 20.29 | 80.00VseGPT | 300 000 |
| Google: Gemma 3n 4Bgoogle/gemma-3n-e4b-it | 5.07 | 10.15 | 9.72BotHub | 32 768 |
| MythoMax 13Bgryphe/mythomax-l2-13b | 5.07 | 5.07 | 160VseGPT | 8 192 |
| Poolside: Laguna XS 2.1poolside/laguna-xs-2.1 | 5.07 | 10.15 | — | 262 144 |
| VoyageAI by MongoDB: voyage-4voyageai/voyage-4 | 5.07 | 0 | — | 32 000 |
| Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash | 5.07 | 33.82 | 12.00AITunnel | 202 752 |
| OpenAI: Text Embedding 3 Large (batch)openai/text-embedding-3-large:batch | 5.50 | 0 | — | 8 192 |
| Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | 5.50 | 21.98 | 13.00AITunnel | 1 000 000 |
| Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 5.92 | 28.75 | 11.34BotHub | 262 144 |
| Microsoft: Phi 4microsoft/phi-4 | 5.92 | 11.84 | — | 16 384 |
| Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct | 5.92 | 23.67 | 14.00AITunnel | 262 144 |
| DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | 6.04 | 12.07 | 18.00AITunnel | 1 048 576 |
| ByteDance Seed: Seed 1.6 Flashbytedance-seed/seed-1.6-flash | 6.34 | 25.36 | — | 262 144 |
| inclusionAI: Ling-2.6-1Tinclusionai/ling-2.6-1t | 6.34 | 52.84 | — | 262 144 |
| inclusionAI: Ring-2.6-1Tinclusionai/ring-2.6-1t | 6.34 | 52.84 | — | 262 144 |
| OpenAI: GPT-4o-mini (batch)openai/gpt-4o-mini:batch | 6.34 | 25.36 | 12.15BotHub | 128 000 |
| OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b | 6.34 | 25.36 | 12.15BotHub | 131 072 |
| DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest | 6.62 | 13.24 | — | 1 310 720 |
| Google: Gemma 3 27Bgoogle/gemma-3-27b-it | 6.76 | 38.05 | 12.96BotHub | 262 144 |
| NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning | 6.76 | 16.91 | — | 1 000 000 |
| Qwen: Qwen3 32Bqwen/qwen3-32b | 6.76 | 23.67 | 60.00VseGPT | 131 072 |
| NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b | 7.19 | 33.82 | — | 1 000 000 |
| Poolside: Laguna S 2.1poolside/laguna-s-2.1 | 7.61 | 15.22 | — | 1 048 576 |
| Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | 7.61 | 46.50 | 18.00AITunnel | 262 144 |
| Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct | 7.93 | 21.14 | 15.00AITunnel | 256 000 |
| ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-mini | 8.45 | 33.82 | — | 262 144 |
| ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7b | 8.45 | 16.91 | — | 128 000 |
| Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | 8.45 | 33.82 | 16.20BotHub | 1 048 576 |
| Google: Gemma 4 31Bgoogle/gemma-4-31b-it | 8.45 | 28.75 | 16.20BotHub | 262 144 |
| Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct | 8.45 | 27.05 | 20.00AITunnel | 131 072 |
| Meta: Llama 4 Scoutmeta-llama/llama-4-scout | 8.45 | 25.36 | 20.00AITunnel | 1 310 720 |
| Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512 | 8.45 | 8.45 | — | 131 072 |
| Mistral: Mistral Embed 2312mistralai/mistral-embed-2312 | 8.45 | 0 | — | 8 192 |
| Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507 | 8.45 | 25.36 | — | 32 000 |
| OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nano | 8.45 | 33.82 | 16.20BotHub | 1 047 576 |
| OpenAI: GPT-5.4 Nano (batch)openai/gpt-5.4-nano:batch | 8.45 | 52.84 | 16.20BotHub | 400 000 |
| OpenAI: GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batch | 8.45 | 50.73 | 16.20BotHub | 1 050 000 |
| OpenAI: GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batch | 8.45 | 50.73 | 16.20BotHub | 1 050 000 |
| OpenAI: Text Embedding Ada 002openai/text-embedding-ada-002 | 8.45 | 0 | — | 8 192 |
| Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct | 8.45 | 16.91 | — | 32 768 |
| Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct | 8.45 | 93.00 | — | 262 144 |
| Qwen: Qwen3.5-9Bqwen/qwen3.5-9b | 8.45 | 12.68 | 20.00AITunnel | 262 144 |
| Reka Edgerekaai/reka-edge | 8.45 | 8.45 | — | 16 384 |
| Reka Flash 3rekaai/reka-flash-3 | 8.45 | 16.91 | — | 65 536 |
| StepFun: Step 3.5 Flashstepfun/step-3.5-flash | 8.45 | 25.36 | — | 262 144 |
| Qwen: Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instruct | 8.79 | 35.17 | — | 131 072 |
| Qwen: Qwen3 8Bqwen/qwen3-8b | 9.89 | 38.47 | — | 131 072 |
| Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct | 9.89 | 38.47 | — | 262 144 |
| Qwen: Qwen3 14Bqwen/qwen3-14b | 10.15 | 20.29 | 48.00VseGPT | 131 072 |
| Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next | 10.15 | 67.64 | 22.00AITunnel | 262 144 |