Используйте клавиши со стрелками влево и вправо, чтобы переходить между отдельными проверками.
Системный статус QuickSilver Pro
Статус неизвестен
Проверка...
- 3 сервиса3 сервиса: Проверка...
- 91 модель под мониторингом91 модель: Проверка...
- Синтетический probe · обновление каждые 3 минпроверка каждые 3 мин
Сервисы
Доступность моделей
- DeepSeek V4 Flash
deepseek-v4-flashПроверка...official 0731 agent model, 1M context, Responses API
- DeepSeek V4.1 Flash
deepseek-v4.1-flashПроверка...official DeepSeek V4.1 Flash — new architecture, faster, 1M context, Responses API
- DeepSeek V4.1 Flash 1017
deepseek-v4.1-flash-1017Проверка...October 17 snapshot, 1M context, tools and optional reasoning
- DeepSeek V4 Pro
deepseek-v4-proПроверка...premium reasoning, 1M context
- Qwen3.8 Max
qwen3.8-maxПроверка...Qwen 3.8 flagship, 2.4T MoE, 1M context, autonomous coding
- Qwen3.8 Max Prime
qwen3.8-max-primeПроверка...Qwen 3.8 top-tier flagship, deepest reasoning & autonomous coding, 1M context
- Qwen3.8 Omni Flash
qwen3.8-omni-flashПроверка...Qwen's first agentic omni model: native image, audio and video understanding with tool use and reasoning, 1M context, at Alibaba's first-party price
- Qwen3.7 Max
qwen3.7-maxПроверка...Qwen 3.7 flagship, 1M context, thinks by default
- Qwen3.7 Plus
qwen3.7-plusПроверка...Qwen 3.7 agent flagship, 1M context, long-horizon coding
- Qwen3.7 Flash
qwen3.7-flashПроверка...fast multimodal agents, vision and tool use, 1M context
- Qwen3.6 Plus
qwen3.6-plusПроверка...1T-MoE flagship, 1M context, thinks by default
- Qwen3.6-35B-A3B
qwen3.6-35bПроверка...262K long-context, MoE, drop-in 3.5 upgrade
- Qwen3.8 27B
qwen3.8-27bПроверка...Cloud-only Qwen 27B with a 1M-token context window
- Qwen3.8 27B Decentered
qwen3.8-27b-decenteredПроверка...Share Compute community Macs: 30% lower token prices; cloud fallback billed at Qwen3.8 27B prices
- Qwen3.8 Flash Next
qwen3.8-flash-nextПроверка...Qwen's open Qwen4-architecture preview: 6B-active MoE, fast and cheap, with a 1M-token context window
- Kimi K2.6
kimi-k2.6Проверка...Opus-class reasoning, 256K context
- Kimi K2.7 Code
kimi-k2.7-codeПроверка...Agentic-coding K2, 256K context, coding-tuned K2.6 successor
- Kimi K3.1 Pro
kimi-k3.1-proПроверка...1M context, image input, tools and optional reasoning
- Kimi K3.1 Pro Highspeed
kimi-k3.1-pro-highspeedПроверка...1M context, image input, tools and optional reasoning
- Kimi K3
kimi-k3Проверка...2.8T multimodal reasoning flagship, 1M context
- Muse Wonder
muse-wonderПроверка...Frontier reasoning for agentic personal and professional work, 1M context
- Muse Spark Open
muse-spark-openПроверка...Meta open-weight model for coding and tools, 1M context
- Muse Spark 1.3
muse-spark-1.3Проверка...Coding & agentic reasoning model, 1M context
- Muse Spark 1.2
muse-spark-1.2Проверка...Coding-focused reasoning model, 1M context
- Muse Glimmer 30B
muse-glimmer-30bПроверка...Compact agentic multimodal model, distilled from Muse Spark
- GLM 5.3
glm-5.3Проверка...Z.ai latest reasoning flagship, 1M context, complex software engineering & long-horizon agents
- GLM 5.3 Prime
glm-5.3-primeПроверка...Z.ai GLM 5.3 Prime, top reasoning flagship, 1M context, complex software engineering
- GLM 5.3 Flash
glm-5.3-flashПроверка...Z.ai fast open-weights reasoning model, 1M context at workhorse pricing
- GLM 5.2
glm-5.2Проверка...Z.ai reasoning flagship, 1M context, long-horizon agents & coding
- Nemotron 3 Ultra
nemotron-3-ultraПроверка...550B-A55B open MoE for frontier reasoning and agent orchestration
- Nemotron 3.5 Lightning
nemotron-3.5-lightningПроверка...30B-A3B open MoE for fast, tool-heavy agents
- GPT-OSS 120B
gpt-oss-120bПроверка...OpenAI's open-weight 117B MoE, high-volume agents & reasoning, 131K context
- GPT-6 Astra
gpt-6-astraПроверка...OpenAI's GPT-6 flagship, long-horizon agentic coding & deep research, 1M context
- GPT-6 Luna
gpt-6-lunaПроверка...OpenAI's cost-efficient GPT-6, high-volume chat & lightweight agentic work, 1M context
- GPT-6.1 Sol
gpt-6.1-solПроверка...OpenAI's GPT-6.1 Sol, near-Astra agentic coding at Sol pricing, 1M context
- GPT-6.1 Terra
gpt-6.1-terraПроверка...OpenAI's GPT-6.1 Terra, mid-tier everyday agentic coding, writing, and screenshot understanding, 1M context
- GPT-6.1 Terra Pro
gpt-6.1-terra-proПроверка...GPT-6.1 Terra in pro reasoning mode -- same model, same per-token price, far more reasoning tokens per request on complex tasks
- GPT-6 Sol
gpt-6-solПроверка...OpenAI's GPT-6 mid-flagship, strong reasoning & agentic coding, 1M context
- GPT-5.6 Luna
gpt-5.6-lunaПроверка...OpenAI's fast, cost-efficient GPT-5.6 tier, 1M context
- GPT-5.6 Terra
gpt-5.6-terraПроверка...OpenAI's balanced GPT-5.6 mid-tier, 1M context
- GPT-5.6 Sol
gpt-5.6-solПроверка...OpenAI's flagship GPT-5.6, complex reasoning & agentic coding, 1M context
- Grok 4.5
grok-4.5Проверка...xAI's smartest model, frontier coding, knowledge work & STEM, 500K context
- Grok 4.6
grok-4.6Проверка...frontier coding, knowledge work and STEM, vision, 500K context
- Grok 4.7
grok-4.7Проверка...frontier coding, knowledge work and STEM, vision, 500K context
- MiniMax M3
minimax-m3Проверка...MiniMax open-weight frontier model, 1M context, agentic coding
- MiMo-V2.6-Pro
mimo-v2.6-proПроверка...Xiaomi flagship open-weight MiMo-V2.6-Pro, top open model on AA Intelligence Index, coding & agentic, vision, 1M context
- MiMo-V2.6-Flash
mimo-v2.6-flashПроверка...Xiaomi open-weight MiMo-V2.6-Flash, fast low-cost coding & agentic, vision, 1M context
- MiMo-V2.5
mimo-v2.5Проверка...Xiaomi open-weight MiMo-V2.5, cost-efficient coding & agentic, 1M context
- Hy4 Preview
hy4-previewПроверка...Tencent Hy4 (preview), reasoning & agentic coding, 1M context
- Hy3
hy3Проверка...Tencent Hy3, selectable reasoning & agentic coding, 262K context
- Step 5 Preview
step-5-previewПроверка...StepFun reasoning model for tools and image understanding, 1M context
- Mistral Large 4
mistral-large-4Проверка...Mistral's frontier multimodal model for coding and agents, 524K context
- Jev 1.13
jev-1.13Проверка...Typed decisions with calibrated probabilities from a single forward pass: routing, classification and scoring without text generation
- Trio-Spark v1.3
trio-spark-v1.3Проверка...System-1 decision model: one forward pass, calibrated probabilities, no generated tokens
- Claude Opus 5.5
claude-opus-5-5Проверка...Anthropic's most capable Claude: agentic coding, knowledge work & computer use, 1M context
- Claude Opus 5
claude-opus-5Проверка...Anthropic Opus 5 for demanding reasoning, coding & long-horizon agentic work, 1M context
- Claude Fable 5.1
claude-fable-5-1Проверка...Anthropic Mythos-class model for deep reasoning and long-horizon agentic work (5.1)
- Claude Fable 5
claude-fable-5Проверка...Anthropic Mythos-class flagship, most capable reasoning
- Claude Opus 4.8
claude-opus-4-8Проверка...Anthropic flagship, top-tier reasoning & agentic
- Claude Sonnet 5.5
claude-sonnet-5-5Проверка...Anthropic's newest Sonnet, faster and fewer tokens per task, 1M context
- Claude Sonnet 5
claude-sonnet-5Проверка...Anthropic's newest Sonnet tier, 1M context
- Claude Haiku 5.5
claude-haiku-5-5Проверка...Anthropic's newest small, fast model for subagents and high-volume work, 1M context
- Claude Haiku 4.5
claude-haiku-4-5Проверка...fast, low-cost Anthropic, high-volume
- Gemini 4 Argon
gemini-4-argonПроверка...Google's new flagship reasoning model, 1M context; introductory price
- Gemini 3.7 Flash
gemini-3.7-flashПроверка...fast multimodal Flash for agents; promotional pricing through 2026-12-31
- Gemini 3.8 Flash
gemini-3.8-flashПроверка...most capable Flash for agents; promotional pricing through 2026-12-31
- Gemini 3.6 Flash
gemini-3.6-flashПроверка...current general-purpose Flash GA, 1M context
- Gemini 3.5 Flash-Lite
gemini-3.5-flash-liteПроверка...current low-cost Flash-Lite GA, 1M context
- Gemini 3.5 Flash
gemini-3.5-flashПроверка...Google's next-gen Flash GA, 1M context, thinking
- Gemini 3.1 Pro Preview
gemini-3.1-pro-previewПроверка...Google's flagship reasoning, 1M context, thinking
- Nano Banana Pro (Gemini 3 Pro Image)
gemini-3-pro-imageПроверка...Google's Nano Banana Pro at 1K, billed per image
- Nano Banana 2.1
gemini-nano-banana-2.1Проверка...Google's newest Nano Banana at 1K, billed per image
- Gemini 3 Flash Preview
gemini-3-flash-previewПроверка...legacy compatibility; migrate to Gemini 3.6 Flash
- Gemini 3.1 Flash Lite
gemini-3.1-flash-liteПроверка...legacy compatibility; migrate to Gemini 3.5 Flash-Lite
- FLUX.2 Pro
flux.2-proПроверка...flagship image generation, billed per image
- FLUX.1 Schnell
flux.1-schnellПроверка...ultra-fast open image generation, billed per image
- SDXL Turbo
sdxl-turboПроверка...fast open image generation (SDXL Turbo), billed per image
- FLUX.2 Klein
flux.2-kleinПроверка...open FLUX.2 image generation, billed per image
- Qwen Image 3.0
qwen-image-3.0Проверка...Alibaba text-to-image, 512x512 to 2560x2560, flat $0.04 per image; optional prompt_extend
- Seedream 5.0 Pro
seedream-5.0-proПроверка...ByteDance's Seedream 5.0 Pro: flagship photorealistic image generation, billed per image
- Seedream 4
seedream-4Проверка...ByteDance Seedream 4: fast, high-quality image generation, billed per image
- Bria FIBO 1.5
bria-fibo-1.5Проверка...Bria FIBO 1.5: image generation trained on fully licensed data (commercially safe), billed per image
- Bria FIBO 2.0
bria-fibo-2.0Проверка...Bria FIBO 2.0: Bria reports training on fully licensed data for commercially safe image generation, billed per image
- GPT Image 2
gpt-image-2Проверка...OpenAI's GPT Image 2 at a fixed ~1.5MP standard output, billed per image
- GPT Image 2.5 Flare
gpt-image-2.5-flareПроверка...OpenAI's GPT Image 2.5, speed tier, at medium quality, billed per image
- GPT Image 2.5 Sunburst
gpt-image-2.5-sunburstПроверка...OpenAI's GPT Image 2.5, precision tier, at medium quality, billed per image
- Qwen3 ASR
qwen3-asrПроверка...Speech to text
- Nemotron 3.5 ASR
nemotron-3.5-asrПроверка...Speech to text
- Whisper Large v3 Turbo
whisper-large-v3-turboПроверка...Speech to text
- Chatterbox Turbo
chatterbox-turboПроверка...English text to speech
- Qwen3 TTS
qwen3-ttsПроверка...Chinese and English text to speech
Дорожная карта инфраструктуры
Текущая основа
Запуск на курируемом каталоге
Каждая модель тарифицируется по опубликованной цене для этой модели, и любое сравнение цен можно проверить по /pricing.json. Узкая операционная поверхность сохраняет эти цифры проверяемыми, и та же поверхность напрямую масштабируется до следующего этапа.
Следующий этап
Собственный inference-стек на H100/H200
Self-hosted serving на выделенных GPU с использованием SGLang + continuous batching, EAGLE-3 speculative decoding, FP8 quantization через DeepGEMM и кастомных ядер SageAttention / ThunderMLA. На этом этапе
system_fingerprintстанет стабильным (он будет меняться только при обновлении стека), а repeatable-seed workflows начнут нормально работать. Цель: быть на 30-50% дешевле текущих цен на DeepSeek V4 wave.Долгосрочное направление
Colocated data center + партнерства с AIDC
Переход от аренды (Vast.ai) к собственным или colocated стойкам. Там, где это имеет смысл, будем работать с операторами AI-датацентров. Цель - самый дешевый и надежный inference для open-source моделей на планете: весь стек и вся инженерия под нашим контролем.
Об этой странице
Строки бэкенда и сайта показывают проверки доступности из вашего браузера. Строка API обобщает результаты проверок перечисленных моделей, полученные от нашего бэкенда. Строки моделей отражают реальный 1-token probe, который наш backend отправляет каждые 3 минуты. Исторические бары показывают результаты недавних проверок, сохраненных в localStorage; при смене устройства история очищается.
Публичное отслеживание аптайма началось 2026-04-16. Если вам нужен контрактный SLA и история, отслеживаемая третьей стороной, свяжитесь с нами.