About Kumo
A billing-and-routing layer, built to be boring
Kumo is one gateway in front of the GPT, Claude and Gemini text models your team already uses: one base URL, one key, one balance — at a lower effective rate than list price. No new SDK, no lock-in, no drama. That’s the whole company, on purpose
What we build
One gateway, everything behind it
Four things, done properly — everything else on the site is detail
A drop-in gateway
Point the OpenAI SDK you already use at https://api.kumorouter.com/v1 and keep every other line of your code. Each request is routed to the model’s upstream provider and the answer comes back verbatim
One balance for the team
Top up once and spend it across every supported model. No per-provider cards, seats or minimums — you pay only for tokens you actually use
A lower effective rate
Routing and caching optimizations bring your effective per-token cost under list price — same models, same API, savings shown per call
Metering you can read
Tokens, models and costs per key and per day in the dashboard — the numbers your finance team asks for, without a spreadsheet safari
How we work
Principles over promises
The same rules run through the product, the pricing page and this site
Verbatim, always
We never rewrite, downgrade or substitute a model behind your back. The response you get is the provider’s response, and the serving model is named on every call
Not a data lake
Prompt and completion bodies are processed to serve the request, then dropped — not stored, not logged, never used for training. The details live on the Security page
Only what’s live
If a feature, certification or metric isn’t real yet, the site says so — status snapshots are labelled as snapshots, and roadmap items are labelled roadmap
Small surface, fast answers
A deliberately small product means questions reach a person who can fix things — security and billing questions are usually answered within one business day
At a glance
The short version
| Fact | Detail |
|---|---|
| Product | OpenAI-compatible API gateway for GPT, Claude and Gemini text models |
| API base | https://api.kumorouter.com/v1 — drop-in for the OpenAI SDK |
| Pricing model | Packages and pay as you go; no seats, no minimums |
| Uptime target | 99.9% target; public status monitoring is being connected |
| Data stance | No prompt logging, no training on your data |
| Russia | Works without a VPN or foreign card — pay in rubles by card or via SBP |
| Talk to us | sales@kumorouter.com support@kumorouter.com @kumo_api |
Kumo in Russia
GPT, Claude and Gemini API — in Russia, without a VPN
Kumo is API access to modern language models from Russian networks: no VPN, no foreign card, no separate account with each provider
One OpenAI-compatible endpoint — https://api.kumorouter.com/v1 — gives access to 90 models: Claude Opus 4.8, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Opus 5, Claude Opus 4.7, Claude Opus 4.6, Claude Opus 4.5, Claude Haiku 4.5, Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5 and Claude Fable 5.2 by Anthropic, GPT-5.6 Terra, GPT-5.6 Sol, GPT-5.6 Luna, GPT-5.5, GPT-5.3 Codex Spark, Codex Auto Review, GPT-6 Astra, GPT-6 Sol, GPT-6 Luna, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6.2 Sol and GPT-6.2 Astra by OpenAI, Gemini 3.8 Flash High, Gemini 3.7 Flash High, Gemini 3.6 Flash High, Gemini 3.1 Pro Low, Gemini 3.1 Flash Lite, Gemini 3 Flash Preview, Gemini 3.6 Flash, Gemini 3.8 Flash, Gemini 4 Argon and Gemini 4 Carbon by Google, Grok 4.6, Grok 4.5 and Grok 4.7 by xAI, GLM-5.3, GLM-5.2, GLM 5.3 Flash, GLM-5.3 FlashX and GLM-5.3 Raw by Zhipu, Kimi K3, Kimi K2.7 Code, Kimi K2.6, Kimi K2.8 and Kimi K3.1 Pro by Moonshot AI, Mistral Large 4, Mistral Medium 3.5, Mistral Small 4 and Devstral 2 by Mistral AI, DeepSeek V4.1 Flash, DeepSeek V4 Pro 0813 and DeepSeek V4 Flash by DeepSeek, Qwen3.8 Max 0902, Qwen3.8 Flash, Qwen3.8 27B, Qwen3.7 Plus, Qwen3 Coder Next, Qwen3.8 27B Antislop, Qwen3.8 Max Preview, Qwen3.7 Max and Qwen3.8 Omni Flash by Qwen, MiniMax M3 and MiniMax M2.7 by MiniMax, MiMo V2.6 Pro and MiMo V2.6 Flash by Xiaomi, Step 5 Preview and Step 3.7 Flash by StepFun, Muse Glimmer 30B and Llama 4 Maverick by Meta, Nemotron 3 Ultra and Nemotron 3 Super by NVIDIA, Seed 2.1 Turbo and Seed 2.0 Code by ByteDance Seed, Hy4 Preview by Tencent, Command A+ by Cohere, Inkling by Thinking Machines, LongCat 2.0 by Meituan, Nova 2 Lite by Amazon, Trinity Large Thinking by trinity-large-thinking, Solar Pro 4 by Upstage, Aion 3.5 by AionLabs, Laguna S 2.1 by laguna-s-2-1, Mercury 2.5 by Inception and Granite 4.2 8B by IBM. The same key works in Cursor, Cline, Continue, n8n, Make and any code built on the official OpenAI SDK
Everything runs directly on Russian networks: top up in rubles with a local card or via SBP. No VPN, foreign card or virtual number — sign up with an email, add funds and call GPT, Claude or Gemini over the API the same day
If you are looking to buy ChatGPT API, Claude API or Gemini API access in Russia, Kumo covers it with one key: a single balance across every model, rates 30–50% below provider list prices, and token metering you can actually read in the dashboard
Models available via the API right now
| Model | Provider | Inputper 1M tokens | Outputper 1M tokens | Context |
|---|---|---|---|---|
| Claude Opus 4.8 | anthropic | 2.6 USD | 12.8 USD | 1M |
| GPT Image 2 | openai | not published | not published | — |
| Claude Sonnet 5 | anthropic | 1.2 USD | 6 USD | 1M |
| Claude Sonnet 4.6 | anthropic | 1.5 USD | 7.7 USD | 1M |
| Claude Sonnet 4.5 | anthropic | 1.5 USD | 7.7 USD | 200K |
| Claude Opus 5 | anthropic | 2.6 USD | 12.8 USD | 1M |
| Claude Opus 4.7 | anthropic | 2.6 USD | 12.8 USD | 1M |
| Claude Opus 4.6 | anthropic | 2.6 USD | 12.8 USD | 1M |
| Claude Opus 4.5 | anthropic | 2.6 USD | 12.8 USD | 200K |
| Claude Haiku 4.5 | anthropic | 0.6 USD | 3 USD | 200K |
| Claude Fable 5.1 | anthropic | 6 USD | 30 USD | 1M |
| Claude Fable 5 | anthropic | 5.1 USD | 25.5 USD | 1M |
| GPT-5.6 Terra | openai | 1 USD | 6.1 USD | 1.1M |
| GPT-5.6 Sol | openai | 2 USD | 10.2 USD | 1.1M |
| GPT-5.6 Luna | openai | 0.1 USD | 0.6 USD | 1.1M |
| GPT-5.5 | openai | 2.6 USD | 15.3 USD | 1.1M |
| GPT-5.3 Codex Spark | openai | 0.9 USD | 7.1 USD | 128K |
| Codex Auto Review | openai | 3 USD | 18 USD | 1.1M |
| Gemini 3.8 Flash High | 0.5 USD | 2.3 USD | 1M | |
| Gemini 3.7 Flash High | 0.4 USD | 1.9 USD | 1M | |
| Gemini 3.6 Flash High | 0.4 USD | 1.9 USD | 1M | |
| Gemini 3.1 Pro Low | 1.1 USD | 6.6 USD | 1M | |
| Gemini 3.1 Flash Lite | 0.2 USD | 0.9 USD | 1M | |
| Gemini 3 Flash Preview | 0.3 USD | 1.5 USD | 1M | |
| Grok 4.6 | xai | 1 USD | 3.1 USD | 500K |
| Grok 4.5 | xai | 1 USD | 3.1 USD | 500K |
| GLM-5.3 | zai | 0.8 USD | 2.6 USD | 1M |
| GLM-5.2 | zai | 0.7 USD | 2.2 USD | 1M |
| GPT-6 Astra | openai | 6 USD | 30 USD | 1.1M |
| Gemini 3.6 Flash | 0.4 USD | 1.8 USD | 1M | |
| Gemini 3.8 Flash | 0.4 USD | 2.1 USD | 1M | |
| GLM 5.3 Flash | zai | 0.2 USD | 0.6 USD | 1M |
| Kimi K3 | moonshot | 1.7 USD | 8.3 USD | 1M |
| Grok 4.7 | xai | 1.1 USD | 3.3 USD | 500K |
| Claude Opus 5.5 | anthropic | 2.2 USD | 11 USD | 1M |
| GPT-6 Sol | openai | 1.1 USD | 5.5 USD | 1.1M |
| GPT-6 Luna | openai | 0.06 USD | 0.3 USD | 1.1M |
| Claude Sonnet 5.5 | anthropic | 1.1 USD | 5.5 USD | 1M |
| GPT-6.1 Sol | openai | 1.1 USD | 5.5 USD | 1.1M |
| Claude Haiku 5.5 | anthropic | 0.06 USD | 0.3 USD | 1M |
| Mistral Large 4 | mistral | 0.8 USD | 2.4 USD | 1M |
| Mistral Medium 3.5 | mistral | 1.7 USD | 8.7 USD | 262.1K |
| Mistral Small 4 | mistral | 0.2 USD | 0.8 USD | 262.1K |
| Devstral 2 | mistral | 0.5 USD | 2.3 USD | 262.1K |
| DeepSeek V4.1 Flash | deepseek | 0.1 USD | 0.5 USD | 1M |
| DeepSeek V4 Pro 0813 | deepseek | 0.5 USD | 1.6 USD | 1M |
| DeepSeek V4 Flash | deepseek | 0.07 USD | 0.1 USD | 1M |
| Qwen3.8 Max 0902 | qwen | 2.3 USD | 7 USD | 1M |
| Qwen3.8 Flash | qwen | 0.2 USD | 0.5 USD | 1M |
| Qwen3.8 27B | qwen | 0.05 USD | 2.9 USD | 1M |
| Qwen3.7 Plus | qwen | 0.4 USD | 1.5 USD | 1M |
| Qwen3 Coder Next | qwen | 0.1 USD | 0.9 USD | 262.1K |
| MiniMax M3 | minimax | 0.3 USD | 1.4 USD | 1M |
| MiniMax M2.7 | minimax | 0.3 USD | 1.4 USD | 204.8K |
| Kimi K2.7 Code | moonshot | 0.8 USD | 3.9 USD | 262.1K |
| Kimi K2.6 | moonshot | 0.8 USD | 4 USD | 262.1K |
| GLM-5.3 FlashX | zai | 0.4 USD | 1.5 USD | 1M |
| MiMo V2.6 Pro | xiaomi | 0.5 USD | 1 USD | 1.1M |
| MiMo V2.6 Flash | xiaomi | 0.2 USD | 0.3 USD | 1.1M |
| Step 5 Preview | stepfun | 1.2 USD | 3.1 USD | 1M |
| Step 3.7 Flash | stepfun | 0.2 USD | 1.3 USD | 262.1K |
| Muse Glimmer 30B | meta | 0.3 USD | 1.4 USD | 131.1K |
| Nemotron 3 Ultra | nvidia | 0.7 USD | 2.8 USD | 262.1K |
| Nemotron 3 Super | nvidia | 0.09 USD | 0.5 USD | 262.1K |
| Seed 2.1 Turbo | bytedance | 0.6 USD | 2.9 USD | 262.1K |
| Seed 2.0 Code | bytedance | 0.6 USD | 3.5 USD | 262.1K |
| Hy4 Preview | tencent | 1 USD | 2.9 USD | 1M |
| Command A+ | cohere | 0.3 USD | 1.7 USD | 192K |
| Inkling | thinkingmachines | 1.2 USD | 4.7 USD | 524.3K |
| LongCat 2.0 | meituan | 0.3 USD | 1.4 USD | 1M |
| Nova 2 Lite | amazon | 0.3 USD | 2.9 USD | 1M |
| Trinity Large Thinking | trinity-large-thinking | 0.3 USD | 0.9 USD | — |
| Solar Pro 4 | upstage | 0.1 USD | 0.4 USD | 524.3K |
| Aion 3.5 | aionlabs | 3.5 USD | 7 USD | 262.1K |
| Laguna S 2.1 | laguna-s-2-1 | 0.1 USD | 0.2 USD | — |
| Mercury 2.5 | inception | 0.05 USD | 0.2 USD | 260K |
| Llama 4 Maverick | meta | 0.2 USD | 0.8 USD | 1M |
| Granite 4.2 8B | ibm | 0.07 USD | 0.3 USD | 131.1K |
| Kimi K2.8 | moonshot | 0.8 USD | 4 USD | 1M |
| Gemini 4 Argon | 1.1 USD | 5.5 USD | 1M | |
| GPT Image 2.5 | openai | not published | not published | — |
| Clef | cloudflare | 0.05 USD | not published | 65.5K |
| Clef Flash | cloudflare | 0.05 USD | not published | 24.6K |
| Clef Omni | cloudflare | 0.2 USD | not published | 65.5K |
| D1 | liquid | 0.02 USD | not published | 65.5K |
| D1 Ultra | liquid | 0.05 USD | not published | 32.8K |
| Jev 1.13 | typesafe | 0.05 USD | not published | 262.1K |
| Jev 1.14 | typesafe | 0.05 USD | not published | 262.1K |
| Microsoft-Decision-1 | microsoft | 0.05 USD | not published | 32.8K |
| Solar Decide | upstage | 0.06 USD | not published | 524.3K |
| Solar Decide Flash | upstage | 0.06 USD | not published | 524.3K |
| Span-01 | respan | 0.02 USD | not published | — |
| Span-02 | respan | 0.01 USD | not published | 131.1K |
| Decider V1.2 | perplexity | 0.02 USD | not published | 262.1K |
| Decider Flash V1.2 | perplexity | 0.01 USD | not published | 262.1K |
| Drex v1.5 | nace | 0.05 USD | not published | 131.1K |
| Drex v2.0 | nace | 0.07 USD | not published | 131.1K |
| Classify-1 | scaledown | 0.05 USD | not published | 1M |
| Mercury Decide | inception | 0.02 USD | not published | 65.5K |
| Tev1 4B Experimental | together | 0.05 USD | not published | 32.8K |
| Kev 4B | jaredpalmer | 0.05 USD | not published | 8.2K |
| GPT Image 1.5 | openai | not published | not published | — |
| GPT Image 1 | openai | not published | not published | — |
| GPT Image 2.5 Flare | openai | not published | not published | — |
| GPT Image 2.5 Sunburst | openai | not published | not published | — |
| Grok Imagine Lite | xai | not published | not published | — |
| Qwen3.8 27B Antislop | qwen | 0.7 USD | 6 USD | 262.1K |
| GLM-5.3 Raw | zai | 3 USD | 8.4 USD | 1M |
| OpenJev | rawmodels | 0.05 USD | not published | 32.8K |
| OpenJev Small | rawmodels | 0.03 USD | not published | 32.8K |
| Qwen3.8 Max Preview | qwen | 2.3 USD | 7 USD | 1M |
| Qwen3.7 Max | qwen | 1.7 USD | 5.1 USD | 1M |
| Qwen3.8 Omni Flash | qwen | 0.2 USD | 0.5 USD | 1M |
| Qwen Image 2.1 Turbo | qwen | not published | not published | — |
| Qwen Image 2.1 Pro | qwen | not published | not published | — |
| Qwen Image 3 | qwen | not published | not published | — |
| Qwen Image 3 Pro | qwen | not published | not published | — |
| Kimi K3.1 Pro | moonshot | 1.6 USD | 8 USD | 1M |
| GPT-6.1 Terra | openai | 0.9 USD | 4.3 USD | 1.1M |
| GPT Image 2.6 Sunburst | openai | not published | not published | — |
| Claude Fable 5.2 | anthropic | 5.1 USD | 25.7 USD | 1M |
| Gemini 4 Carbon | 1.1 USD | 5.5 USD | 1M | |
| GPT-6.2 Sol | openai | 1.1 USD | 5.5 USD | 1.1M |
| GPT-6.2 Astra | openai | 4.8 USD | 24 USD | 1.1M |
Kumo rates per 1M tokens (input / output) after the routing discount — a standard saving of 25–30% off list; committed volume adds up to 20 points more, reaching ~50% at the 1B-token tier. The full catalog with cached-input pricing lives on the models page
Want the longer version?
See exactly how a request travels through the gateway — or just ask us directly