Claude Code counts tokens at Anthropic's rate. On a large research run that reads hundreds of sources, or on an iterative landing page rewritten twenty times, the bill grows fast — and the lion's share is eaten not by \"thinking\" but by volume: reading, drafts, the housekeeping calls of agents. The good news: that volume can be offloaded onto Chinese models that cost 10–50× less, without changing a single familiar step in Claude Code. The bad: there's a precisely drawn line here, and if you don't know it, the savings turn into rework.
\n\nThis guide is practical. Below: how it works mechanically, which providers actually plug in (with verified pricing as of June 2026), which model to take for which task, ready-made configs for Windows, the two tactics that cut the bill the hardest, and an honest list of where you must not save.
\n\n\n\nClaude Code isn't bolted to Anthropic's servers forever. It reads the backend address from the environment: ANTHROPIC_BASE_URL (where to send requests) and ANTHROPIC_AUTH_TOKEN (what to authenticate with). If a provider exposes an Anthropic-compatible endpoint — usually an address with a /anthropic suffix — you redirect the CLI to someone else's server with a single variable, and your entire workflow (agents, skills, parallel tool-use) runs without a single change in code.
The key watershed of the entire comparison is this: DeepSeek, Zhipu GLM, Moonshot Kimi, MiniMax, Alibaba Qwen, and even Xiaomi MiMo already have an official /anthropic — they plug in within thirty seconds. But that endpoint is \"trimmed\" in all of them: it does not carry MCP servers, Claude Code's native web_search, images/PDF, and features behind anthropic-beta. This isn't a bug of a particular provider but a shared property — and it's exactly what determines what can be offloaded onto the cheap option and what must stay on Claude.
Below are the providers with a working /anthropic, ordered from the cheapest-and-effective. Prices verified from official documentation (June 2026), in dollars per 1M tokens.
| Model | Endpoint | Input | Output | Cache-hit | Context | Strength |
|---|---|---|---|---|---|---|
| DeepSeek v4-flash | api.deepseek.com/anthropic | $0.14 | $0.28 | $0.0028 | 1M | cheapest usable default |
| DeepSeek v4-pro | same one | $0.435 | $0.87 | $0.0036 | 1M | strong reasoner (→ opus) |
| GLM-4.7-FlashX | api.z.ai/api/anthropic | $0.07 | $0.40 | $0.01 | ~200K | ultra-cheap bulk content |
| GLM-4.6 / 4.7 | same one | $0.60 | $2.20 | $0.11 | 200K | multilingual (UK) + tool-use |
| GLM-5.2 | same one | $1.40 | $4.40 | $0.26 | 1M (opt-in) | flagship-quality coding |
| Kimi k2.7-code | api.moonshot.ai/anthropic | $0.95 | $4.00 | $0.19 | 262K | long-horizon agentic coding |
| MiniMax M2.7 | api.minimax.io/anthropic | $0.30 | $1.20 | $0.06 | 200K | cheap agentic coding |
| Qwen3-Coder-Next | dashscope…/apps/anthropic | $0.30–0.80 | $1.50–4.00 | ~10–20% | 262K | multilingual coding |
| Xiaomi MiMo v2.5 | api.xiaomimimo.com/anthropic | ~$0.15 | ~$0.29 | ~$0.003 | 1M | cheap 1M agent |
| Claude Opus / Sonnet | native | $5+ | $25+ | cache_control | 200K+ | reference + MCP / web / images |
Separately — subscriptions with a fixed price instead of a meter, if your load is predictable:
\n\n| Subscription | Price / mo | Model | For whom |
|---|---|---|---|
| GLM Coding Plan | Lite $18 · Pro $72 · Max $160 (promo −30% until September 2026) | glm-5.2 | daily coding / landing pages |
| MiniMax Token Plan | Plus $20 · Max $50 · Ultra $120 | M2.x | agentic sessions |
| Qwen Coding Plan | Pro $50 (Lite discontinued) | qwen3.7-plus | multilingual coding |
The main mistake is hunting for \"one model for everything.\" The right way is to route by task type.
\n\n| Task | Primary model | Why / caveat |
|---|---|---|
| Large research | DeepSeek v4-flash (gathering/reading) → v4-pro or Claude (synthesis) | 1M context + cache-hit $0.0028 make bulk reading almost free. But web_search through DeepSeek doesn't work — feed sources as files / via WebFetch, keep the web phase on Claude. |
| Landing pages | GLM Coding Plan (glm-5.2); fallback DeepSeek v4-pro | A fixed subscription removes the meter anxiety while iterating. Images don't go through the endpoint → keep Figma MCP and screen-driven design on Claude. |
| Bulk content | EN: DeepSeek v4-flash / GLM-4.7-FlashX. UK: GLM-4.6/4.7, final — Claude | DeepSeek is trained on EN/ZH — its Ukrainian is noticeably weaker. GLM is better multilingually. Cheap draft + Claude polish = optimum. |
| Agentic coding | GLM Coding Plan; fallback DeepSeek v4-pro | Both hold parallel tool-use well. MCP (Notion / GitHub / Postgres / Figma) does NOT work through Chinese endpoints — keep such workflows on Claude. |
| Ukrainian quality | Claude (final); GLM draft; avoid DeepSeek for UK output | DeepSeek's Ukrainian quality is lower (EN/ZH corpus). The Ukrainian reference is Claude. Don't cut corners here blindly. |
Run them in a separate terminal — environment variables override settings.json, so your current native Claude session stays untouched. The \"budget\" profile for volume and research:
# ПРОФІЛЬ «БЮДЖЕТ» — DeepSeek (дослідження, масовий текст, scaffold)\n$env:ANTHROPIC_BASE_URL = \"https://api.deepseek.com/anthropic\"\n$env:ANTHROPIC_AUTH_TOKEN = \"sk-<твій_deepseek_key>\"\n$env:ANTHROPIC_API_KEY = \"\" # ОБОВ’ЯЗКОВО порожній, не unset\n$env:ANTHROPIC_DEFAULT_OPUS_MODEL = \"deepseek-v4-pro\"\n$env:ANTHROPIC_DEFAULT_SONNET_MODEL = \"deepseek-v4-flash\"\n$env:ANTHROPIC_DEFAULT_HAIKU_MODEL = \"deepseek-v4-flash\"\n$env:CLAUDE_CODE_SUBAGENT_MODEL = \"deepseek-v4-flash\" # субагенти на найдешевшому\nclaudeThe \"coding / landing pages\" profile on the fixed GLM subscription:
\n\n# ПРОФІЛЬ «КОДИНГ / ЛЕНДІНГИ» — GLM Coding Plan (фіксована підписка)\n$env:ANTHROPIC_BASE_URL = \"https://api.z.ai/api/coding/paas/v4\"\n$env:ANTHROPIC_AUTH_TOKEN = \"<твій_zai_key>\"\n$env:ANTHROPIC_API_KEY = \"\"\n$env:ANTHROPIC_DEFAULT_OPUS_MODEL = \"glm-5.2\"\n$env:ANTHROPIC_DEFAULT_SONNET_MODEL = \"glm-5.2\"\n$env:ANTHROPIC_DEFAULT_HAIKU_MODEL = \"glm-4.7\"\nclaudeIf you want automatic routing within a single session (housekeeping calls and reading — to the cheapest, the main reasoning — to a pricier one), set up claude-code-router (npm i -g @musistudio/claude-code-router, launch with ccr code):
// %APPDATA%\\Claude Code Router\\config.json — авто-роутинг в одній сесії\n{\n \"Providers\": [\n { \"name\": \"deepseek\",\n \"api_base_url\": \"https://api.deepseek.com/chat/completions\",\n \"api_key\": \"sk-...\", \"models\": [\"deepseek-v4-flash\", \"deepseek-v4-pro\"] },\n { \"name\": \"zai\",\n \"api_base_url\": \"https://api.z.ai/api/anthropic\",\n \"api_key\": \"...\", \"models\": [\"glm-5.2\", \"glm-4.7\"] }\n ],\n \"Router\": {\n \"default\": \"zai,glm-5.2\", // головний reasoning\n \"background\": \"deepseek,deepseek-v4-flash\", // службові виклики\n \"think\": \"deepseek,deepseek-v4-pro\", // складні кроки\n \"longContext\": \"deepseek,deepseek-v4-flash\" // читання великих обсягів\n }\n}Cache prefix. Don't turn caching off. Automatic caching keeps the stable beginning of the prompt — the system prompt, the tool schema, large unchanging files — and serves it at a cache-hit price dozens of times cheaper. The practical consequence: keep the unchanging part on top, the variable part at the bottom. Any change at the start breaks the whole cache tail. Through /anthropic the cache_control headers are ignored, but caching still kicks in automatically on the provider's side — nothing extra to do.
Draft → polish. Generate the bulk volume — drafts, boilerplate, source reading — with a cheap model, and send Claude or v4-pro only on the final pass: fact-checking, claim verification, Ukrainian editing. This is classic batch economics: the expensive model strikes precisely at the steps where its quality actually changes the result.
\n\nHere savings turn into rework, because the Chinese /anthropic endpoints physically can't carry this. Switch to native Claude deliberately when the task involves:
deepseek-chat / deepseek-reasoner are aliases for v4-flash, and they disappear on July 24, 2026. Migrate your model names before that date.document block type breaks file work in Claude Code./anthropic it returns 200K of context instead of 1M — Claude Code compacts too early; fixed with the variable CLAUDE_CODE_MAX_CONTEXT_TOKENS=1000000. The M2.x models don't accept images.If you run into these names: OpenCode Zen isn't a model but a curated model gateway from the CLI agent OpenCode (a Claude Code competitor). It's attached to Claude Code only through a Cloudflare proxy — an extra layer you don't need. OpenRouter is a gateway to 300+ models with a single key (handy for A/B), but it officially guarantees Claude Code compatibility only for Anthropic models; for the Chinese ones it's another point of failure, so for working sessions a provider's direct /anthropic is more reliable.
The formula is simple. DeepSeek v4-flash is the workhorse for volume and reading. GLM is for when you need Ukrainian and tool-use. Claude stays on the final polish, MCP, and the sensitive stuff. Keep two or three profiles, switch by task (or hand that off to claude-code-router), don't turn off the cache, and don't skimp on the final pass. The savings on the bulk phase are dozens of times over; the risk is exactly where you deliberately keep Claude.