DEV Community: tinyhuman-fpj

Search teniuai for big model tokens with your coding plan.

tinyhuman-fpj — Tue, 12 May 2026 16:53:40 +0000

Deepseek has raised 50 billion yuan

tinyhuman-fpj — Sun, 10 May 2026 04:33:09 +0000

Deepseek has raised 50 billion yuan, and Chinese ai companies are accelerating.To have a try https://teniuapi.online/

big modle coding plan of china

tinyhuman-fpj — Thu, 07 May 2026 16:37:48 +0000

Compared with Claude Opus, Chinese models offer better value for money and are very affordable.
If you are developing complex engineering systems, GLM-5 is your top choice, with 744 billion parameters, suitable for enterprise-level projects and system reconstruction. If you are looking for a more budget-friendly option, DeepSeek is a great choice, with 685 billion parameters and an extremely low price. Oh, and there's Kimi, which is an expert in long context, with 1 trillion parameters, capable of supporting 300 agents working together for 13 hours, making it ideal for maintaining large-scale projects and multi-document analysis. Try out Chinese models, click https://teniuapi.online/

Install claude code

# install npm
npm install -g @anthropic-ai/claude-code

# verify version
claude --version

# update to the latest
sudo npm i -g @anthropic-ai/claude-code
sudo claude update

setting for claude code

mkdir -p ~/.claude && cat > ~/.claude/settings.json << 'EOF'
{
   "env": {
    "ANTHROPIC_BASE_URL": "https://teniuapi.online",
    "ANTHROPIC_AUTH_TOKEN": "Your Api key",
    "API_TIMEOUT_MS": "3000000",
    "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1",
    "ANTHROPIC_MODEL": "glm-5",
    "ANTHROPIC_SMALL_FAST_MODEL": "glm-5",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "glm-5",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "glm-5",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-5"
  }
}
EOF

Click the website to get your api key.

latest ai model tokens

tinyhuman-fpj — Sun, 03 May 2026 13:47:27 +0000

Here, the world's most cutting-edge large model tokens are gathered. We can experience the differences among models provided by various companies, which helps to accelerate the project delivery. Get it by search teniuapi.online.

share big model of deepseekv4

tinyhuman-fpj — Sun, 03 May 2026 03:48:06 +0000

The DeepSeek-V4 series abandons the single model specification and offers two versions for different scenarios: the Pro version with ultimate performance and the Flash version with ultimate cost-effectiveness. The total parameter count reaches 1.6 trillion, with the activated parameter count reaching 49 billion, and the context length is 1 million Tokens. Its core advantages lie in deep reasoning, complex code generation, and Agent tasks.

Three key features:

Super-long context: With the new hybrid attention mechanism (CSA+HCA) and DSA sparse attention, V4 reduces the computing power demand to 27% of the previous generation when processing a million contexts, and the KV cache to 10%.
Agent capabilities leap from "chatting" to "working": The core of V4 lies in its powerful agent capabilities. It is no longer just answering questions but can independently plan tasks, invoke tools, correct errors, and complete deliveries.
Ultimate cost-effectiveness: DeepSeek-V4 continues its inclusive pricing strategy, reducing the calling cost of top models to an extremely low level.
It outperformed all open-source models in evaluations such as LiveCodeBench and HMMT, and was on par with top-tier closed-source models.
It scored 84.4 in the Chinese-SimpleQA evaluation, significantly outperforming GPT-5.5 and Claude.

API Access (Recommended for Developers)
Visit https://teniuapi.online, register and log in, then create a token in the "Token Management" menu.
{ "env": { "ANTHROPIC_BASE_URL": "https://teniuapi.online", "ANTHROPIC_AUTH_TOKEN": "Your API Access Key", "API_TIMEOUT_MS": "3000000", "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1", "ANTHROPIC_MODEL": "deepseek-v4-flash", "ANTHROPIC_SMALL_FAST_MODEL": "deepseek-v4-flash", "ANTHROPIC_DEFAULT_SONNET_MODEL": "deepseek-v4-flash", "ANTHROPIC_DEFAULT_OPUS_MODEL": "deepseek-v4-flash", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "deepseek-v4-flash" }, "skipDangerousModePermissionPrompt": true }