hHamro AI
Free · Open access · No signup

AI, Made Simple.

Hamro AI is a free AI chat and gateway — one public key, dozens of free models across ten providers, routed with automatic failover. Ask questions, write code, or point your coding agent at it.

hHamro AI
Auto
Write a Python function that fetches data from an API and retries on failure.

Here's a resilient fetch with exponential backoff:

python
import time, requests

def fetch(url, retries=3):
    for attempt in range(retries):
        try:
            return requests.get(url, timeout=10).json()
        except requests.RequestException:
            if attempt == retries - 1:
                raise
            time.sleep(2 ** attempt)  # backoff
Message Hamro AI…

54 free models, one key

Llama, Nemotron, DeepSeek, GLM and more — every request routes to a healthy provider automatically, so a hiccup never stops you.

Groq1 free
llama-3.3-70b-versatile
OpenRouter3 free
nemotron-3-ultra-550b-a55b:freenemotron-3-super-120b-a12b:freefree
OpenCode Zen2 free
nemotron-3-ultra-freedeepseek-v4-flash-free
Ollama Cloud4 free
nemotron-3-ultranemotron-3-supergpt-oss:120bgemma4:31b
Naga AI4 free
nemotron-3-ultra-550b-a55b:freenemotron-3-super-120b-a12b:freellama-3.3-70b-instruct:freellama-4-scout-17b-16e-instruct:free
ZenMux3 free
deepseek-v4-flash-freeglm-4.7-flash-freeglm-4.6v-flash-free
LLM75 free
gpt-oss:20bgemma4:31bminimax-m2.7codestral-latestmistral-Nemo-Instruct-2407
Cerebras3 free
zai-glm-4.7gpt-oss-120bgemma-4-31b
Chutes AI7 free
DeepSeek-V4-Flash-0731-TEEQwen3-235B-A22B-Thinking-2507-TEEGLM-5.2-TEEKimi-K2.6-TEEQwen3.6-27B-TEEgemma-4-31B-turbo-TEE+1 more
HuggingFace22 free
Llama-3.3-70B-InstructDeepSeek-V4-Flash-0731DeepSeek-V4-FlashDeepSeek-R1DeepSeek-V3.2Qwen3-235B-A22B-Instruct-2507+16 more

Built for people and for coding agents

Native OpenAI and Anthropic protocols — the same key powers this chat, Claude Code, OpenCode, Cursor and any OpenAI SDK.

Claude Code
One command — the gateway starts itself.
$ npm run claude

# opens Claude Code on
# Hamro AI's free models
OpenCode / any OpenAI client
Point OPENAI_BASE_URL at the gateway.
export OPENAI_API_KEY=nishan-bajagain
export OPENAI_BASE_URL="https://hamro.site/v1"
opencode
curl
Stream a completion in one line.
curl -N https://hamro.site/v1/chat/completions \
  -H "Authorization: Bearer nishan-bajagain" \
  -H "Content-Type: application/json" \
  -d '{"model":"random","messages":
    [{"role":"user","content":"hi"}],
    "stream":true}
Smart routing

Sticky-success routing picks the fastest healthy provider and remembers it.

Automatic failover

429s, 5xx, timeouts and disconnects fall through the chain mid-stream.

Agent-ready

Tool calling, code fences and SSE streaming pass through verbatim.

Private by design

One public key, per-key namespaced history, no account required.

Start chatting — it's free

No signup, no credit card. Just open the chat and ask anything.

Open the chat