Typhoon

typhoon-v2.5-30b-a3b-instruct
Context window131K tokens
Free budgetOngoing free research API (shared rate limits) tokens/mo
Rate limitsnot published
Ongoing free research API info
Typhoon provides an ongoing, rate-limited research API, not monthly credits or a production SLA. Usage data is collected to improve the models and API; review the provider data-use terms before sending sensitive content. Chat, streaming, tool calling and both ASR endpoints were smoke-tested on October 7, 2026. The Isan model was tested with standard Thai speech, not an Isan accuracy benchmark. See https://docs.opentyphoon.ai/en/faq/ and https://docs.opentyphoon.ai/en/asr/.

Get this model the moment it changes

Limits move, models get replaced, better ones launch. Premium routers see this page's data live. Free routers see last month's.

Kích hoạt trực tiếp · $19/yr →

Use it

FreeLLMAPI is a self-hosted router you run yourself. Install it, paste in your free Typhoon key, and typhoon-v2.5-30b-a3b-instruct answers on an OpenAI-compatible endpoint at http://localhost:3001/v1. No credit card, no hosted middleman: your prompts and your provider keys never leave your machine.

Install the router (macOS, Linux, WSL)
curl -fsSL https://freellmapi.co/install.sh | bash
Install the router (Windows PowerShell)
iwr -useb https://freellmapi.co/install.ps1 | iex
Call typhoon-v2.5-30b-a3b-instruct with curl
curl http://localhost:3001/v1/chat/completions \
  -H "Authorization: Bearer freellmapi-your-unified-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "typhoon-v2.5-30b-a3b-instruct",
    "messages": [{"role": "user", "content": "Say hi in five words."}]
  }'
The same request in Python (openai)
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:3001/v1",
    api_key="freellmapi-your-unified-key",
)

resp = client.chat.completions.create(
    model="typhoon-v2.5-30b-a3b-instruct",
    messages=[{"role": "user", "content": "Say hi in five words."}],
)
print(resp.choices[0].message.content)

The router answers on /v1/chat/completions and every other OpenAI surface, plus the Anthropic Messages API, so existing clients need only a new base_url. Swap the model id for auto and the router picks the best free model that is still under its limits. Full reference: docs/api.md.