·4 min read
✴️

Claude Sonnet 5 Is on Antbase — 1M Context, and the NetMind Route Costs a Third Less

Claude Sonnet 5, Anthropic's most capable Sonnet-class model, is live on Antbase. Frontier coding, agents, and computer use on a 1M-token context with 128K output — reachable through the same OpenAI-compatible API. Antbase routes it two ways: Anthropic direct, or through NetMind at $2/$10 per 1M instead of $3/$15. You call one model string; the router picks the cheaper healthy path.

AntbaseClaudeClaude Sonnet 5AnthropicNetMindcodingagentsreasoning1M contextOpenAI-compatible

Claude Sonnet 5 is now on Antbase. It's Anthropic's most capable Sonnet-class model — built to be the most agentic Sonnet yet, with frontier performance across coding, long-running agents, browser and computer use, and professional workflows. On Antbase it runs on a 1M-token context window with up to 128K output tokens, image input, and function calling, through the same OpenAI-compatible (and Anthropic-compatible) API you already point at.

What you get

  • •1M-token context window, up to 128K output tokens.
  • •Vision (image input), function calling, streaming, and extended thinking / reasoning.
  • •Frontier-grade coding and multi-step agent workflows — browser and computer use included.
  • •Reachable by name (anthropic/claude-sonnet-5) or through the pools it now feeds: ant:best, ant:reasoning, and ant:coder.

Two routes, one model string

Antbase serves Sonnet 5 two ways: Anthropic direct at standard list price, and through NetMind, which prices the same model lower. You don't choose the backend — cost-weighted routing prefers the cheaper healthy path and falls back to the other if it degrades. Same model, same dashboard, same usage tracking.

  • •Anthropic direct — input $3.00, output $15.00, cache write $3.75, cache read $0.30 per 1M.
  • •NetMind — input $2.00, output $10.00, cache write $2.50, cache read $0.20 per 1M. One rate across the full 1M context.
  • •That is a third off input and output versus the direct list price — for the same weights, behind your existing Antbase key.
python
from openai import OpenAI

client = OpenAI(base_url="https://antbase.ai/v1", api_key="ant-...")

# Pin Claude Sonnet 5 by name — Antbase picks the cheaper healthy backend.
resp = client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    messages=[{"role": "user", "content": "Plan the refactor, then execute it end to end."}],
)

# Or let the router choose the strongest model for the task —
# Sonnet 5 now sits in these pools:
resp = client.chat.completions.create(
    model="ant:coder",   # also: ant:best, ant:reasoning
    messages=[{"role": "user", "content": "Refactor this 500-line module for readability."}],
)

Want to force the cheaper path explicitly? Pin the NetMind route by name:

bash
curl https://antbase.ai/v1/chat/completions \
  -H "Authorization: Bearer $ANT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "netmind/anthropic/claude-sonnet-5",
    "messages": [{"role":"user","content":"Ship it."}]
  }'

Find it in the catalog, or try it side by side in the playground:

Try ANT routing today

Drop-in OpenAI-compatible API. Change your base URL and every request gets intelligent routing across 30+ providers.