Claude Sonnet 5 Is Live on BUZZ: Model ID, Pricing, and Migration Notes

Claude Sonnet 5 — the balanced workhorse of the new Claude 5 family — is now routable through BUZZ AI Gateway. It is both newer and cheaper than Sonnet 4.6, which makes it the new default for most chat, drafting, and everyday coding. Change the model string to claude-sonnet-5 and you are on it. This post covers the exact identifier, the price, and the one thing to watch when you switch.

Published 2026-06-30 · Reading time ~5 min

The identifier

The model name is claude-sonnet-5. As with every Claude model, Anthropic uses hyphens, not dots — claude-sonnet-5.0 is not valid and will return a 404 model not found. If you see that error after switching, check the string first.

BUZZ exposes Sonnet 5 on both interfaces it already serves:

• Anthropic Messages at https://buzzai.cc/v1/messages — used by Claude Code and the official anthropic SDK.
• OpenAI-compatible at https://buzzai.cc/v1/chat/completions — used by the openai SDK and anything that speaks the chat.completions schema.

The full live model list is always published at https://buzzai.cc/models. If a name appears there, your key can reach it.

Calling it

Anthropic Messages (curl):

curl https://buzzai.cc/v1/messages \
  -H "x-api-key: $BUZZ_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Summarize this changelog into release notes."}]
  }'

OpenAI SDK (Python) — only base_url and model differ from a stock OpenAI call:

from openai import OpenAI

client = OpenAI(
    base_url="https://buzzai.cc/v1",
    api_key="YOUR_BUZZ_KEY",
)

resp = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Summarize this changelog into release notes."}],
)
print(resp.choices[0].message.content)

Claude Code — point it at BUZZ once and select Sonnet 5 like any other model:

export ANTHROPIC_BASE_URL=https://buzzai.cc
export ANTHROPIC_AUTH_TOKEN=YOUR_BUZZ_KEY
# then select claude-sonnet-5 in Claude Code's model picker

Pricing: newer and cheaper than 4.6

The headline for Sonnet 5 is that it undercuts the model it replaces. Sonnet 5 is billed pure pay-per-token, no monthly fee and no minimum spend.

That is a one-third cut on both input and output for the newer model. For most workloads there is no trade-off to reason about: Sonnet 5 is the straight upgrade. Prompt cache reads and writes are billed automatically using Anthropic's official discount multipliers, so a workload with a stable reused prefix pays far below even the $0.08 headline input rate. See the prompt caching playbook for how to structure requests so the cache actually hits.

Upgrading from Sonnet 4.6: what changes (almost nothing)

The one thing to watch: cache warm-up

Prompt cache entries are scoped per model. A prefix you cached under claude-sonnet-4-6 does not carry over to claude-sonnet-5 — the first request on the new model is a cache miss and pays the full input rate for that prefix. After that first warm-up pass, cache reads resume normally.

If you swap models mid-session and notice cache_read_input_tokens drop to zero for a request or two, that is expected. It climbs back as the new model's cache fills.

Where Sonnet 5 fits in the Claude 5 family

Sonnet 5 is the default. It handles the overwhelming majority of production traffic — chat, drafting, summarization, routine coding, tool-calling loops — at a fraction of the frontier price. Reserve Claude Fable 5 for the genuinely hard requests: deep multi-file refactors, long agentic chains, tricky analysis where a wrong answer costs real money.

Because BUZZ serves the whole Claude 5 family behind one key and one endpoint, the "default to Sonnet 5, escalate to Fable 5" pattern is a single string in your own routing code. For a full decision tree, see the Claude 5 family selection guide.