Anthropic
Claude Sonnet 4.6
model
claude-sonnet-4-6MidStableVisionStreamingVisionToolsBatchLong contextUnited States
Context
1.0M
Input / 1M tokens
$3.00
Output / 1M tokens
$15.00
Weighted tokens formula
1× provider × 4× tier
About this model
Claude Sonnet 4.6
Claude Sonnet 4.6 is Anthropic's mid-tier flagship — the workhorse choice. Near-Opus quality on most tasks at a third of the price. The right default for production agentic workloads.
Released
2024-12
Training cutoff
2024-11
Parameters
Not disclosed
Best for
Use cases
- ✓Production AI assistants
- ✓Coding agents (best price/quality balance)
- ✓Customer support automation
- ✓Document analysis + extraction
- ✓Most agentic workflows with tool calling
Strengths
What it does well
- ●Near-Opus quality at significantly lower cost
- ●Strong instruction-following + tool calling
- ●1M-token context window
- ●Excellent prompt caching support
- ●Faster than Opus — ~2× the throughput
Limitations
Know the trade-offs
- !Trails Opus on the hardest multi-step planning tasks
- !Latency higher than Haiku — not for sub-second UX
- !Premium pricing vs open-weights alternatives
Code example
Chat completion with Claude Sonnet 4.6
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="claude-sonnet-4-6",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Weighted tokens
weighted_tokens = raw_tokens × 1 (provider) × 4 (tier)
Pro plan: 20M weighted tokens/month. Combined multiplier 4×: 5,000,000 raw tokens available.
Alternatives
Similar models in our catalog
Workloads that fit Claude Sonnet 4.6 often fit these too. Compare benchmarks and pricing before locking in a default.