Anthropic200K (1M tier available) contextclaude-sonnet-4-6

Claude Sonnet 4.6

The default workhorse — best price-performance for >90% of agent traffic

Claude Sonnet 4.6 is the right default for most production AI workloads in 2026 — Claude Code's primary model, Cursor's most-used Claude option, and the price-performance sweet spot of the entire Anthropic lineup. Strong at coding, agent work, and document analysis, with an optional 1M-token context tier for very long inputs.

Pricing

Rate	List price	Anvat effective	Savings
Input (≤200K)	$3.00	$2.10	30%
Output (≤200K)	$15.00	$10.50	30%
Input (1M tier)	$6.00	$4.20	30%
Output (1M tier)	$22.50	$15.75	30%
Cache write (5 min)	$3.75	$2.63	30%
Cache read	$0.30	$0.21	30%
All prices per million tokens (MTok). List = provider direct. Anvat effective = 30% discount applied.

Pricing verified 2026-06 · See full Anvat pricing

Strengths

Best price-performance on the market for coding agents
Strong tool use — second only to Opus in reliability
1M context option for long-document analysis
Excellent prompt caching support (Claude Code hits 60-85% cache rate in prod)
Sonnet 4.6 + caching beats Opus 4.5 on most real workloads at 1/5th the cost

Where it underperforms

Not Opus-tier on hardest reasoning tasks
1M tier is 2× more expensive than 200K — only use when needed
Output speed slower than Haiku for short responses

Use cases this model is the right pick for

Claude Code default model (most users)
Coding agents — refactor, review, test generation
Document Q&A with prompt caching
Multi-file code generation
Agent orchestration where Opus is overkill

Benchmarks

coding
Coding benchmarks
Top-tier (close to Opus)
agentic
Tool-use reliability
Excellent
reasoning
Long-context @ 1M
Strong on the extended tier

Benchmark numbers self-reported by provider; verify against the latest publisher documentation before quoting.

Quickstart

Same wire format as direct provider APIs — your existing SDK code keeps working. Point at api.anvat.app/v1 and use your Anvat key.

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: "https://api.anvat.app/v1",
  authToken: process.env.ANVAT_API_KEY,
});

const response = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 1024,
  system: [{
    type: "text",
    text: largeSystemPrompt,
    cache_control: { type: "ephemeral" }, // 90% off on cache hits
  }],
  messages: [
    { role: "user", content: "Add a retry wrapper to this fetch helper..." },
  ],
});

Try Claude Sonnet 4.6 — 30% off list

Same model, same quality, same wire format — at the discounted Anvat effective rate. $2 free credit on signup, no card required.

Get a key →