impulse

Claude Sonnet 4.6

Frontier lab

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.

API id claude-sonnet-4-6Released 17 Feb 2026 (Feb 2026)
A newer model in this line is out: Claude Sonnet 5.5, released 28 Sep 2026.
Azure AI Foundry retires it on 10 Feb 2027 (in 83 days). 9 hosts keep serving it.
Input / 1M
$3.00
at Anthropic
Output / 1M
$15.00
at Anthropic
Context window
1M
tokens
Max output
128K
tokens per reply
Hosts
10
19 listings
Released
Feb 2026
17 Feb 2026

Pricing

List prices at Anthropic, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$3.00$15.00
Cached input
90% off input
$0.30
Cache write, 5 minutes$3.75
Cache write, 1 hour$6.00
Batch
50% off
$1.50$7.50
Web search
$10.00 per 1,000 searches
Regional endpoints
10% more

What it costs a month

At Anthropic list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,782
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,332
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$2,232
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$5,400
Use your own numbers

Where to run it

10 hosts serve Claude Sonnet 4.6. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
AnthropicLab API
claude-sonnet-4-6
$3.00 / $15.00
databricks-claude-sonnet-4-6
$3.00 / $15.00
anthropic.claude-sonnet-4-6
$3.00 / $15.00
claude-sonnet-4-6
$3.00 / $15.00
Retires 10 Feb 2027
claude-sonnet-4-6
$3.00 / $15.00
claude-sonnet-4-6
$3.00 / $15.00
DeepInfraInference
claude-sonnet-4-6
$3.00 / $15.00
ReplicateInference
claude-sonnet-4.6
$3.00 / $15.00
PerplexityGateway
claude-sonnet-4-6
$3.00 / $15.00
claude-sonnet-4-6
$4.05 / $20.25
+35% vs headline
GitHub CopilotSubscription
claude-sonnet-4.6
In the subscription
Show 8 more listings: regions, snapshots and variants
Amazon Bedrock
Claude Platform
claude-sonnet-4-6
$3.00 / $15.00
global
global.anthropic.claude-sonnet-4-6
$3.00 / $15.00
au
au.anthropic.claude-sonnet-4-6
$3.30 / $16.50
+10% vs headline
eu
eu.anthropic.claude-sonnet-4-6
$3.30 / $16.50
+10% vs headline
jp
jp.anthropic.claude-sonnet-4-6
$3.30 / $16.50
+10% vs headline
us
us.anthropic.claude-sonnet-4-6
$3.30 / $16.50
+10% vs headline
apac
apac.anthropic.claude-sonnet-4-6
$3.30 / $16.50
+10% vs headline
Vertex AI
Alias
claude-sonnet-4-6@default
$3.00 / $15.00

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImagesPDFs
Produces
Text
Effort settings the source lists
max
Features
Adaptive thinkingComputer useNative structured outputPDF inputPrompt cachingBuilt-in web search

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Anthropic.

Smaller Anthropic models

  • Claude Sonnet 5.5
    Anthropic · on Anthropic
    $2.00 / $10.00
    Has every key capability
    33% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    97% less

Other frontier labs

  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    20% less
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    33% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    50% less
  • GPT-6.2 Sol
    OpenAI · on OpenAI
    $2.00 / $10.00
    Has every key capability
    33% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    33% less
  • Qwen4 Max
    Alibaba Qwen · on Together AI
    $1.43 / $4.28
    Has every key capability
    64% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    71% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    91% less

Model line

Newer and older versions, at each lab's own price.

  1. Sep 2026Claude Sonnet 5.5Latest$2.00 / $10.00
  2. Jun 2026Claude Sonnet 5$2.00 / $10.00
  3. Feb 2026Claude Sonnet 4.6This page$3.00 / $15.00
  4. Sep 2025Claude Sonnet 4.5$3.00 / $15.00
  5. UndatedClaude Sonnet 4.1$3.00 / $15.00
  6. May 2025Claude Sonnet 4$3.00 / $15.00
  7. Jun 2024Claude 3.7 Sonnet$3.00 / $15.00
  8. Jun 2024Claude 3.5 Sonnet$3.00 / $15.00

Call it

Using Anthropic's API.

Python
from anthropic import Anthropic

client = Anthropic()  # reads ANTHROPIC_API_KEY

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

Quick answers

How much does Claude Sonnet 4.6 cost?

On Anthropic, Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens. Cached input costs $0.30 per million tokens.

Which APIs offer Claude Sonnet 4.6?

Claude Sonnet 4.6 runs on 10 APIs: Anthropic, Databricks, Amazon Bedrock, Azure AI Foundry, Snowflake, Vertex AI, DeepInfra, Replicate, Perplexity and Kyma API.

What is Claude Sonnet 4.6's context window?

1M tokens, with up to 128K tokens in one reply.

Is Claude Sonnet 4.6 being retired?

Azure AI Foundry retires it on 10 Feb 2027. 9 hosts keep serving it.

Is there a newer version of Claude Sonnet 4.6?

Yes. Claude Sonnet 5.5 is the newest model in this line, released on 28 Sep 2026.

What are cheaper alternatives to Claude Sonnet 4.6?

Models that cost less and keep most of what it can do: Claude Sonnet 5.5 on Anthropic (33% less), GPT-5.3 Codex on OpenAI (20% less), Gemini 4 Carbon on Google AI Studio (33% less) and Kimi K3.1 Pro on Databricks (33% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Claude Sonnet 4.6 released?

Anthropic released it on 17 Feb 2026.

What is Claude Sonnet 4.6's API model id?

Use claude-sonnet-4-6 with Anthropic. Other hosts use their own ids: databricks-claude-sonnet-4-6 on Databricks, anthropic.claude-sonnet-4-6 on Amazon Bedrock, claude-sonnet-4.6 on Replicate.

Sources

Raw catalog entry for claude-sonnet-4-6 on Anthropic
{
  "supports_web_search": true,
  "supports_anthropic_compaction": true,
  "cache_creation_input_token_cost": 0.00000375,
  "cache_creation_input_token_cost_above_1hr": 0.000006,
  "cache_creation_input_token_cost_batches": 0.000001875,
  "cache_read_input_token_cost": 3e-7,
  "cache_read_input_token_cost_batches": 1.5e-7,
  "input_cost_per_token": 0.000003,
  "input_cost_per_token_batches": 0.0000015,
  "litellm_provider": "anthropic",
  "max_input_tokens": 1000000,
  "max_output_tokens": 128000,
  "mode": "chat",
  "output_cost_per_token": 0.000015,
  "output_cost_per_token_batches": 0.0000075,
  "search_context_cost_per_query": {
    "search_context_size_high": 0.01,
    "search_context_size_low": 0.01,
    "search_context_size_medium": 0.01
  },
  "supports_adaptive_thinking": true,
  "supports_legacy_thinking": true,
  "supports_assistant_prefill": false,
  "supports_computer_use": true,
  "supports_function_calling": true,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_thinking_cache_preservation": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_native_structured_output": true,
  "supports_max_reasoning_effort": true,
  "supports_tool_choice": true,
  "supports_vision": true,
  "supports_output_config": true,
  "prompt_cache_min_tokens": 1024,
  "provider_specific_entry": {
    "us": 1.1
  },
  "source": "https://platform.claude.com/docs/en/about-claude/pricing"
}