impulse

Claude Sonnet 5

Frontier lab

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.

API id claude-sonnet-5Released 30 Jun 2026 (Jun 2026)
Input / 1M
$2.00
at Anthropic
Output / 1M
$10.00
at Anthropic
Context window
1M
tokens
Max output
128K
tokens per reply
Hosts
11
25 listings
Released
Jun 2026
30 Jun 2026

Pricing

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

TierInput / 1MOutput / 1M
Standard$2.00$10.00
Cached input
90% off input
$0.20
Cache write, 5 minutes$2.50
Cache write, 1 hour$4.00
Batch
50% off
$1.00$5.00
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$1,188
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$888
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$1,488
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$3,600
Use your own numbers

Where to run it

11 hosts serve Claude Sonnet 5. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
AnthropicLab API
claude-sonnet-5
$2.00 / $10.00
databricks-claude-sonnet-5
$2.00 / $10.00
anthropic.claude-sonnet-5
$2.00 / $10.00
claude-sonnet-5
$2.00 / $10.00
Retires 30 Jun 2027
claude-sonnet-5
$2.00 / $10.00
No retirement before 24 Dec 2026
ReplicateInference
claude-sonnet-5
$2.00 / $10.00
AIHubMixGateway
claude-sonnet-5
$2.00 / $10.00
PerplexityGateway
claude-sonnet-5
$2.00 / $10.00
claude-sonnet-5
$2.64 / $13.20
+32% vs headline
claude-sonnet-5
$2.70 / $13.50
+35% vs headline
DeepInfraInference
claude-sonnet-5
$3.00 / $15.00
+50% vs headline
GitHub CopilotSubscription
claude-sonnet-5
In the subscription
Show 13 more listings: regions, snapshots and variants
Amazon Bedrock
Claude Platform
claude-sonnet-5
$2.00 / $10.00
global
global.anthropic.claude-sonnet-5
$2.00 / $10.00
Mantle
anthropic.claude-sonnet-5
$2.20 / $11.00
+10% vs headline
Mantle
anthropic.claude-sonnet-5
$2.20 / $11.00
+10% vs headline
au
au.anthropic.claude-sonnet-5
$2.20 / $11.00
+10% vs headline
eu
eu.anthropic.claude-sonnet-5
$2.20 / $11.00
+10% vs headline
jp
jp.anthropic.claude-sonnet-5
$2.20 / $11.00
+10% vs headline
us
us.anthropic.claude-sonnet-5
$2.20 / $11.00
+10% vs headline
apac
apac.anthropic.claude-sonnet-5
$2.20 / $11.00
+10% vs headline
us-gov-west-1
anthropic.claude-sonnet-5
$2.40 / $12.00
+20% vs headline
us-gov-east-1
anthropic.claude-sonnet-5
$2.40 / $12.00
+20% vs headline
us-gov
us-gov.anthropic.claude-sonnet-5
$2.40 / $12.00
+20% vs headline
Vertex AI
Alias
claude-sonnet-5@default
$2.00 / $10.00
No retirement before 24 Dec 2026

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
xhighmax
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 Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    95% less

Other frontier labs

  • Gemini 4 Hydrogen
    Google · on Google AI Studio
    $1.50 / $7.50
    Has every key capability
    25% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    25% less
  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    50% less
  • GPT-5.4 Mini
    OpenAI · on OpenAI
    $0.75 / $4.50
    Has every key capability
    58% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    0% less
  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    44% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    57% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    87% 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 5This page$2.00 / $10.00
  3. Feb 2026Claude Sonnet 4.6$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-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

Quick answers

How much does Claude Sonnet 5 cost?

On Anthropic, Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens. Cached input costs $0.20 per million tokens.

Which APIs offer Claude Sonnet 5?

Claude Sonnet 5 runs on 11 APIs: Anthropic, Databricks, Amazon Bedrock, Azure AI Foundry, Vertex AI, Replicate, AIHubMix, Perplexity, Hostinger Router and 2 more.

What is Claude Sonnet 5's context window?

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

Is Claude Sonnet 5 being retired?

Azure AI Foundry retires it on 30 Jun 2027. 10 hosts keep serving it.

Is there a newer version of Claude Sonnet 5?

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

What are cheaper alternatives to Claude Sonnet 5?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (95% less), Gemini 4 Hydrogen on Google AI Studio (25% less), Grok 4.7 on xAI (25% less) and Kimi K3.1 Pro on Databricks (0% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Claude Sonnet 5 released?

Anthropic released it on 30 Jun 2026.

What is Claude Sonnet 5's API model id?

Use claude-sonnet-5 with Anthropic. Other hosts use their own ids: databricks-claude-sonnet-5 on Databricks, anthropic.claude-sonnet-5 on Amazon Bedrock.

Sources

Raw catalog entry for claude-sonnet-5 on Anthropic
{
  "supports_web_search": true,
  "supports_anthropic_compaction": true,
  "cache_creation_input_token_cost": 0.0000025,
  "cache_creation_input_token_cost_above_1hr": 0.000004,
  "cache_creation_input_token_cost_batches": 0.00000125,
  "cache_read_input_token_cost": 2e-7,
  "cache_read_input_token_cost_batches": 1e-7,
  "input_cost_per_token": 0.000002,
  "input_cost_per_token_batches": 0.000001,
  "litellm_provider": "anthropic",
  "max_input_tokens": 1000000,
  "max_output_tokens": 128000,
  "mode": "chat",
  "output_cost_per_token": 0.00001,
  "output_cost_per_token_batches": 0.000005,
  "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,
  "thinking_on_by_default": true,
  "supports_mid_conversation_system": true,
  "supports_assistant_prefill": false,
  "supports_computer_use": true,
  "supports_function_calling": true,
  "supports_native_structured_output": true,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_thinking_cache_preservation": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_sampling_params": false,
  "supports_tool_choice": true,
  "supports_vision": true,
  "supports_xhigh_reasoning_effort": true,
  "supports_max_reasoning_effort": true,
  "provider_specific_entry": {
    "us": 1.1
  },
  "supports_output_config": true,
  "prompt_cache_min_tokens": 1024,
  "source": "https://platform.claude.com/docs/en/about-claude/pricing"
}