Claude Sonnet 5
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.
claude-sonnet-5Released 30 Jun 2026 (Jun 2026)Pricing
List prices at Anthropic, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.00 | $10.00 | |
| Cached input 90% off input | $0.20 | 90% off input | |
| Cache write, 5 minutes | $2.50 | ||
| Cache write, 1 hour | $4.00 | ||
| Batch 50% off | $1.00 | $5.00 | 50% off |
| Web search $10.00 per 1,000 searches | $10.00 per 1,000 searches | ||
| Regional endpoints 10% more | 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
Where to run it
11 hosts serve Claude Sonnet 5. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
AnthropicLab API claude-sonnet-5 | $2.00 / $10.00 | claude-sonnet-5 | |
DatabricksCloud databricks-claude-sonnet-5 | $2.00 / $10.00 | databricks-claude-sonnet-5 | |
Amazon BedrockCloud anthropic.claude-sonnet-5 | $2.00 / $10.00 | anthropic.claude-sonnet-5 | |
Azure AI FoundryCloud claude-sonnet-5 | $2.00 / $10.00 Retires 30 Jun 2027 | claude-sonnet-5 | Retires 30 Jun 2027 |
Vertex AICloud claude-sonnet-5 | $2.00 / $10.00 No retirement before 24 Dec 2026 | claude-sonnet-5 | No retirement before 24 Dec 2026 |
ReplicateInference claude-sonnet-5 | $2.00 / $10.00 | claude-sonnet-5 | |
AIHubMixGateway claude-sonnet-5 | $2.00 / $10.00 | claude-sonnet-5 | |
PerplexityGateway claude-sonnet-5 | $2.00 / $10.00 | claude-sonnet-5 | |
Hostinger RouterCloud claude-sonnet-5 | $2.64 / $13.20 +32% vs headline | claude-sonnet-5 | |
Kyma APICloud claude-sonnet-5 | $2.70 / $13.50 +35% vs headline | claude-sonnet-5 | |
DeepInfraInference claude-sonnet-5 | $3.00 / $15.00 +50% vs headline | claude-sonnet-5 | |
GitHub CopilotSubscription claude-sonnet-5 | In the subscription | claude-sonnet-5 |
Show 13 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| Claude Platform claude-sonnet-5 | $2.00 / $10.00 | claude-sonnet-5 | |||||
| global global.anthropic.claude-sonnet-5 | $2.00 / $10.00 | global.anthropic.claude-sonnet-5 | |||||
| Mantle anthropic.claude-sonnet-5 | $2.20 / $11.00 +10% vs headline | anthropic.claude-sonnet-5 | |||||
| Mantle anthropic.claude-sonnet-5 | $2.20 / $11.00 +10% vs headline | anthropic.claude-sonnet-5 | |||||
| au au.anthropic.claude-sonnet-5 | $2.20 / $11.00 +10% vs headline | au.anthropic.claude-sonnet-5 | |||||
| eu eu.anthropic.claude-sonnet-5 | $2.20 / $11.00 +10% vs headline | eu.anthropic.claude-sonnet-5 | |||||
| jp jp.anthropic.claude-sonnet-5 | $2.20 / $11.00 +10% vs headline | jp.anthropic.claude-sonnet-5 | |||||
| us us.anthropic.claude-sonnet-5 | $2.20 / $11.00 +10% vs headline | us.anthropic.claude-sonnet-5 | |||||
| apac apac.anthropic.claude-sonnet-5 | $2.20 / $11.00 +10% vs headline | apac.anthropic.claude-sonnet-5 | |||||
| us-gov-west-1 anthropic.claude-sonnet-5 | $2.40 / $12.00 +20% vs headline | anthropic.claude-sonnet-5 | |||||
| us-gov-east-1 anthropic.claude-sonnet-5 | $2.40 / $12.00 +20% vs headline | anthropic.claude-sonnet-5 | |||||
| us-gov us-gov.anthropic.claude-sonnet-5 | $2.40 / $12.00 +20% vs headline | us-gov.anthropic.claude-sonnet-5 | |||||
| Vertex AI | |||||||
| Alias claude-sonnet-5@default | $2.00 / $10.00 No retirement before 24 Dec 2026 | claude-sonnet-5@default | 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
- 95% less
Other frontier labs
- 25% less
- 25% less
- 50% less
- 58% less
Open-weight picks
- 0% less
- 44% less
- 57% less
- 87% less
Model line
Newer and older versions, at each lab's own price.
- Sep 2026Claude Sonnet 5.5Latest$2.00 / $10.00
- Jun 2026Claude Sonnet 5This page$2.00 / $10.00
- Feb 2026Claude Sonnet 4.6$3.00 / $15.00
- Sep 2025Claude Sonnet 4.5$3.00 / $15.00
- UndatedClaude Sonnet 4.1$3.00 / $15.00
- May 2025Claude Sonnet 4$3.00 / $15.00
- Jun 2024Claude 3.7 Sonnet$3.00 / $15.00
- Jun 2024Claude 3.5 Sonnet$3.00 / $15.00
Call it
Using Anthropic's API.
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)curl https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{"model": "claude-sonnet-5", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}]}'from litellm import completion
response = completion(
model="anthropic/claude-sonnet-5",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)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
- Amazon Bedrock pricing
- AIHubMix pricing
- Anthropic pricing
- DeepInfra pricing
- GitHub Copilot pricing
- Hostinger Router pricing
- Perplexity pricing
- Replicate pricing
- Vertex AI pricing
- Databricks pricing
- LiteLLM model map
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"
}