Skip to content
Dashboard

Claude Sonnet 4.5

Claude Sonnet 4.5 is a coding model from Anthropic with strong benchmark scores, including 77.2% on SWE-bench Verified and 61.4% on OSWorld for computer use, sustaining 30+ hour agentic coding sessions, and delivering substantial gains across coding, reasoning, math, and domain-specific expertise. Your use is subject to Anthropic's Terms & Privacy Policies.

Explicit CachingFile InputReasoningTool UseVision (Image)Web Search
import { streamText } from 'ai'
const result = streamText({
model: 'anthropic/claude-sonnet-4.5',
prompt: 'Why is the sky blue?'
})
Read docs

Copy link to headingMore models by Anthropic

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1M
1.9s
109tps
$5/MFast $10/M
$25/MFast $50/M
Read:$0.50/M
Write:
$6.25/M+1 more
$10/K
+ input costs
+3
anthropic logo
bedrock logo
claudeaws logo
+1
07/24/2026
1M
1.2s
119tps
$3/M$2/M
$15/M$10/M
Read:$0.30/M$0.20/M
Write:
$3.75/M$2.50/M+1 more
$10/K
+ input costs
+3
anthropic logo
bedrock logo
claudeaws logo
+1
06/29/2026
1M
1.0s
100tps
$5/MFast $10/M
$25/MFast $50/M
Read:$0.50/M
Write:
$6.25/M+1 more
$10/K
+ input costs
+3
anthropic logo
bedrock logo
claudeaws logo
+1
05/28/2026
1M
1.0s
60tps
$3/M
$15/M
Read:$0.30/M
Write:
$3.75/M+1 more
$10/K
+ input costs
+3
anthropic logo
bedrock logo
claudeaws logo
+1
02/17/2026
1M
1.3s
60tps
$5/MFast $30/M
$25/MFast $150/M
Read:$0.50/M
Write:
$6.25/M+1 more
$10/K
+ input costs
+3
anthropic logo
bedrock logo
vertexAnthropic logo
02/05/2026
200K
0.7s
109tps
$1/M
$5/M
Read:$0.10/M
Write:
$1.25/M+1 more
$10/K
+ input costs
+3
anthropic logo
bedrock logo
claudeaws logo
+1
10/15/2025