Anthropic
·Released on Sep 29, 2025Claude Sonnet 4.5 API Benchmarks, Pricing & Provider Data
Compare Claude Sonnet 4.5 with another model
Choose a model to open its comparison page.
LLM
Claude Sonnet 4.5 benchmark, API pricing, and provider data cover 615 API providers, with prices starting at $0.0041/request. Claude Sonnet 4.5 free API options are available from 8 providers. The page also shows measured API speed and first-token latency.
Anthropic Claude Sonnet 4.5 balances strong reasoning, coding, and agent capabilities with lower latency and cost than Opus, making it a practical default for production assistants.
Quality
#77of 100
48.0
LMSpeed score
Speed
41char/s
4.57 s
Cost
#156of 181
$0.0041/ 1M · 8:1 in:out
$0.0007 in · $0.0035 out
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 5 / 8
- Methodology
- V3.0
#1Knowledge54.5Provisional1/4 Measured dimensions
80% interval: 38.4–70.5
broad knowledge54.5
benchlm_category_knowledge · benchlm_category_knowledge
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#2Coding51.8Estimated2/4 Measured dimensions
80% interval: 40.6–62.9
code generation52.6
livecodebench · livecodebench / scicode · scicode
repository engineeringPrior only
debugging testing51
swe_verified · swe_verified
tooling qualityPrior only
#3Agents46.6RatedGlobal rank #433/4 Measured dimensions
80% interval: 37.8–55.3
planning49.7
deep_planning · gert_labs
tool usePrior only
environment execution40.4
osworld · os_world_verified / terminalbench · benchlm_agentic_terminal_bench2 / vita_bench · vita_bench
recovery reliability49.6
jobbench · job_bench
#4Reasoning45.6Estimated3/4 Measured dimensions
80% interval: 36.7–54.5
abstract logic32.4
arc_agi · arc_agi2
scientific causal47.2
gpqa · gpqa / hle · hle
multistep constraints57.3
mmlu_pro · mmlu_pro
evidence verificationPrior only
#5Math42.5Estimated2/4 Measured dimensions
80% interval: 30.2–54.8
foundational mathPrior only
competition math35.8
aime · aime2025
proof frontier49.2
frontiermath · frontier_math_v2_tier4 / frontiermath · frontier_math_v2_tiers13
applied tool mathPrior only
No data:MultilingualMultimodalInstruction following
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
INPUT
1Mtokens
≈ 1.2K pages of text
OUTPUT
64Ktokens
8K128K1M4M
1M
Features
Rankings
Excels at
Falls behind in
Detailed scores
Updated: Sep 1, 2026Overall
undefined metric} other undefined metrics}}
Overall score48.0#77 / 100
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Pricing
undefined metric} other undefined metrics}}
Input price$3.00/M#156 / 181Output price$15.00/M#156 / 181
Pricing
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score46.6#4380% interval37.8–55.33/4 Measured dimensionsAgentic score33.4#58 / 69Terminal-Bench 2.050.0#45 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decomposition49.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_planning · gert_labs · z -0.02 · q 1.00
Tool usePrior only
Environment & long-horizon execution40.4
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
osworld · os_world_verified · z -0.98 · q 1.00
terminalbench · benchlm_agentic_terminal_bench2 · z -0.83 · q 1.00
vita_bench · vita_bench · z -1.07 · q 1.00
Recovery & completion reliability49.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
jobbench · job_bench · z -0.30 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Score51.880% interval40.6–62.92/4 Measured dimensionsLiveCodeBench59.0%#45 / 115SciCode42.8%#58 / 206
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Code generation52.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
livecodebench · livecodebench · z 0.28 · q 1.00
scicode · scicode · z 0.46 · q 1.00
Repository engineeringPrior only
Debugging & testing51
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
swe_verified · swe_verified · z 0.08 · q 1.00
Tool-assisted development & qualityPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
LiveCodeBenchV3 evidence
LMSpeed rank#45
Score59.0%
Sourceartificialanalysis.ai
UpdatedSep 1, 2026
Confidence4
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score45.680% interval36.7–54.53/4 Measured dimensionsMMLU-Pro86.0%#23 / 129GPQA72.7%#130 / 213
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Abstract logic32.4
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
arc_agi · arc_agi2 · z -2.53 · q 1.00
Scientific & causal reasoning47.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
gpqa · gpqa · z -0.22 · q 1.00
hle · hle · z -0.47 · q 1.00
Multi-step constraints57.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu_pro · mmlu_pro · z 0.77 · q 1.00
Evidence integration & verificationPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
MMLU-ProV3 evidence
LMSpeed rank#23
Score86.0%
Sourceartificialanalysis.ai
UpdatedSep 1, 2026
Confidence4
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score54.580% interval38.4–70.51/4 Measured dimensionsKnowledge score72.2#24 / 69
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledge54.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
benchlm_category_knowledge · benchlm_category_knowledge · z 0.35 · q 1.00
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Score42.580% interval30.2–54.82/4 Measured dimensionsAIME 202587.0#4 / 4Math score34.9#47 / 62
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Foundational mathPrior only
Competition math35.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aime · aime2025 · z -2.43 · q 0.50
Advanced proofs49.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
frontiermath · frontier_math_v2_tier4 · z -0.24 · q 1.00
frontiermath · frontier_math_v2_tiers13 · z -0.41 · q 1.00
Applied & tool-assisted mathPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
FrontierMath v2 (Tiers 1-3)V3 evidence
LMSpeed rank#33
Score13.5
Sourcebenchlm.ai
UpdatedAug 20, 2026
Confidence2
FrontierMath v2 (Tier 4)V3 evidence
LMSpeed rank#23
Score4.2
Sourcebenchlm.ai
UpdatedAug 20, 2026
Confidence2
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Cross-language understandingPrior only
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
80% interval30.8–69.20/4 Measured dimensionsDesign Arena Website1201.0#47 / 75
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoningPrior only
Video & grounded actionPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalizationPrior only
Multi-turn & long instructionsPrior only
OpenRouter endpoints
7 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Google google-vertex/global | $3/M | $15/M | 100.0% | — | — | undefined tokens / undefined tokens |
Anthropic anthropic | $3/M | $15/M | 99.9% | — | — | undefined tokens / undefined tokens |
Amazon Bedrock amazon-bedrock | $3/M | $15/M | 99.9% | — | — | undefined tokens / undefined tokens |
Amazon Bedrock amazon-bedrock/eu-west-1 | $3.30/M | $16.50/M | 99.8% | — | — | undefined tokens / undefined tokens |
Azure azure/global | $3/M | $15/M | 99.7% | — | — | undefined tokens / undefined tokens |
Claude Platform on AWS claude-on-aws | $3/M | $15/M | 99.6% | — | — | undefined tokens / undefined tokens |
Google google-vertex/us-east5 | $3.30/M | $16.50/M | — | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Claude Sonnet 4.5 API pricing across 607 providers. Prices range from $0.0041/request to $9600.00/M. 钠 API offers the lowest rate at $0.0041/request. 8 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | claude-sonnet-4-5-20250929 | default | -93%$0.205/M Cache read$0.021/M | -93%$1.03/M | 41.4 t/s | 3.27 s | — | |
L1 100% | claude-sonnet-4-5 | default | $3.00/M Cache read$0.300/M | $15.00/M | 28.8 t/s | 9.80 s | — | |
L1 100% | claude-sonnet-4-5-20250929 | default | $2.99/M Cache read$0.299/MCache write$3.74/MCache write 1h$5.98/M | $14.96/M | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929 | cc | -64%$1.07/M Cache read$0.107/M | -64%$5.36/M | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929 | claude_kiro | -65%$1.05/M | -65%$5.25/M | — | — | — | |
L1 99% | claude-sonnet-4-5-20250929 | aws | -99%$0.035/M Cache read$0.0035/MCache write$0.044/MCache write 1h$0.070/M | -99%$0.176/M | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929 | default | -86%$0.410/M Cache read$0.041/MCache write$0.512/MCache write 1h$0.820/M | -86%$2.05/M | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929 | default | -86%$0.411/M | -86%$2.05/M | — | — | — | |
L1 100% | claude-sonnet-4.5 | default | -86%$0.411/M | -86%$2.05/M | — | — | — | |
L1 100% | claude-sonnet-4-5 | default | -86%$0.411/M | -86%$2.05/M | — | — | — | |
L1 100% | claude-sonnet-4-5-all | claude_official_re_19 | -74%$0.781/M | -74%$3.90/M | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929 | default | -86%$0.411/M Cache read$0.041/M | -86%$2.05/M | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929 | default | $3.00/M Cache read$0.300/MCache write$3.75/MCache write 1h$6.00/M | $15.00/M | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929 | default | -23%$2.30/M | -23%$11.51/M | — | — | — | |
兔子API Free | L1 100% | claude-sonnet-4-5 | Claude-Code | Free | Free | — | — | — |
L1 100% | claude-sonnet-4-5-all | default | Free | Free | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929 | default | Free | Free | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929-c | default | $0.114/request | - | — | — | — | |
L1 100% | claude-sonnet-4-5 | default | $3.00/M Cache read$0.300/M | $15.00/M | — | — | — | |
L1 100% | claude-sonnet-4-5-20250929 | default | $3.00/M Cache read$0.300/MCache write$3.75/MCache write 1h$6.00/M | $15.00/M | — | — | — |
Showing 20 model IDs of 135.
Alternatives & Similar Models
Claude Sonnet 4.6
claude-sonnet-4-6
Anthropic Claude Sonnet 4.6 extends the Sonnet line with improved tool use, coding reliability, and long-context performance for everyday production workloads.
214 shared providers
Claude Opus 4.6
claude-opus-4-6
Anthropic Claude Opus 4.6 is the most capable Claude Opus tier, optimized for complex analysis, long-horizon coding, and high-stakes enterprise reasoning workloads.
212 shared providers
Claude Haiku 4.5
claude-haiku-4-5
Anthropic Claude Haiku 4.5 delivers fast, low-cost responses while retaining solid instruction following for chat, classification, and lightweight coding.
211 shared providers
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
209 shared providers
Claude Opus 4.5
claude-opus-4-5
Anthropic Claude Opus 4.5 is the flagship Claude model for the hardest reasoning, research, and multi-step agent tasks where accuracy matters more than speed.
203 shared providers
GPT-5.3 Codex
gpt-5-3-codex
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
198 shared providers
Frequently Asked Questions
- What benchmark data does Claude Sonnet 4.5 include?
- LMSpeed shows Claude Sonnet 4.5 benchmark context, API price, output speed, first-token latency, and provider data across 615 providers when those signals are available.
- What is the Claude Sonnet 4.5 API price?
- Claude Sonnet 4.5 has pricing from 615 providers, ranging from $0.0041/request to $9600.00/M. 钠 API has the lowest listed price.
- What does the Claude Sonnet 4.5 API pricing table include?
- The Claude Sonnet 4.5 API pricing table compares 615 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Claude Sonnet 4.5 API pricing?
- 钠 API currently has the lowest listed Claude Sonnet 4.5 price at $0.0041/request across 615 providers.
- Can I compare Claude Sonnet 4.5 API price and speed together?
- Yes. LMSpeed shows Claude Sonnet 4.5 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is Claude Sonnet 4.5 API free?
- Yes, Claude Sonnet 4.5 free API options are available through 8 providerundefined other undefined} on LMSpeed, including 兔子API, Dext API, 兔子API, 兔子API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Claude Sonnet 4.5 free API access?
- LMSpeed currently lists 8 free API providerundefined other undefined} for Claude Sonnet 4.5: 兔子API, Dext API, 兔子API, 兔子API, 兔子API. Check each provider row before using it because free tier limits can change.