Claude 3 Haiku API Benchmarks, Pricing & Provider Data
Compare Claude 3 Haiku with another model
Choose a model to open its comparison page.
Claude 3 Haiku benchmark, API pricing, and provider data cover 21 API providers, with prices starting at $0.034/M.
Anthropic Claude 3 Haiku is optimized for speed and scale in customer support, routing, and low-latency chat applications.
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 6 / 8
- Methodology
- V3.0
#1Instruction following42.2Provisional1/4 Measured dimensions
#2Knowledge39.2Provisional1/4 Measured dimensions
#3Agents37.9Provisional1/4 Measured dimensions
#4Math36.4Estimated2/4 Measured dimensions
#5Reasoning35.3Estimated2/4 Measured dimensions
#6Coding30.3Provisional1/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Sep 5, 2026Pricing
undefined metric} other undefined metrics}}
Input price$0.250/M#44 / 185Output price$1.25/M#61 / 185
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Score37.980% interval21.9–53.91/4 Measured dimensionsΤ²-bench results21.1#77 / 82
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Score30.380% interval16.4–44.21/4 Measured dimensionsLiveCodeBench15.4%#111 / 115AA-SciCode18.6#111 / 113
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score35.380% interval24.5–46.12/4 Measured dimensionsGPQA37.4%#208 / 217HLE4.1%#179 / 214
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score39.280% interval23.2–55.21/4 Measured dimensionsArtificial Analysis Intelligence Index3.5#117 / 117AA-GPQA Diamond37.4#112 / 113
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Score36.480% interval24.5–48.22/4 Measured dimensionsAIME1.0%#67 / 68MATH-50039.4%#72 / 73
Math
V3.0undefined metric} other undefined metrics}} · Estimated
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
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
80% interval30.8–69.20/4 Measured dimensionsAA-MMMU-Pro30.8#67 / 68
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score42.280% interval26.2–58.21/4 Measured dimensionsAA-IFBench36.1#78 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
OpenRouter endpoints
1 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 |
|---|---|---|---|---|---|---|
Amazon Bedrock amazon-bedrock | $0.250/M | $1.25/M | 100% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Claude 3 Haiku API pricing across 21 providers. Prices range from $0.034/M to $2.00/M. DuckDuck API offers the lowest rate at $0.034/M.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | claude-3-haiku-20240307 | test | -86%$0.034/M Cache read$0.0034/MCache write$0.043/MCache write 1h$0.068/M | -86%$0.171/M | — | — | — | |
L1 99% | claude-3-haiku-20240307 | claude aws 官2 | -38%$0.154/M Cache read$0.015/M | -38%$0.771/M | — | — | — | |
L1 100% | claude-3-haiku-20240307 | claude官 | $1.25/M Cache read$0.125/MCache write$1.56/MCache write 1h$2.50/M | $6.25/M | — | — | — | |
L1 99% | claude-3-haiku-20240307 | claude官 | -32%$0.171/M Cache read$0.017/MCache write$0.214/MCache write 1h$0.342/M | -32%$0.856/M | — | — | — | |
L1 100% | claude-3-haiku-20240307 | Claudecode-求稳分组 | $0.300/M | $1.50/M | — | — | — | |
L1 100% | claude-3-haiku-20240307 | default | -86%$0.034/M Cache read$0.0034/MCache write$0.043/MCache write 1h$0.068/M | -86%$0.171/M | — | — | — | |
L1 0% | claude-3-haiku-20240307 | claude官 | -32%$0.171/M Cache read$0.017/MCache write$0.214/MCache write 1h$0.342/M | -32%$0.856/M | — | — | — | |
L1 0% | claude-3-haiku-20240307 | default | $0.250/M | $1.25/M | — | — | — | |
L1 0% | anthropic/claude-3-haiku | default | $0.250/M | $1.25/M | — | — | — | |
L1 0% | claude-3-haiku-20240307 | claude官 | $0.257/M Cache read$0.026/MCache write$0.321/MCache write 1h$0.514/M | $1.28/M | — | — | — | |
L1 0% | claude-3-haiku-20240307 | default | $1.75/M Cache read$0.175/MCache write$2.19/MCache write 1h$3.50/M | $8.75/M | — | — | — |
Alternatives & Similar Models
GPT-4o
gpt-4o
OpenAI GPT-4o is a multimodal flagship model with fast text, vision, and audio understanding, optimized for real-time chat, coding assistants, and production API workloads.
Claude Sonnet 4
claude-sonnet-4
Anthropic Claude Sonnet 4 balances speed and intelligence for coding, analysis, and enterprise automation, with strong instruction following and long-context performance.
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.
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.
Claude Sonnet 4.5
claude-sonnet-4-5
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.
Gemini 2.5 Pro
gemini-2-5-pro
Google Gemini 2.5 Pro is Google advanced multimodal model with a 1M-token context window, strong STEM reasoning, and native support for images, audio, and video understanding.
Frequently Asked Questions
- What benchmark data does Claude 3 Haiku include?
- LMSpeed shows Claude 3 Haiku benchmark context, API price, output speed, first-token latency, and provider data across 21 providers when those signals are available.
- What is the Claude 3 Haiku API price?
- Claude 3 Haiku has pricing from 21 providers, ranging from $0.034/M to $2.00/M. DuckDuck API has the lowest listed price.
- What does the Claude 3 Haiku API pricing table include?
- The Claude 3 Haiku API pricing table compares 21 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 3 Haiku API pricing?
- DuckDuck API currently has the lowest listed Claude 3 Haiku price at $0.034/M across 21 providers.
- Is Claude 3 Haiku API free?
- Claude 3 Haiku does not currently have a free API tier on LMSpeed. All 21 providers charge per token.