Claude 3.5 Haiku API Benchmarks, Pricing & Provider Data
Compare Claude 3.5 Haiku with another model
Choose a model to open its comparison page.
Claude 3.5 Haiku benchmark, API pricing, and provider data cover 49 API providers, with prices starting at $0.034/M. The page also shows measured API speed and first-token latency.
Anthropic Claude 3.5 Haiku offers quick responses and efficient throughput for high-volume chat, routing, and lightweight automation.
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 3 / 8
- Methodology
- V3.0
#1Math42.5Estimated2/4 Measured dimensions
#2Coding41.3Provisional1/4 Measured dimensions
#3Reasoning39.3Estimated2/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Rankings
Excels at
Detailed scores
Updated: Sep 1, 2026Agents
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Agents
V3.0undefined metric} other undefined metrics}} · No data
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Score41.380% interval27.4–55.21/4 Measured dimensionsLiveCodeBench31.4%#87 / 115SciCode27.4%#169 / 206
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score39.380% interval28.2–50.42/4 Measured dimensionsMMLU-Pro63.4%#116 / 129GPQA40.8%#200 / 213
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Score42.580% interval30.7–54.42/4 Measured dimensionsAIME3.3%#62 / 68MATH-50072.1%#58 / 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
No data80% interval30.8–69.20/4 Measured dimensions
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
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
Pricing Comparison
Compare Claude 3.5 Haiku API pricing across 49 providers. Prices range from $0.034/M to $75.00/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-3-5-haiku-20241022 | default | $0.800/M Cache read$0.080/MCache write$1.00/MCache write 1h$1.60/M | $4.00/M | — | — | — | |
L1 100% | claude-3-5-haiku-20241022 | test | $0.034/M Cache read$0.0034/MCache write$0.043/MCache write 1h$0.068/M | $0.171/M | — | — | — | |
L1 99% | claude-3-5-haiku-latest | default | $0.035/M Cache read$0.0035/MCache write$0.043/MCache write 1h$0.069/M | $0.174/M | — | — | — | |
L1 99% | claude-3-5-haiku-20241022 | claude aws 官=oai兼容 | $0.384/M Cache read$0.038/MCache write$0.479/MCache write 1h$0.767/M | $1.92/M | — | — | — | |
L1 100% | claude-3-5-haiku-20241022 | default | $9.00/M Cache read$0.900/MCache write$11.25/MCache write 1h$18.00/M | $45.00/M | — | — | — | |
L1 100% | claude-3-5-haiku-latest | claude官 | $1.25/M | $6.25/M | — | — | — | |
L1 100% | claude-3-5-haiku-20241022 | claude官 | $5.00/M Cache read$0.500/MCache write$6.25/MCache write 1h$10.00/M | $25.00/M | — | — | — | |
L1 99% | claude-3-5-haiku-latest | claude官 | $0.171/M | $0.856/M | — | — | — | |
L1 99% | claude-3-5-haiku-20241022 | claude官 | $0.685/M Cache read$0.068/MCache write$0.856/MCache write 1h$1.37/M | $3.42/M | — | — | — | |
L1 100% | claude-3-5-haiku-20241022 | Claudecode-求稳分组 | $1.20/M | $6.00/M | — | — | — | |
L1 63% | claude-3-5-haiku-20241022 | Claude-code-NiXiang | $0.800/M Cache read$0.080/MCache write$1.00/MCache write 1h$1.60/M | $4.00/M | — | — | — | |
L1 100% | claude-3-5-haiku-20241022 | default | $0.137/M Cache read$0.014/MCache write$0.171/MCache write 1h$0.274/M | $0.685/M | — | — | — | |
L1 0% | claude-3-5-haiku-latest | claude官 | $0.257/M | $1.28/M | — | — | — | |
L1 0% | claude-3-5-haiku-20241022 | claude官 | $1.03/M Cache read$0.103/MCache write$1.28/MCache write 1h$2.05/M | $5.14/M | — | — | — | |
L1 0% | claude-3-5-haiku | default | $0.800/M | $4.00/M | — | — | — | |
L1 0% | anthropic/claude-3.5-haiku | default | $0.800/M | $4.00/M | — | — | — | |
L1 0% | anthropic/claude-3.5-haiku-20241022 | default | $0.800/M | $4.00/M | — | — | — | |
L1 0% | claude-3-5-haiku-20241022 | default | $1.00/M | $5.00/M | — | — | — | |
L1 0% | claude-3.5-haiku | default | $75.00/M | $375.00/M | — | — | — | |
L1 0% | claude-3-5-haiku-latest | default | $75.00/M | $375.00/M | — | — | — |
Alternatives & Similar Models
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 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.
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.
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.
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.
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.
Frequently Asked Questions
- What benchmark data does Claude 3.5 Haiku include?
- LMSpeed shows Claude 3.5 Haiku benchmark context, API price, output speed, first-token latency, and provider data across 49 providers when those signals are available.
- What is the Claude 3.5 Haiku API price?
- Claude 3.5 Haiku has pricing from 49 providers, ranging from $0.034/M to $75.00/M. DuckDuck API has the lowest listed price.
- What does the Claude 3.5 Haiku API pricing table include?
- The Claude 3.5 Haiku API pricing table compares 49 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 3.5 Haiku API pricing?
- DuckDuck API currently has the lowest listed Claude 3.5 Haiku price at $0.034/M across 49 providers.
- Can I compare Claude 3.5 Haiku API price and speed together?
- Yes. LMSpeed shows Claude 3.5 Haiku API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is Claude 3.5 Haiku API free?
- Claude 3.5 Haiku does not currently have a free API tier on LMSpeed. All 49 providers charge per token.