Claude 3.5 Haiku
Proprietary CommercialDeveloped by Anthropic · High-Speed Compact Transformer · Modalities: Text, Vision · Released 2024-11-04
What are the token costs and operational benchmarks for Claude 3.5 Haiku?
Verified Capability Benchmarks
Composite Intelligence: 54.2/100Architectural & Production Profile
Fast, compact Anthropic model delivering sub-200ms responses with 90% prompt caching discounts for interactive applications.
Rapid customer-facing chat, sub-agent routing, and real-time code autocomplete.
- Architecture
- High-Speed Compact Transformer
- Modalities
- Text, Vision
- Max Output Tokens
- 8,192 tokens
- Blended Rate (3:1)
- $1.600 / 1M
Verified Cloud Inference Endpoints Hosting Claude 3.5 Haiku
Compare latency, streaming speed, and token pricing across cloud API providers.
| Inference Provider | Role | Input / 1M | Output / 1M | Avg TTFT | Throughput |
|---|---|---|---|---|---|
| Anthropic Claude API → | Primary Host | $0.80 | $4.00 | 190ms | 130 tok/s |
Interactive Monthly Token Economics & ROI Forecaster
Model production workloads across prompt, completion, and cached context tokens, or switch models on the fly.
Estimated Monthly Spend
$0.80/1M in · $4.00/1M out
Prompt Cache: $0.080/1M read · $1.00/1M write
$2.00/1M in · $10.00/1M out
Prompt Cache: $0.100/1M read · $0.50/1M write
Head-to-Head Comparisons Involving Claude 3.5 Haiku (36)
Claude 3.5 Haiku vs Claude 3.7 Sonnet
Claude 3.5 Haiku is 73.3% cheaper for input tokens ($0.80 vs. $3.00 per 1M tokens) and $4.00 vs. $15.00 for output tokens (3.8x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (350ms faster than Claude 3.7 Sonnet) with 130 vs. 72 tok/s throughput. Claude 3.7 Sonnet leads coding evaluations at 70.3% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 78.5% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Gemini 4 Argon
Claude 3.5 Haiku is 60.0% cheaper for input tokens ($0.80 vs. $2.00 per 1M tokens) and $4.00 vs. $10.00 for output tokens (2.5x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (660ms faster than Gemini 4 Argon) with 130 vs. 115 tok/s throughput. Gemini 4 Argon leads coding evaluations at 84.5% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 93.8% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Claude 4.5 Sonnet
Claude 3.5 Haiku cuts input token costs by 73.3% compared to Claude 4.5 Sonnet ($0.80 vs. $3.00 per 1M input tokens; $4.00 vs. $15.00/1M output). For autonomous software engineering, Claude 4.5 Sonnet leads on SWE-bench Verified (75.8% vs. 40.6%), while Claude 4.5 Sonnet edges ahead on GPQA Diamond scientific reasoning (84.2%). In real-time API production, Claude 3.5 Haiku achieves a faster 190ms TTFT latency (130.0 tokens/sec).
Claude 3.5 Haiku vs Claude Opus 5.5
Claude 3.5 Haiku is 80.0% cheaper for input tokens ($0.80 vs. $4.00 per 1M tokens) and $4.00 vs. $20.00 for output tokens (5.0x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (490ms faster than Claude Opus 5.5) with 130 vs. 95 tok/s throughput. Claude Opus 5.5 leads coding evaluations at 89.9% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 93.2% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Gemini 3.8 Flash
Gemini 3.8 Flash is 68.8% cheaper for input tokens ($0.25 vs. $0.80 per 1M tokens) and $1.50 vs. $4.00 for output tokens (3.2x cost advantage). In terms of operational performance, Gemini 3.8 Flash delivers lower response latency at 105ms TTFT (85ms faster than Claude 3.5 Haiku) with 210 vs. 130 tok/s throughput. Gemini 3.8 Flash leads coding evaluations at 68.5% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 79.2% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs GPT-5
Claude 3.5 Haiku is 68.0% cheaper for input tokens ($0.80 vs. $2.50 per 1M tokens) and $4.00 vs. $10.00 for output tokens (3.1x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (150ms faster than GPT-5) with 130 vs. 105 tok/s throughput. GPT-5 leads coding evaluations at 74.9% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 85.4% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs GPT-6 Astra
Claude 3.5 Haiku is 92.0% cheaper for input tokens ($0.80 vs. $10.00 per 1M tokens) and $4.00 vs. $50.00 for output tokens (12.5x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (550ms faster than GPT-6 Astra) with 130 vs. 74 tok/s throughput. GPT-6 Astra leads coding evaluations at 75.7% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 96.0% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs DeepSeek V4 Pro
Claude 3.5 Haiku is 39.4% cheaper for input tokens ($0.80 vs. $1.32 per 1M tokens) and $4.00 vs. $3.96 for output tokens (1.6x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (330ms faster than DeepSeek V4 Pro) with 130 vs. 78 tok/s throughput. DeepSeek V4 Pro leads coding evaluations at 80.6% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 90.1% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs DeepSeek R1
DeepSeek R1 is 31.2% cheaper for input tokens ($0.55 vs. $0.80 per 1M tokens) and $2.19 vs. $4.00 for output tokens (1.5x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (1260ms faster than DeepSeek R1) with 130 vs. 58 tok/s throughput. DeepSeek R1 leads coding evaluations at 49.2% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 71.5% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs DeepSeek V4 Flash Vision (Exp)
DeepSeek V4 Flash Vision (Exp) is 72.5% cheaper for input tokens ($0.22 vs. $0.80 per 1M tokens) and $0.65 vs. $4.00 for output tokens (3.6x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (120ms faster than DeepSeek V4 Flash Vision (Exp)) with 130 vs. 165 tok/s throughput. DeepSeek V4 Flash Vision (Exp) leads coding evaluations at 77.4% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 91.3% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs OpenAI o3
Claude 3.5 Haiku is 60.0% cheaper for input tokens ($0.80 vs. $2.00 per 1M tokens) and $4.00 vs. $8.00 for output tokens (2.5x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (960ms faster than OpenAI o3) with 130 vs. 82 tok/s throughput. OpenAI o3 leads coding evaluations at 71.7% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 87.7% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Claude 4 Opus
Claude 3.5 Haiku is 94.7% cheaper for input tokens ($0.80 vs. $15.00 per 1M tokens) and $4.00 vs. $75.00 for output tokens (18.8x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (730ms faster than Claude 4 Opus) with 130 vs. 46 tok/s throughput. Claude 4 Opus leads coding evaluations at 77.2% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 87.1% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Gemini 3.1 Pro
Claude 3.5 Haiku is 36.0% cheaper for input tokens ($0.80 vs. $1.25 per 1M tokens) and $4.00 vs. $10.00 for output tokens (1.6x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (230ms faster than Gemini 3.1 Pro) with 130 vs. 98 tok/s throughput. Gemini 3.1 Pro leads coding evaluations at 71.8% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 82.4% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Grok 4
Claude 3.5 Haiku is 68.0% cheaper for input tokens ($0.80 vs. $2.50 per 1M tokens) and $4.00 vs. $12.50 for output tokens (3.1x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (290ms faster than Grok 4) with 130 vs. 95 tok/s throughput. Grok 4 leads coding evaluations at 73.2% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 86.2% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Llama 4 Maverick
Llama 4 Maverick is 75.0% cheaper for input tokens ($0.20 vs. $0.80 per 1M tokens) and $0.60 vs. $4.00 for output tokens (4.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (55ms faster than Claude 3.5 Haiku) with 175 vs. 130 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 73.8% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Qwen 3.8 Flash Next
Qwen 3.8 Flash Next is 80.0% cheaper for input tokens ($0.16 vs. $0.80 per 1M tokens) and $0.47 vs. $4.00 for output tokens (5.0x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (90ms faster than Qwen 3.8 Flash Next) with 130 vs. 185 tok/s throughput. Qwen 3.8 Flash Next leads coding evaluations at 81.0% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 91.7% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite is 90.6% cheaper for input tokens ($0.07 vs. $0.80 per 1M tokens) and $0.30 vs. $4.00 for output tokens (10.7x cost advantage). In terms of operational performance, Gemini 3.5 Flash-Lite delivers lower response latency at 78ms TTFT (112ms faster than Claude 3.5 Haiku) with 265 vs. 130 tok/s throughput. Gemini 3.5 Flash-Lite leads coding evaluations at 55.4% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 68.4% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs OpenAI o4-mini
Claude 3.5 Haiku is 27.3% cheaper for input tokens ($0.80 vs. $1.10 per 1M tokens) and $4.00 vs. $4.40 for output tokens (1.4x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (490ms faster than OpenAI o4-mini) with 130 vs. 125 tok/s throughput. OpenAI o4-mini leads coding evaluations at 68.1% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 81.4% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs DeepSeek V3
DeepSeek V3 is 82.5% cheaper for input tokens ($0.14 vs. $0.80 per 1M tokens) and $0.28 vs. $4.00 for output tokens (5.7x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (220ms faster than DeepSeek V3) with 130 vs. 78 tok/s throughput. DeepSeek V3 leads coding evaluations at 42.0% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 59.1% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Gemma 4 31B IT
Gemma 4 31B IT is 85.0% cheaper for input tokens ($0.12 vs. $0.80 per 1M tokens) and $0.36 vs. $4.00 for output tokens (6.7x cost advantage). In terms of operational performance, Gemma 4 31B IT delivers lower response latency at 115ms TTFT (75ms faster than Claude 3.5 Haiku) with 155 vs. 130 tok/s throughput. Gemma 4 31B IT leads coding evaluations at 59.2% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 71.2% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs OpenAI o3-mini
Claude 3.5 Haiku is 27.3% cheaper for input tokens ($0.80 vs. $1.10 per 1M tokens) and $4.00 vs. $4.40 for output tokens (1.4x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (760ms faster than OpenAI o3-mini) with 130 vs. 98 tok/s throughput. OpenAI o3-mini leads coding evaluations at 49.3% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 79.7% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Claude 3.5 Sonnet
Claude 3.5 Haiku is 73.3% cheaper for input tokens ($0.80 vs. $3.00 per 1M tokens) and $4.00 vs. $15.00 for output tokens (3.8x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (120ms faster than Claude 3.5 Sonnet) with 130 vs. 80 tok/s throughput. Claude 3.5 Sonnet leads coding evaluations at 49.0% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 59.4% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Gemini 2.0 Flash
Gemini 2.0 Flash is 87.5% cheaper for input tokens ($0.10 vs. $0.80 per 1M tokens) and $0.40 vs. $4.00 for output tokens (8.0x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (90ms faster than Gemini 2.0 Flash) with 130 vs. 185 tok/s throughput. Gemini 2.0 Flash leads coding evaluations at 51.8% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 63.6% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Gemini 2.5 Flash
Gemini 2.5 Flash is 62.5% cheaper for input tokens ($0.30 vs. $0.80 per 1M tokens) and $2.50 vs. $4.00 for output tokens (2.7x cost advantage). In terms of operational performance, Gemini 2.5 Flash delivers lower response latency at 110ms TTFT (80ms faster than Claude 3.5 Haiku) with 180 vs. 130 tok/s throughput. Gemini 2.5 Flash leads coding evaluations at 58.0% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 70.5% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Gemini 2.5 Pro
Claude 3.5 Haiku is 36.0% cheaper for input tokens ($0.80 vs. $1.25 per 1M tokens) and $4.00 vs. $10.00 for output tokens (1.6x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (510ms faster than Gemini 2.5 Pro) with 130 vs. 80 tok/s throughput. Gemini 2.5 Pro leads coding evaluations at 63.8% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 74.0% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs GLM-5.3
GLM-5.3 is 56.2% cheaper for input tokens ($0.35 vs. $0.80 per 1M tokens) and $1.00 vs. $4.00 for output tokens (2.3x cost advantage). In terms of operational performance, GLM-5.3 delivers lower response latency at 160ms TTFT (30ms faster than Claude 3.5 Haiku) with 120 vs. 130 tok/s throughput. GLM-5.3 leads coding evaluations at 56.0% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 67.0% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs GLM-5.3-Flash
GLM-5.3-Flash is 85.0% cheaper for input tokens ($0.12 vs. $0.80 per 1M tokens) and $0.40 vs. $4.00 for output tokens (6.7x cost advantage). In terms of operational performance, GLM-5.3-Flash delivers lower response latency at 90ms TTFT (100ms faster than Claude 3.5 Haiku) with 175 vs. 130 tok/s throughput. GLM-5.3-Flash leads coding evaluations at 52.8% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 63.5% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs GPT-4o
Claude 3.5 Haiku is 68.0% cheaper for input tokens ($0.80 vs. $2.50 per 1M tokens) and $4.00 vs. $10.00 for output tokens (3.1x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (90ms faster than GPT-4o) with 130 vs. 100 tok/s throughput. GPT-4o leads coding evaluations at 48.0% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 53.6% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs GPT-4o Mini
GPT-4o Mini is 81.2% cheaper for input tokens ($0.15 vs. $0.80 per 1M tokens) and $0.60 vs. $4.00 for output tokens (5.3x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (30ms faster than GPT-4o Mini) with 130 vs. 140 tok/s throughput. GPT-4o Mini leads coding evaluations at 41.0% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 40.2% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs GPT-6.1 Sol
Claude 3.5 Haiku is 60.0% cheaper for input tokens ($0.80 vs. $2.00 per 1M tokens) and $4.00 vs. $10.00 for output tokens (2.5x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (330ms faster than GPT-6.1 Sol) with 130 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 92.4% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Grok 3
Claude 3.5 Haiku is 73.3% cheaper for input tokens ($0.80 vs. $3.00 per 1M tokens) and $4.00 vs. $15.00 for output tokens (3.8x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (430ms faster than Grok 3) with 130 vs. 88 tok/s throughput. Grok 3 leads coding evaluations at 65.8% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 84.6% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Grok 3 Mini
Grok 3 Mini is 62.5% cheaper for input tokens ($0.30 vs. $0.80 per 1M tokens) and $1.20 vs. $4.00 for output tokens (2.7x cost advantage). In terms of operational performance, Grok 3 Mini delivers lower response latency at 150ms TTFT (40ms faster than Claude 3.5 Haiku) with 160 vs. 130 tok/s throughput. Grok 3 Mini leads coding evaluations at 54.0% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 68.0% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Llama 3.3 70B Instruct
Llama 3.3 70B Instruct is 85.0% cheaper for input tokens ($0.12 vs. $0.80 per 1M tokens) and $0.30 vs. $4.00 for output tokens (6.7x cost advantage). In terms of operational performance, Llama 3.3 70B Instruct delivers lower response latency at 145ms TTFT (45ms faster than Claude 3.5 Haiku) with 165 vs. 130 tok/s throughput. Llama 3.3 70B Instruct leads coding evaluations at 42.5% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 55.6% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Mistral Large 2 (2411)
Claude 3.5 Haiku is 60.0% cheaper for input tokens ($0.80 vs. $2.00 per 1M tokens) and $4.00 vs. $6.00 for output tokens (2.5x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (190ms faster than Mistral Large 2 (2411)) with 130 vs. 75 tok/s throughput. Mistral Large 2 (2411) leads coding evaluations at 45.2% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 54.2% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs o1
Claude 3.5 Haiku is 94.7% cheaper for input tokens ($0.80 vs. $15.00 per 1M tokens) and $4.00 vs. $60.00 for output tokens (18.8x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (2410ms faster than o1) with 130 vs. 48 tok/s throughput. o1 leads coding evaluations at 48.9% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 78.0% vs. 41.6% on GPQA Diamond.
Claude 3.5 Haiku vs Qwen 3.8 27B
Qwen 3.8 27B is 75.0% cheaper for input tokens ($0.20 vs. $0.80 per 1M tokens) and $0.60 vs. $4.00 for output tokens (4.0x cost advantage). In terms of operational performance, Qwen 3.8 27B delivers lower response latency at 120ms TTFT (70ms faster than Claude 3.5 Haiku) with 140 vs. 130 tok/s throughput. Qwen 3.8 27B leads coding evaluations at 58.4% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 68.0% vs. 41.6% on GPQA Diamond.
Frequently Asked Questions & Query Fan-Out
How much does Claude 3.5 Haiku cost per 1M tokens including prompt caching?
Claude 3.5 Haiku costs $0.80 per million input tokens and $4.00 per million output tokens. Cached input reads cost $0.080 per 1M tokens, reducing repeated context costs by 90%.
What are Claude 3.5 Haiku's coding and reasoning benchmark scores?
Claude 3.5 Haiku achieves 40.6% on SWE-bench Verified, 88.5% on HumanEval coding, 41.6% on GPQA Diamond graduate-level science, 71% on MMLU-Pro, and 69.4% on MATH-500, earning an overall Inference Value Ratio (IVR) of 52.4/100.
What is the context window, TTFT latency, and token throughput of Claude 3.5 Haiku?
Claude 3.5 Haiku supports a 204,800 token context window (8,192 max output tokens) and operates at 190ms average Time to First Token (TTFT) with 130 tokens/sec output streaming throughput.
What are the primary production use cases for Claude 3.5 Haiku?
Rapid customer-facing chat, sub-agent routing, and real-time code autocomplete.