Anthropic
Claude 3.5 Haiku
Released Oct 22, 2024 · 44B tokens this week · 3 providers
Overview
A small, cheap Claude from 2024 for quick classification and short-form generation. Fast enough for inline UI features and cheap enough for overnight bulk jobs. Text-only, with solid instruction-following for its size.
Providers
Reference data — not yet measured from live traffic
| PROVIDER | MAX OUT | OUTPUT /M | QUANT | |||||
|---|---|---|---|---|---|---|---|---|
AnthropicCheapest | 200K | 8K | $0.80 | $4.00 | 239ms | 145 | 99.90% | Full |
Amazon Bedrock | 200K | 8K | $0.85 | $4.24 | 520ms | 120 | 99.65% | Full |
Google Vertex AI | 200K | 8K | $0.85 | $4.24 | 500ms | 124 | 99.60% | Full |
Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.
Price comparison
Blended $ per 1M tokens
Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.
Call it
OpenAI-compatible — swap the base URL and go
curl https://model.cards/api/v1/chat/completions \
-H "Authorization: Bearer $MODELCARDS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-3.5-haiku",
"messages": [
{ "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
]
}'