Claude 3 Haiku: API Pricing, Context Window & Benchmarks
Claude 3 Haiku is a language model from Anthropic, released in March 2024, with multimodal input.
Claude 3 Haiku is the fastest and most compact model in the Claude 3 family, designed for near-instant responsiveness. It excels at answering simple queries and requests with unmatched speed, making it ideal for seamless AI experiences
Claude 3 Haiku benchmarks
Rankings
Quality Tracker
Claude 3 Haiku Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sun Jul 19 2026Claude 3 Haiku pricing
Providers
Claude 3 Haiku starts at $0.250 per million input tokens and $1.25 per million output tokens via Anthropic. See all 3 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Workload 1M + 100K | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|---|
 Anthropic | $0.250 | $1.25 | $0.375 | 200.0K/200.0K | —/0.50 | 100/— | — | / |
 Bedrock | $0.250 | $1.25 | $0.375 | 200.0K/200.0K | —/0.50 | 104/— | — | / |
 Google | $0.250 | $1.25 | $0.375 | 200.0K/200.0K | —/0.40 | 42/— | — | / |
Workload cost uses 1M input tokens plus 100K output tokens at published list prices without assuming a cache hit. Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
Claude 3 Haiku context window
Input and output token limits for Claude 3 Haiku, plus how it ranks on long-context understanding.
Claude 3 Haiku API
Available from the model provider
Claude 3 Haiku has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationClaude 3 Haiku latency
Claude 3 Haiku time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Claude 3 Haiku examples
Recent arena outputs from Claude 3 Haiku, picked from the highest-ranked matchups.
Claude 3 Haiku license
Claude 3 Haiku is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
Claude 3 Haiku resources
Official sources for Claude 3 Haiku: api documentation, official playground, paper or system card, official launch post.
Claude 3 Haiku vs other models
The most-compared alternatives to Claude 3 Haiku are GPT-4, Command R+, Gemma 2 27B. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Claude 3 Haiku
Models ranked just above and below Claude 3 Haiku by LLM Stats score.
FAQ
Common questions about Claude 3 Haiku.