Inteligencia de modelos de IA

Claude Haiku 3.5

anthropic/claude-3-5-haiku

Por Anthropic · familia: claude-haiku · lanzado 2024-10-22 · fecha de conocimiento: 2024-07-31

$0.800
Entrada / 1M tokens
$4.00
Salida / 1M tokens
200K
Ventana de contexto
8K
Salida máxima

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Capacidades

Llamada a herramientasRazonamiento? Salida estructuradaAdjuntosPesos abiertosControl de temperatura
Modalidades: entrada text, image, pdf · salida text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding56
  • Tool calling40/40
  • Structured output0/20
  • Reasoning0/10
  • Context window (100K → 1M)6/20
  • Provider availability10/10
Agents50
  • Tool calling35/35
  • Structured output0/25
  • Reasoning0/15
  • Output token limit5/15
  • Provider availability10/10
JSON / structured output40
  • Structured output / JSON mode0/50
  • Tool calling20/20
  • Temperature control10/10
  • Price-friendly for high-volume10/20
Cost efficiency50
  • Headline price (log-scaled)45/95
  • Has prompt-cache pricing5/5
Long context55
  • Context window (100K → 2M)45/90
  • Has published price for full window10/10
Vision90
  • Accepts image input50/50
  • Context window (10K → 1M)20/30
  • Has published price10/10
  • Provider availability10/10
Production-readiness96
  • Number of independent providers40/40
  • Has published per-token price20/20
  • Context window ≥ 8K15/15
  • No data inconsistencies across providers6/10
  • Official model (not derivative)15/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$6.00
< $0.01 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$12.00
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$3.60
< $0.01 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$10.40
$0.01 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$12.00
$0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

Detalle de precios

Precio recomendado de openrouter · anthropic/claude-3.5-haiku

$0.800
Entrada
$4.00
Salida
$0.080
Lectura de caché
$1.00
Escritura de caché

Disponible en 11 proveedores

ProveedorID de modelo del proveedorEntrada / 1MSalida / 1MContextoLanzado
OpenRouter
openrouter
anthropic/claude-3.5-haiku$0.800$4.00200K2024-10-22
Vercel AI Gateway
vercel
anthropic/claude-3.5-haiku$0.800$4.00200K2024-10-22
ZenMux
zenmux
anthropic/claude-3.5-haiku$0.800$4.00200K2024-11-04
Qiniu
qiniu-ai
claude-3.5-haikuUnknownUnknown200K2025-08-26
Kilo Gateway
kilo
anthropic/claude-3.5-haiku$0.800$4.00200K2024-10-22
Cloudflare AI Gateway
cloudflare-ai-gateway
anthropic/claude-3-5-haiku$0.800$4.00200K2024-10-22
Cloudflare AI Gateway
cloudflare-ai-gateway
anthropic/claude-3.5-haiku$0.800$4.00200K2024-10-22
OpenCode Zen
opencode
claude-3-5-haiku$0.800$4.00200K2024-10-22
Helicone
helicone
claude-3.5-haiku$0.800$4.00200K2024-10-22
DigitalOcean
digitalocean
anthropic-claude-3.5-haiku$0.800$4.00200K2024-11-05
LLM Gateway
llmgateway
claude-3-5-haiku$0.800$4.00200K2024-10-22

Inconsistencias de datos entre proveedores

  • release_date varies (span 308d): 2024-10-22, 2024-11-04, 2024-11-05, 2025-08-26
  • modalities varies across offerings

Los proveedores reportan valores distintos para este modelo. Los datos clave de arriba usan un proveedor representativo; consulta la tabla para detalles por proveedor.

Frequently asked questions

How much does Claude Haiku 3.5 cost?

Claude Haiku 3.5 costs $0.800 per 1M input tokens and $4.00 per 1M output tokens, sourced from openrouter. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

What is the context window of Claude Haiku 3.5?

Claude Haiku 3.5 has a context window of 200K tokens, with a max output of 8K tokens per reply. This is the total combined size of prompt + completion.

Does Claude Haiku 3.5 support tool calling?

Yes. Claude Haiku 3.5 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.

Does Claude Haiku 3.5 support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for Claude Haiku 3.5 in our data source. Verify with Anthropic's official documentation before relying on it in production.

Can Claude Haiku 3.5 accept image input?

Yes. Claude Haiku 3.5 accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check Anthropic's docs for the exact rule.

Is Claude Haiku 3.5 open-weight?

No. Claude Haiku 3.5 is a proprietary model — only Anthropic (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.

What are the best alternatives to Claude Haiku 3.5?

If Claude Haiku 3.5 doesn't fit, consider Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 4.5 (latest). Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

More Anthropic models

Última actualización:

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.