Intelligence des modèles d'IA

Claude-Haiku-3.5

poe/claude-haiku-3-5

Par poe · famille: claude-haiku · sorti 2024-10-01

⚠ Il s'agit d'un fine-tune communautaire ou dérivé — pas d'une publication officielle de l'éditeur.

$0.680
Entrée / 1M jetons
$3.40
Sortie / 1M jetons
189K
Fenêtre de contexte
8K
Sortie max

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

Capacités

Tool callingRaisonnement? Sortie structuréePièces jointesPoids ouvertsContrôle de température
Modalités: entrée text, image, pdf · sortie 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.

Coding47
  • Tool calling40/40
  • Structured output0/20
  • Reasoning0/10
  • Context window (100K → 1M)6/20
  • Provider availability1/10
Agents41
  • Tool calling35/35
  • Structured output0/25
  • Reasoning0/15
  • Output token limit5/15
  • Provider availability1/10
JSON / structured output32
  • Structured output / JSON mode0/50
  • Tool calling20/20
  • Temperature control0/10
  • Price-friendly for high-volume12/20
Cost efficiency52
  • Headline price (log-scaled)47/95
  • Has prompt-cache pricing5/5
Long context54
  • Context window (100K → 2M)44/90
  • Has published price for full window10/10
Vision80
  • Accepts image input50/50
  • Context window (10K → 1M)19/30
  • Has published price10/10
  • Provider availability1/10
Production-readiness50
  • Number of independent providers5/40
  • Has published per-token price20/20
  • Context window ≥ 8K15/15
  • No data inconsistencies across providers10/10
  • Official model (not derivative)0/15

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
$5.10
< $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
$10.20
< $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
$3.06
< $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
$8.84
< $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
$10.20
$0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

Détail des tarifs

Tarif recommandé de poe · anthropic/claude-haiku-3.5

$0.680
Entrée
$3.40
Sortie
$0.068
Lecture cache
$0.850
Écriture cache

Disponible chez 1 fournisseurs

FournisseurID modèle fournisseurEntrée / 1MSortie / 1MContextePublié le
Poe
poe
anthropic/claude-haiku-3.5$0.680$3.40189K2024-10-01

Frequently asked questions

How much does Claude-Haiku-3.5 cost?

Claude-Haiku-3.5 costs $0.680 per 1M input tokens and $3.40 per 1M output tokens, sourced from poe. 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 189K 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 poe'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 poe's docs for the exact rule.

Is Claude-Haiku-3.5 open-weight?

No. Claude-Haiku-3.5 is a proprietary model — only poe (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 Tako. 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.

Dernière mise à jour :

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.