Claude 3 Haiku
Anthropic · released Mar 13, 2024
- Type
- Closed
- Input
- $0.25
- Output
- $1.25
- Cached
- None held
List price · per 1M tokens · Anthropic at 200K context · machine-readable source ↗
Our take
Written Sep 30, 2026Claude 3 Haiku is a hosted-only model: we list no download for it, so using it means choosing a host. It is cheap and easy to reach, but every board we hold places it near the bottom of its field, so treat it as a workhorse for low-stakes jobs rather than a strong model.
Reach for it on high-volume, low-stakes work where the bill matters more than answer quality — classification, extraction, short summaries — or when a long document needs to go in whole rather than chunked first. It takes text and images and returns text, and all three hosts list the same rate, so the choice between them is not a price decision. Skip it if the work needs measured coding, maths or instruction-following strength, or if you need a model you can run yourself.
The case for it
- Cheap to reach at scale: all three hosts list the same rate, so a high-volume pipeline is affordable to run.
- A long report or a stack of documents fits beside the question without splitting it up first, though reliable recall across all of it is unverified in our data.
- Text and images go into the same request, so a screenshot does not have to be described in words first.
The case against it
- Near the bottom of every board we hold: 157th of 168 on Arena Text as of 25 Sep 2026 and 16th of 16 on LiveCodeBench as of 28 Sep 2026, at 22.5% pass.
- The Arena placings record which answer people preferred, not whether it was correct, so they say nothing about factual accuracy or task completion.
- Released 2024-03-13, and no parameter count is published, so there is little here to judge it on beyond the boards.
How good is it?
A small closed text model for chat and light drafting, though it trails most models on everyday questions, prose and code.
- getting answers to everyday questionsArena Text (overall) · 157th of 168
- drafts, rewrites and editingArena Creative Writing · 157th of 168
- writing and completing codeArena Coding · 158th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)157th of 168 · 1262
CodingWriting and fixing code on its own
Arena Coding158th of 168 · 1301
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing157th of 168 · 1216
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model7 scoresEvery figure we hold, from 7 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked between 6 days and 9 days ago — each listing carries its own date.
Anthropic, direct
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Anthropic on 200K of context.
- per 1M tokens
- $0.25 in / $1.25 out
- Context served
- 200K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.25 / $1.25checked 6 days ago | 200K | not measured | Unknown | Unknown | Unknown |
| AnthropicDirect | $0.25 / $1.25checked 9 days ago | 200K4K max reply | not measured | Unknown | Unknown | Unknown |
| Amazon BedrockThrough OpenRouter | $0.25 / $1.25checked 6 days ago | 200K4K max reply | 30 tok/s | No | No | Unknown |
OpenRouter
Amazon BedrockAcross the 3 listings we hold: 1 says it does not train on prompts, 0 say they do and 2 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✗ | ✗ |
| AnthropicDirect | |||
| Amazon BedrockThrough OpenRouter | ✓ | ✗ | ✗ |
Tool calling: 2 of 3 listings say yes, 1 publishes no parameter list. JSON output: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. Strict schema: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list.
Models people weigh against Claude 3 Haiku
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- 1 of 3 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 3 listings do not say whether they train on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- anthropic-claude-3-haiku