Claude 3 Haiku
Anthropic · released Mar 13, 2024
- Type
- Proprietary
- Input
- $0.25
- Output
- $1.25
- Cached
- Not published
List price · per 1M tokens · Anthropic at 200K context · source ↗
Our take
Written Aug 3, 2026Claude 3 Haiku is Anthropic's fastest, most affordable text-and-image model, built for high-volume work with a 200,000-token request limit. Its benchmark scores sit in the lower tier of the independent chat leaderboard we track, so it trades peak quality for speed and cost.
Pick this for high-volume text and image tasks where cost matters more than top-tier quality, or for long-document processing that needs a 200,000-token request limit. Use it on Amazon Bedrock if you need a disclosed throughput figure of 65 tokens per second. Skip it if you need strong measured coding ability, top-half chat scores, or consistent speed data across every host.
The case for it
- Largest request limit in Anthropic's fast and affordable tier, at 200,000 tokens.
- Price parity across every host we track, with no premium for any provider.
- Slight upward trend in creative writing and coding scores between late July and early August 2026.
The case against it
- Arena scores cluster at the bottom of the measured range, with overall chat, maths and creative writing all below its own coding score.
- LiveCodeBench coding score of 22.5 is weak.
- No speed data for two of three hosts; only Amazon Bedrock discloses throughput.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)133rd of 143 · 1261.1
CodingWriting and fixing code on its own
Arena Coding134th of 143 · 1300.7
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Claude 3 Haiku for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Claude 3 Haiku placed and give it no mark out of five.
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, which is why they get no rating.
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.
Or rent it from someone else
Why this differs from the header. The strip above quotes Anthropic's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.25 / $1.25 | 200K | not measured | Unknown | Unknown | Unknown |
| Anthropic | $0.25 / $1.25 | 200K4K out | not measured | Unknown | Unknown | Unknown |
| Amazon Bedrock | $0.25 / $1.25 | 200K | 65 tok/s | No | No | Confirmed |
Amazon BedrockAcross the 3 listings we hold: 1 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| Anthropic | |||
| Amazon Bedrock | ✓ | ✗ | ✗ |
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
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 1 of 3 listings publish no parameter list, so what their 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.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image->text
- Catalogue slug
- anthropic-claude-3-haiku