Claude Haiku 4.5
Anthropic · released Oct 15, 2025
- Type
- Proprietary
- Input
- $1.00
- Output
- $5.00
- Cached
- $0.10
List price · per 1M tokens · Anthropic at 200K context · source ↗
Our take
Written Aug 3, 2026Claude Haiku 4.5 is Anthropic's fast, lightweight entry point that can handle up to 200,000 tokens in a single request and accepts text, images and files. It is the cheapest way into the Claude family for high-volume work, though its speed varies sharply depending on which host you choose.
Pick this for high-volume text, image or file processing where long context matters and budget is tight. Use it for coding assistance, where its measured coding score runs ahead of its general chat rating. Skip it if you need strong web-development coding, reliable maths help, or guaranteed fast throughput without checking your provider.
The case for it
- Largest context window at the cheapest price tier in its family: 200,000 tokens.
- Coding performance outruns its general chat rating by a measured margin.
- Stable web-development coding scores over three days, with near-zero variance.
- Broad multimodal intake — images and files, not just text — at text-model pricing.
The case against it
- Web development coding lags well behind its own general coding score.
- Maths and creative writing are relative soft spots, both below its overall rating.
- Throughput varies more than threefold depending on provider and tier, with no price difference to match.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)68th of 143 · 1412.2
CodingWriting and fixing code on its own
Arena Coding52nd of 143 · 1479
AgenticPlanning, calling tools, staying on task
Claude Haiku 4.5 is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 14th of 39 with 66.6.
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 Haiku 4.5 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 model8 scoresEvery figure we hold, from 8 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
- $1.00 in / $5.00 out
- Context served
- 200K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $1.00 / $5.00 | 200K | not measured | Unknown | Unknown | Unknown |
| DeepInfra | $1.00 / $5.00 | 200K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIus-east-2 | $1.00 / $5.00 | 200K | 70 tok/s | No | No | Unknown |
| Microsoft Azure AIglobal | $1.00 / $5.00 | 200K | 31 tok/s | No | No | Unknown |
| Google Vertex AIglobal | $1.00 / $5.00 | 200K | 80 tok/s | No | No | Confirmed |
| Anthropic | $1.00 / $5.00 | 200K64K out | 68 tok/s | No | Yes30 days | Unknown |
| Amazon Bedrockglobal | $1.00 / $5.00 | 200K | 43 tok/s | No | No | Confirmed |
| Google Vertex AIeurope | $1.10 / $5.50 | 200K | 88 tok/s | No | No | Confirmed |
| Amazon Bedrockeu-west-1 | $1.10 / $5.50 | 200K | 24 tok/s | No | No | Confirmed |
DeepInfra
Microsoft Azure AI
Google Vertex AI
Amazon BedrockAcross the 9 listings we hold: 7 say they do not train on prompts, 0 say they do and 2 do not say. 4 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 | ✓ | ✓ | ✓ |
| DeepInfra | |||
| Microsoft Azure AIus-east-2 | ✓ | ✓ | ✓ |
| Microsoft Azure AIglobal | ✓ | ✓ | ✓ |
| Google Vertex AIglobal | ✓ | ✗ | ✗ |
| Anthropic | ✓ | ✓ | ✓ |
| Amazon Bedrockglobal | ✓ | ✓ | ✓ |
| Google Vertex AIeurope | ✓ | ✗ | ✗ |
| Amazon Bedrockeu-west-1 | ✓ | ✓ | ✓ |
Tool calling: 8 of 9 listings say yes, 1 publishes no parameter list. JSON output: 6 of 9 listings say yes, 2 say no, 1 publishes no parameter list. Strict schema: 6 of 9 listings say yes, 2 say no, 1 publishes no parameter list.
Models people weigh against Claude Haiku 4.5
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 9 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 9 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+file->text
- Catalogue slug
- anthropic-claude-haiku-4-5