Claude Haiku 4.5
Anthropic · released Oct 15, 2025
- Type
- Closed
- Input
- $1.00
- Output
- $5.00
- Cached
- $0.10
List price · per 1M tokens · Anthropic at 200K context · machine-readable source ↗
Our take
Written Sep 6, 2026Claude Haiku 4.5 is Anthropic's lightweight text-and-image model that can handle up to 200,000 tokens in a single request. It is priced at the entry level yet matches the context limits of much larger frontier models, with its strongest measured skill in coding assistance.
Pick this for long-document processing where budget matters, or for coding assistance where its measured coding score is the peak skill. Use it if you want identical base pricing across six platforms for predictable multi-provider deployment. Skip it if you need web development coding, creative writing, or maths, where it scores below its own overall level.
The case for it
- Largest context window in the budget tier at 200,000 tokens.
- Strongest at coding among its measured skills, with a 67.4-point gap above its own overall text score.
- Real software engineering capability: 66.6% end-to-end issue resolution on SWE-bench Verified.
- Consistent cross-platform base pricing on six of eleven offers, with no provider undercutting or overcharging at the standard tier.
The case against it
- Web development coding lags general coding skill by 151.7 points on the measured leaderboard.
- Creative writing and maths are relative soft spots, both below its own overall text score.
- Throughput varies 2.3× depending on provider and price tier, from 45 to 104 tokens per second.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)86th of 168 · 1414
CodingWriting and fixing code on its own
Arena Coding67th of 168 · 1482
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 14th of 42 with 66.6.
WritingDrafting and rewriting prose
Arena Creative Writing82nd of 168 · 1387
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 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.
Where to rent it
Prices checked between 57 min and 60 min 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
- $1.00 in / $5.00 out
- Context served
- 200K
- Throughput
- ~54 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Amazon BedrockglobalThrough OpenRouter | $1.00 / $5.00checked 60 min ago | 200K64K max reply | 57 tok/s | No | No | Confirmed |
| DeepInfraDirect | $1.00 / $5.00checked 59 min ago | 200K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIglobalThrough OpenRouter | $1.00 / $5.00checked 60 min ago | 200K64K max reply | 70 tok/s | No | No | Unknown |
| Google Vertex AIglobalThrough OpenRouter | $1.00 / $5.00checked 60 min ago | 200K64K max reply | 78 tok/s | No | No | Confirmed |
| AnthropicDirect | $1.00 / $5.00checked 57 min ago | 200K64K max reply | 54 tok/s | No | Yes30 days | Unknown |
| OpenRouterOpenRouter's own listing | $1.00 / $5.00checked 60 min ago | 200K | not measured | Unknown | Unknown | Unknown |
| Amazon BedrockusThrough OpenRouter | $1.10 / $5.50checked 60 min ago | 200K64K max reply | 85 tok/s | No | No | Confirmed |
| Google Vertex AIus-east5Through OpenRouter | $1.10 / $5.50checked 60 min ago | 200K64K max reply | 192 tok/s | No | No | Confirmed |
| Google Vertex AIeuropeThrough OpenRouter | $1.10 / $5.50checked 60 min ago | 200K64K max reply | 56 tok/s | No | No | Confirmed |
| Amazon Bedrockeu-west-1Through OpenRouter | $1.10 / $5.50checked 60 min ago | 200K64K max reply | 98 tok/s | No | No | Confirmed |
Amazon Bedrock
DeepInfra
Microsoft Azure AI
Google Vertex AI
OpenRouterAcross the 10 listings we hold: 8 say they do not train on prompts, 0 say they do and 2 do not say. 6 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 |
|---|---|---|---|
| Amazon BedrockglobalThrough OpenRouter | ✓ | ✓ | ✓ |
| DeepInfraDirect | |||
| Microsoft Azure AIglobalThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobalThrough OpenRouter | ✓ | ✗ | ✓ |
| AnthropicDirect | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Amazon BedrockusThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIus-east5Through OpenRouter | ✓ | ✗ | ✓ |
| Google Vertex AIeuropeThrough OpenRouter | ✓ | ✗ | ✓ |
| Amazon Bedrockeu-west-1Through OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 9 of 10 listings say yes, 1 publishes no parameter list. JSON output: 6 of 10 listings say yes, 3 say no, 1 publishes no parameter list. Strict schema: 9 of 10 listings say yes, 1 publishes no parameter list.
Models people weigh against Claude Haiku 4.5
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 10 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 10 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, images and documents in, text out
- Catalogue slug
- anthropic-claude-haiku-4-5