Advertised pdf input support
PDF input advertised by 2 of the 7 peers that list their features.
Anthropic · Chat
Newer version: Claude Haiku 5.5. Our catalogue has no release date for Claude Haiku 3.5. We compared the version names in our catalogue.
Evidence and sources
PDF input advertised by 2 of the 7 peers that list their features.
The maker has already deprecated this model (5 Jul 2026).
Maker's price: $1.60 blended / 1M, pricier than 6 of 9 priced peers.
The weights aren't public, so you can't run it yourself.
Supported operations and provider-stated features
| 200K | $0.80cache read $0.08 | $4.00cache write $1.00 | |
| 189K | $0.68cache read $0.068 | $3.40cache write $0.85 | |
| —Not published by the provider | $0.80cache read $0.08 | $4.00cache write $1.00 | |
| 200K | $0.80cache read $0.08 | $4.00cache write $1.00 | |
| 200K | $0.80cache read $0.08 | $4.00cache write $1.60 | |
| 200K | $0.80 | $4.00 | |
| —Not published by the provider | $0.80 | $4.00 | |
| —Not published by the provider | $0.80 | $4.00 | |
| 200K | $0.80 | $4.00 | |
| 200K | $0.80cache read $0.08 | $4.00cache write $1.00 |
Showing 10 of 21: the maker's own listing first, then the cheapest per 1M input tokens from each provider.
Also sold by Replicate.
3 listings without a price are hidden.
Named effort levels run from lowest to highest. Select a result to see its source details.
| Benchmark | Score |
|---|---|
| Arena ELO | |
| Chinese | |
| Creative Writing | |
| English |
| Benchmark | dev, version: 0.1.0 |
|---|---|
| Overall (dev) | |
| grammar_morphology (accuracy, dev) | |
| knowledge_mc (accuracy, dev) | |
| reading_comprehension (accuracy, dev) |
| Benchmark | dev, version: 0.1.0 |
|---|---|
| sentiment (accuracy, dev) | |
| translation (chrF, dev) |
Data credits: Aider LLM Leaderboards (Aider-AI), Apache-2.0 (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · DABstep (Adyen), CC BY 4.0 (licence) · Data by LLM Stats · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · Stanford HELM (Stanford CRFM), Apache-2.0 (licence) · KazBench by Yersultan Akhmer. Provisional DEV numeric results; code MIT and task-data CC BY 4.0 do not establish a separate score licence. · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Phare (Giskard), CC BY 4.0 (licence) · SeaExam and SeaBench leaderboard, SeaLLMs (DAMO-NLP-SG). Published leaderboard scores; results licence not stated.
docs.aws.amazon.com
aws.amazon.com
www-cdn.anthropic.com
github.com
techcrunch.com
docs.aws.amazon.com
simonwillison.net
image: https://og-api.replicateassets.com/api/models/anthropic/claude-3.5-haiku description: Anthropic's fastest, most cost-effective model, with a 200K token context window (claude-3-5-haiku-2024102…
replicate.com
pi.dev
openrouter.ai
Also known as: anthropic.claude-3-5-haiku-20241022-v1:0, anthropic/claude-3-5-haiku, anthropic/claude-3.5-haiku, anthropic/claude-3.5-haiku-20241022, anthropic/claude-haiku-3.5, bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0, claude-3-5-haiku, claude-3-5-haiku-20241022, claude-3-5-haiku-latest, claude-3.5-haiku, claude-3.5-haiku-20241022, eu.anthropic.claude-3-5-haiku-20241022-v1:0, gradient_ai/anthropic-claude-3.5-haiku, heroku/claude-3-5-haiku, regional.anthropic.claude-3-5-haiku-20241022-v1:0, replicate/anthropic/claude-3.5-haiku, us.anthropic.claude-3-5-haiku-20241022-v1:0, vercel_ai_gateway/anthropic/claude-3.5-haiku, vertex_ai/claude-3-5-haiku, vertex_ai/claude-3-5-haiku@20241022
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works