geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
anthropic

Claude Haiku 4.5

AI model Released

API mode
Chat*
Context window
200,000 tokens
Maximum output
64,000 tokens
Open weights
No

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Claude Haiku 4.5 1396.6 claude-haiku-4-5-20251001 · 95% interval 1394.2–1399.0 · 149,199 votes · 2026-10-15

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Claude Haiku 4.5

Radar task score

Unrated

2/4 core tests · not enough evidence

3 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Claude Haiku 4.5 71.2*% Approx. 95% interval: 64.9–77.5% · Older result

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Claude Haiku 4.5 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Claude Haiku 4.5 Not available

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Claude Haiku 4.5 12.6*% Approx. 95% interval: 10.5–14.7%

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

Claude Haiku 4.5 66.7*% Approx. 95% interval: 52.7–80.6% · Older result

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Benchmark results

  • Reported score · version unreported · intelligence37*Platform unreported Compare results

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Arena text preference / chinesehuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,418.13 rating

Confidence interval: 1,411.74 – 1,424.53

10532 votes

Category
chinese
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,453.50 rating

Confidence interval: 1,449.51 – 1,457.50

38427 votes

Category
coding
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,371.30 rating

Confidence interval: 1,366.63 – 1,375.96

25394 votes

Category
creative_writing
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,413.89 rating

Confidence interval: 1,410.60 – 1,417.18

64734 votes

Category
english
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,376.30 rating

Confidence interval: 1,373.05 – 1,379.55

111418 votes

Category
exclude_ties
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,442.74 rating

Confidence interval: 1,436.88 – 1,448.60

13709 votes

Category
expert
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,409.10 rating

Confidence interval: 1,398.04 – 1,420.17

4213 votes

Category
french
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,373.90 rating

Confidence interval: 1,360.70 – 1,387.10

2468 votes

Category
german
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,420.15 rating

Confidence interval: 1,417.15 – 1,423.16

92034 votes

Category
hard_prompts
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,434.40 rating

Confidence interval: 1,430.45 – 1,438.34

40648 votes

Category
hard_prompts_english
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,400.37 rating

Confidence interval: 1,396.00 – 1,404.74

28782 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,369.36 rating

Confidence interval: 1,365.08 – 1,373.64

32219 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,400.38 rating

Confidence interval: 1,394.10 – 1,406.66

11207 votes

Category
industry_legal_and_government
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,405.82 rating

Confidence interval: 1,401.21 – 1,410.43

24337 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,429.59 rating

Confidence interval: 1,422.30 – 1,436.88

7959 votes

Category
industry_mathematical
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,393.54 rating

Confidence interval: 1,386.83 – 1,400.25

10077 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,438.92 rating

Confidence interval: 1,435.44 – 1,442.40

56191 votes

Category
industry_software_and_it_services
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,386.69 rating

Confidence interval: 1,382.65 – 1,390.72

36448 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,414.47 rating

Confidence interval: 1,410.79 – 1,418.15

47790 votes

Category
instruction_following
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,338.15 rating

Confidence interval: 1,321.79 – 1,354.50

1712 votes

Category
japanese
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,346.13 rating

Confidence interval: 1,332.58 – 1,359.67

2378 votes

Category
korean
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,426.95 rating

Confidence interval: 1,423.25 – 1,430.65

56594 votes

Category
longer_query
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,396.70 rating

Confidence interval: 1,389.68 – 1,403.72

8311 votes

Category
math
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,409.42 rating

Confidence interval: 1,404.88 – 1,413.97

25888 votes

Category
multi_turn
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,376.68 rating

Confidence interval: 1,373.69 – 1,379.67

84413 votes

Category
non_english
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,396.64 rating

Confidence interval: 1,394.25 – 1,399.04

149199 votes

Category
overall
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,341.89 rating

Confidence interval: 1,331.27 – 1,352.50

3483 votes

Category
polish
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,380.97 rating

Confidence interval: 1,375.76 – 1,386.17

16646 votes

Category
russian
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

Claude Haiku 4.5

1,421.10 rating

Confidence interval: 1,410.84 – 1,431.35

4363 votes

Category
spanish
Evaluated configuration
claude-haiku-4-5-20251001
Evaluation type
human preference

Run it locally

Inference · memory estimate

Claude Haiku 4.5

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Claude Haiku 4.5

Claude Haiku 4.5 / Pricing tiers 4
Provider / scopeRateCurrencyAmount / unit
AWS BedrockClaude Haiku 4.5Batch Global cross-region InputUSD0.5 / 1M tokens
OutputUSD2.5 / 1M tokens
AWS BedrockClaude Haiku 4.5Standard Global cross-region Cached inputUSD0.1 / 1M tokens
InputUSD1 / 1M tokens
OutputUSD5 / 1M tokens
Google Vertex AIClaude Haiku 4.5Batch Token tier: 0 – 200,000 Cached inputUSD0.05 / 1M tokens
InputUSD0.5 / 1M tokens
OutputUSD2.5 / 1M tokens
Google Vertex AIClaude Haiku 4.5Standard Token tier: 0 – 200,000 Cached inputUSD0.1 / 1M tokens
InputUSD1 / 1M tokens
OutputUSD5 / 1M tokens

Capabilities

Context window
200,000 tokens
Maximum input
200,000 tokens*
Maximum output
64,000 tokens
Reasoning
Yes
Tool calling
Yes
Structured output
Yes*
Open weights
No
Knowledge cutoff
2025-02-28
API mode
Chat*
Declared context window
200K*
Model type
LLM*
Declared modalities
Text, Vision → Text*
Image input
Yes*
PDF input
Yes*
Prompt caching
Yes*
Tool choice
Yes*
Model license
Proprietary

Input modalities

  • text
  • image
  • pdf

Output modalities

  • text

System configuration

Detailed specifications

Specifications 1 · 13 fields
api providers
Anthropic, AWS, Vertex AI, Azure*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
context window
200K*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
developer
Anthropic*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
input price
1*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
intelligence
37*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
license
Proprietary*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
max output
64K*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
modality
Text, Vision → Text*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
model type
LLM*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
name
Claude Haiku 4.5*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
open weights
no*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
output price
5*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
release date
2025*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
Anthropic*
price_unit
Not reported*
price_tiers
Not reported*
Specifications 2 · 25 fields
cache creation input token cost
1.25e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache creation input token cost above 1hr
2.0e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache creation input token cost batches
6.25e-7*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost
1.0e-7*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost batches
5.0e-8*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token
1.0e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token batches
5.0e-7*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
anthropic*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max input tokens
200,000*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max output tokens
64,000*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max tokens
64,000*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
chat*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token
5.0e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token batches
2.5e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
prompt cache min tokens
4,096*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports assistant prefill
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports computer use
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports function calling
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports native structured output
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports pdf input
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports prompt caching
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports reasoning
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports response schema
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports tool choice
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports vision
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-haiku-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*

* Provisional data