GeekRadar / The comparison desk

COMPARE.

AI models

anthropic

Claude Sonnet 5.5

AI model Released Sep 28, 2026

API mode: Chat^*
Context window: 1,000,000 tokens
Maximum output: 128,000 tokens
Open weights: No

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Claude Sonnet 5.5 166.7^* Claude Sonnet 5.5 · 95% interval 163.6–171.3

Human preference · Arena

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

Claude Sonnet 5.5 1472.9 Claude Sonnet 5.5 (xHigh) · 95% interval 1466.1–1479.6 · 10,033 votes · 2026-10-28

Model performance

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

Claude Sonnet 5.5

Tested configuration Radar task score

74.0^* / 100

4/4 core tests · experimental v1

9 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

Claude Sonnet 5.5 95.6^*% Approx. 95% interval: 92.9–98.3% · 2026-09-29

Novel problem solving

Mystery Game Puzzles · 25%

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

Claude Sonnet 5.5 65.0^*% Approx. 95% interval: 55.6–74.4% · 2026-09-29

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Claude Sonnet 5.5 88.8^*% Approx. 95% interval: 85.1–92.4% · 2026-09-29

Factual answers

SimpleQA Verified · 25%

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

Claude Sonnet 5.5 46.5^*% Approx. 95% interval: 43.4–49.6% · 2026-09-29

End-to-end software

MirrorCode · Separate result

Whole-program reimplementation with hidden tests; ML + Private, two languages. Budget: seven days and ten billion tokens per attempt.

Claude Sonnet 5.5 97.8^*% Approx. 95% interval: 94.8–100.0% · 2026-10-05

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 Sonnet 5.5 100.0^*% Uncertainty not available · 2026-09-29

Research mathematics

FrontierMath Tier 4 v2 · Separate result

The hardest private FrontierMath problems, corrected v2 set, with Python tools. Separate from Tiers 1-3 in the core score.

Claude Sonnet 5.5 80.5^*% Approx. 95% interval: 68.2–92.8% · 2026-09-29

Visual spatial reasoning

Furniture Assembly · Separate result

Assembly-error detection from photos and manuals, with zoom and Python tools. Uses model-assisted grading; not a general vision score.

Claude Sonnet 5.5 75.0^*% Approx. 95% interval: 64.2–85.8% · 2026-09-29

Long-horizon computer use

SpireClimb · Separate result

Equally weighted win rates in two Slay the Spire games via screenshots and controls. Fixed game versions; not a general desktop success rate.

Claude Sonnet 5.5 1.3^*% Approx. 95% interval: 0.0–3.2% · 2026-09-29

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.

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.

Test version

Arena text preference / chinesehuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,537.45 rating

Confidence interval: 1,516.67 – 1,558.23

859 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,511.91 rating

Confidence interval: 1,499.19 – 1,524.64

2339 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,470.37 rating

Confidence interval: 1,456.76 – 1,483.98

2278 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,483.81 rating

Confidence interval: 1,473.48 – 1,494.13

3741 votes

Oct 28, 2026

Category: english
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,479.65 rating

Confidence interval: 1,470.58 – 1,488.71

7356 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,527.21 rating

Confidence interval: 1,508.75 – 1,545.67

1024 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,497.67 rating

Confidence interval: 1,468.41 – 1,526.94

407 votes

Oct 28, 2026

Category: french
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,425.03 rating

Confidence interval: 1,384.63 – 1,465.43

178 votes

Oct 28, 2026

Category: german
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,493.76 rating

Confidence interval: 1,485.48 – 1,502.05

6168 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,501.45 rating

Confidence interval: 1,488.73 – 1,514.16

2356 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,466.28 rating

Confidence interval: 1,451.42 – 1,481.15

1666 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,459.50 rating

Confidence interval: 1,446.93 – 1,472.07

2615 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,484.77 rating

Confidence interval: 1,463.75 – 1,505.79

822 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,486.97 rating

Confidence interval: 1,472.04 – 1,501.90

1704 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,513.33 rating

Confidence interval: 1,488.20 – 1,538.47

536 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,476.11 rating

Confidence interval: 1,453.41 – 1,498.81

703 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,504.26 rating

Confidence interval: 1,493.64 – 1,514.88

3416 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,474.30 rating

Confidence interval: 1,462.29 – 1,486.31

2855 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,491.84 rating

Confidence interval: 1,481.07 – 1,502.61

3357 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,456.70 rating

Confidence interval: 1,416.92 – 1,496.48

205 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,494.45 rating

Confidence interval: 1,484.40 – 1,504.49

4212 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,503.89 rating

Confidence interval: 1,477.82 – 1,529.96

497 votes

Oct 28, 2026

Category: math
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,468.11 rating

Confidence interval: 1,452.09 – 1,484.14

1445 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,456.10 rating

Confidence interval: 1,447.91 – 1,464.28

6288 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,472.85 rating

Confidence interval: 1,466.09 – 1,479.61

10033 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,460.95 rating

Confidence interval: 1,444.43 – 1,477.47

1400 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Claude Sonnet 5.5

1,447.36 rating

Confidence interval: 1,417.35 – 1,477.37

359 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Claude Sonnet 5.5 (xHigh)
Evaluation type: human preference

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

Claude Sonnet 5.5

1,536.90 rating

Confidence interval: 1,511.44 – 1,562.36

553 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,513.04 rating

Confidence interval: 1,498.12 – 1,527.96

1627 votes

Oct 15, 2026

Category: coding
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,466.86 rating

Confidence interval: 1,450.79 – 1,482.93

1532 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,484.53 rating

Confidence interval: 1,472.52 – 1,496.53

2578 votes

Oct 15, 2026

Category: english
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,475.90 rating

Confidence interval: 1,465.46 – 1,486.34

4998 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,532.22 rating

Confidence interval: 1,510.16 – 1,554.28

700 votes

Oct 15, 2026

Category: expert
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,496.87 rating

Confidence interval: 1,460.94 – 1,532.79

259 votes

Oct 15, 2026

Category: french
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,492.54 rating

Confidence interval: 1,483.01 – 1,502.07

4222 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,502.72 rating

Confidence interval: 1,487.71 – 1,517.73

1606 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,459.96 rating

Confidence interval: 1,442.74 – 1,477.18

1177 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,457.59 rating

Confidence interval: 1,442.80 – 1,472.38

1741 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,484.96 rating

Confidence interval: 1,460.75 – 1,509.18

591 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,478.58 rating

Confidence interval: 1,461.03 – 1,496.12

1187 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,506.28 rating

Confidence interval: 1,475.85 – 1,536.70

362 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,455.77 rating

Confidence interval: 1,428.69 – 1,482.85

468 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,501.29 rating

Confidence interval: 1,488.83 – 1,513.75

2359 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,472.04 rating

Confidence interval: 1,457.82 – 1,486.25

1902 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,488.49 rating

Confidence interval: 1,475.91 – 1,501.07

2303 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,493.73 rating

Confidence interval: 1,482.02 – 1,505.43

2882 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,498.64 rating

Confidence interval: 1,467.33 – 1,529.95

345 votes

Oct 15, 2026

Category: math
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,462.88 rating

Confidence interval: 1,444.22 – 1,481.53

1008 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,454.15 rating

Confidence interval: 1,444.67 – 1,463.64

4250 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,470.38 rating

Confidence interval: 1,462.66 – 1,478.10

6831 votes

Oct 15, 2026

Category: overall
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,445.16 rating

Confidence interval: 1,426.08 – 1,464.24

955 votes

Oct 15, 2026

Category: russian
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

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

Claude Sonnet 5.5

1,450.18 rating

Confidence interval: 1,413.90 – 1,486.46

244 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: claude-sonnet-5.5-xhigh
Evaluation type: human preference

Run it locally

Inference · memory estimate

Claude Sonnet 5.5

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

API cost

USD / month

Input tokens / monthOutput tokens / month

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

Claude Sonnet 5.5

Provider offer

Claude Sonnet 5.5 / Pricing tiers 3

Provider / scope	Rate	Currency	Amount / unit
AnthropicClaude Sonnet 5.5Batch	Input	USD	1 / 1M tokens
AnthropicClaude Sonnet 5.5Batch	Output	USD	5 / 1M tokens
AnthropicClaude Sonnet 5.5Standard	Cached input	USD	0.1 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	10 / 1M tokens
AWS BedrockClaude Sonnet 5.5Standard Global cross-region	Cached input	USD	0.1 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	10 / 1M tokens

Capabilities

Context window: 1,000,000 tokens
Maximum input: 1,000,000 tokens^*
Maximum output: 128,000 tokens
Reasoning: Yes
Tool calling: Yes
Structured output: Yes^*
Open weights: No
Knowledge cutoff: 2026-06
API mode: Chat^*
Image input: Yes^*
PDF input: Yes^*
Prompt caching: Yes^*
Tool choice: Yes^*
Web search: Yes^*
Model license: Proprietary

Input modalities

text
image
pdf

Output modalities

text

System configuration

Detailed specifications

Specifications · 73 fields

bedrock converse supports strict tools

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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.^*

bedrock output config effort ceiling

xhigh^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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

2.5e-6^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

2.5e-6^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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

4.0e-6^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

4.0e-6^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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

1.25e-6^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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-sonnet-5-5^*
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

2.0e-6^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

2.0e-6^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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

1.0e-6^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

bedrock_converse^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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

1,000,000^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

1,000,000^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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

128,000^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

128,000^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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

128,000^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

128,000^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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

1.0e-5^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

1.0e-5^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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

5.0e-6^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

512^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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

512^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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.^*

provider specific entry

us: 1.1^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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.^*

search context cost per query

search_context_size_high: 0.01^*
search_context_size_low: 0.01^*
search_context_size_medium: 0.01^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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.^*

search context cost per query

search_context_size_high: 0.01^*
search_context_size_low: 0.01^*
search_context_size_medium: 0.01^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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 adaptive thinking

Yes^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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 adaptive thinking

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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 anthropic compaction

Yes^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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

No^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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 bedrock native structured output

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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 forced tool use

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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 forced tool use

No^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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 max reasoning effort

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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 max reasoning effort

Yes^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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 mid conversation system

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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 mid conversation system

Yes^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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-sonnet-5-5^*
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

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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 output config

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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 output config

Yes^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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 parallel tool use config

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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 sampling params

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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 sampling params

No^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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 search

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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-sonnet-5-5^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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 web search

Yes^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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 xhigh reasoning effort

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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 xhigh reasoning effort

Yes^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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.^*

thinking always on

Yes^*

Scope and conditions

native_context

provider: anthropic^*
mode: chat^*
full_native_model_id: claude-sonnet-5-5^*
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.^*

thinking always on

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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.^*

token count model

model: anthropic.claude-opus-5-5^*
litellm_provider: bedrock_mantle^*
region: us-east-1^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: anthropic.claude-sonnet-5-5^*
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