Claude Sonnet 4.6
3 benchmark results for this configuration
GeekRadar / The comparison desk
COMPARE.
AI modelsClaude Sonnet 4.6
AI model Released
- API mode
- Chat*
- Context window
- 1,000,000 tokens
- Maximum output
- 64,000 tokens
- Open weights
- No
Capability & preference
General capability · ECI
A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
Benchmark results
- Reported score · version unreported · intelligence47*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 · 2026-10-28 · rating
Claude Sonnet 4.6
1,491.20 rating
Confidence interval: 1,481.79 – 1,500.60
4514 votes
- Category
- chinese
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,503.23 rating
Confidence interval: 1,497.71 – 1,508.75
19723 votes
- Category
- coding
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,435.41 rating
Confidence interval: 1,428.92 – 1,441.91
12351 votes
- Category
- creative_writing
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,472.28 rating
Confidence interval: 1,467.63 – 1,476.94
31970 votes
- Category
- english
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,458.24 rating
Confidence interval: 1,453.66 – 1,462.82
53775 votes
- Category
- exclude_ties
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,499.79 rating
Confidence interval: 1,492.02 – 1,507.56
7392 votes
- Category
- expert
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,465.03 rating
Confidence interval: 1,451.02 – 1,479.04
2271 votes
- Category
- french
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,427.64 rating
Confidence interval: 1,409.96 – 1,445.33
1220 votes
- Category
- german
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,484.31 rating
Confidence interval: 1,480.07 – 1,488.54
46219 votes
- Category
- hard_prompts
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,493.28 rating
Confidence interval: 1,487.87 – 1,498.70
21357 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,463.65 rating
Confidence interval: 1,457.54 – 1,469.76
14057 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,430.57 rating
Confidence interval: 1,424.57 – 1,436.57
15926 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,470.06 rating
Confidence interval: 1,461.48 – 1,478.63
5702 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,474.52 rating
Confidence interval: 1,468.10 – 1,480.94
11654 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,482.57 rating
Confidence interval: 1,472.51 – 1,492.64
3988 votes
- Category
- industry_mathematical
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,450.12 rating
Confidence interval: 1,441.37 – 1,458.88
5438 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,491.22 rating
Confidence interval: 1,486.32 – 1,496.12
27747 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,443.68 rating
Confidence interval: 1,438.01 – 1,449.35
17563 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,475.71 rating
Confidence interval: 1,470.57 – 1,480.86
23684 votes
- Category
- instruction_following
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,419.99 rating
Confidence interval: 1,397.75 – 1,442.22
802 votes
- Category
- japanese
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,409.53 rating
Confidence interval: 1,391.06 – 1,427.99
1150 votes
- Category
- korean
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,478.68 rating
Confidence interval: 1,473.74 – 1,483.61
31064 votes
- Category
- longer_query
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,462.39 rating
Confidence interval: 1,452.40 – 1,472.38
3795 votes
- Category
- math
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,463.21 rating
Confidence interval: 1,456.82 – 1,469.60
12685 votes
- Category
- multi_turn
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,439.77 rating
Confidence interval: 1,435.47 – 1,444.07
38942 votes
- Category
- non_english
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,457.71 rating
Confidence interval: 1,454.21 – 1,461.20
70916 votes
- Category
- overall
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,441.68 rating
Confidence interval: 1,425.89 – 1,457.47
1409 votes
- Category
- polish
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,439.51 rating
Confidence interval: 1,432.17 – 1,446.86
7987 votes
- Category
- russian
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Claude Sonnet 4.6
1,463.26 rating
Confidence interval: 1,449.47 – 1,477.06
2161 votes
- Category
- spanish
- Evaluated configuration
- Claude Sonnet 4.6
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,491.58 rating
Confidence interval: 1,482.17 – 1,501.00
4520 votes
- Category
- chinese
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,503.55 rating
Confidence interval: 1,498.02 – 1,509.08
19724 votes
- Category
- coding
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,435.40 rating
Confidence interval: 1,428.90 – 1,441.89
12367 votes
- Category
- creative_writing
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,472.40 rating
Confidence interval: 1,467.75 – 1,477.06
31965 votes
- Category
- english
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,458.49 rating
Confidence interval: 1,453.91 – 1,463.07
53806 votes
- Category
- exclude_ties
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,500.16 rating
Confidence interval: 1,492.38 – 1,507.95
7384 votes
- Category
- expert
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,464.92 rating
Confidence interval: 1,450.88 – 1,478.95
2284 votes
- Category
- french
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,428.12 rating
Confidence interval: 1,410.37 – 1,445.87
1221 votes
- Category
- german
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,484.67 rating
Confidence interval: 1,480.43 – 1,488.91
46229 votes
- Category
- hard_prompts
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,493.54 rating
Confidence interval: 1,488.12 – 1,498.96
21356 votes
- Category
- hard_prompts_english
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,463.77 rating
Confidence interval: 1,457.65 – 1,469.89
14063 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,430.71 rating
Confidence interval: 1,424.71 – 1,436.71
15933 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,470.11 rating
Confidence interval: 1,461.53 – 1,478.70
5707 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,474.93 rating
Confidence interval: 1,468.50 – 1,481.35
11651 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,482.93 rating
Confidence interval: 1,472.83 – 1,493.02
3982 votes
- Category
- industry_mathematical
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,451.04 rating
Confidence interval: 1,442.27 – 1,459.81
5437 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,491.37 rating
Confidence interval: 1,486.46 – 1,496.27
27745 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,443.62 rating
Confidence interval: 1,437.95 – 1,449.29
17602 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,475.98 rating
Confidence interval: 1,470.83 – 1,481.13
23711 votes
- Category
- instruction_following
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,420.02 rating
Confidence interval: 1,397.65 – 1,442.39
801 votes
- Category
- japanese
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,410.77 rating
Confidence interval: 1,392.26 – 1,429.29
1153 votes
- Category
- korean
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,478.96 rating
Confidence interval: 1,474.02 – 1,483.90
31070 votes
- Category
- longer_query
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,462.70 rating
Confidence interval: 1,452.70 – 1,472.69
3792 votes
- Category
- math
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,463.80 rating
Confidence interval: 1,457.40 – 1,470.20
12693 votes
- Category
- multi_turn
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,440.08 rating
Confidence interval: 1,435.77 – 1,444.39
38962 votes
- Category
- non_english
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,457.87 rating
Confidence interval: 1,454.37 – 1,461.36
70931 votes
- Category
- overall
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,442.27 rating
Confidence interval: 1,426.48 – 1,458.07
1412 votes
- Category
- polish
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,439.39 rating
Confidence interval: 1,432.03 – 1,446.74
7983 votes
- Category
- russian
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Claude Sonnet 4.6
1,463.74 rating
Confidence interval: 1,449.92 – 1,477.55
2168 votes
- Category
- spanish
- Evaluated configuration
- claude-sonnet-4-6
- Evaluation type
- human preference
Run it locally
Claude Sonnet 4.6
Closed weights. No supported local deployment or GPU requirement is published.
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Claude Sonnet 4.6
Claude Sonnet 4.6 / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| AWS BedrockClaude Sonnet 4.6Batch Global cross-region | Input | USD | 1.5 / 1M tokens |
| Output | USD | 7.5 / 1M tokens | |
| AWS BedrockClaude Sonnet 4.6Standard Global cross-region | Cached input | USD | 0.3 / 1M tokens |
| Input | USD | 3 / 1M tokens | |
| Output | USD | 15 / 1M tokens | |
| Google Vertex AIClaude Sonnet 4.6Batch Token tier: 0 – 200,000 | Cached input | USD | 0.15 / 1M tokens |
| Input | USD | 1.5 / 1M tokens | |
| Output | USD | 7.5 / 1M tokens | |
| Google Vertex AIClaude Sonnet 4.6Standard Token tier: 0 – 200,000 | Cached input | USD | 0.3 / 1M tokens |
| Input | USD | 3 / 1M tokens | |
| Output | USD | 15 / 1M tokens | |
| Google Vertex AIClaude Sonnet 4.6Standard Token tier: 200,000 – No stated upper limit | Cached input | USD | 0.3 / 1M tokens |
| Input | USD | 3 / 1M tokens | |
| Output | USD | 15 / 1M tokens |
Capabilities
- Context window
- 1,000,000 tokens
- Maximum input
- 1,000,000 tokens*
- Maximum output
- 64,000 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes*
- Open weights
- No
- Knowledge cutoff
- 2025-08-31
- API mode
- Chat*
- Declared context window
- 1M*
- Model type
- LLM*
- Declared modalities
- Text, Vision → Text*
- Image input
- Yes*
- PDF input
- Yes*
- Prompt caching
- Yes*
- Tool choice
- Yes*
- Web search
- Yes*
- Model license
- Proprietary
Input modalities
- text
- image
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
- 1M*
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
- 3*
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
- 47*
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 Sonnet 4.6*
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
- 15*
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 · 63 fields
- cache creation input token cost
- 3.75e-6*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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
- 3.75e-6*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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
- 6.0e-6*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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
- 6.0e-6*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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
- 1.875e-6*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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
- 3.0e-7*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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
- 3.0e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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
- 1.5e-7*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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
- 3.0e-6*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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
- 3.0e-6*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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
- 1.5e-6*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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-4-6*
- 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
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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-4-6*
- 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-4-6*
- 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
- 1.5e-5*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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
- 1.5e-5*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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
- 7.5e-6*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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
- 1,024*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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
- 1,024*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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 legacy thinking
- Yes*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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 legacy thinking
- Yes*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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 thinking cache preservation
- Yes*
Scope and conditions
- native_context
- provider
- anthropic*
- mode
- chat*
- full_native_model_id
- claude-sonnet-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-4-6*
- 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-sonnet-4-6*
- litellm_provider
- bedrock*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- anthropic.claude-sonnet-4-6*
- 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.*
0 selected Compare 0
* Provisional data