DeepSeek V3.2
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsDeepSeek V3.2
AI model Released
- API mode
- Chat*
- Context window
- 128,000 tokens
- Maximum output
- 64,000 tokens
- Open weights
- Yes
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.
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
DeepSeek V3.2
1,454.94 rating
Confidence interval: 1,444.89 – 1,464.99
3726 votes
- Category
- chinese
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,448.79 rating
Confidence interval: 1,442.56 – 1,455.03
10917 votes
- Category
- coding
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,399.59 rating
Confidence interval: 1,392.03 – 1,407.14
6873 votes
- Category
- creative_writing
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,436.64 rating
Confidence interval: 1,431.64 – 1,441.63
19604 votes
- Category
- english
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,414.57 rating
Confidence interval: 1,409.72 – 1,419.42
34020 votes
- Category
- exclude_ties
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,435.80 rating
Confidence interval: 1,425.60 – 1,446.01
3429 votes
- Category
- expert
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,429.05 rating
Confidence interval: 1,411.39 – 1,446.70
1241 votes
- Category
- french
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,408.12 rating
Confidence interval: 1,387.97 – 1,428.26
901 votes
- Category
- german
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,433.51 rating
Confidence interval: 1,429.08 – 1,437.94
27074 votes
- Category
- hard_prompts
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,445.45 rating
Confidence interval: 1,439.24 – 1,451.66
11105 votes
- Category
- hard_prompts_english
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,409.65 rating
Confidence interval: 1,402.93 – 1,416.37
9049 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,394.86 rating
Confidence interval: 1,388.06 – 1,401.66
8781 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,425.12 rating
Confidence interval: 1,414.96 – 1,435.29
3489 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,445.29 rating
Confidence interval: 1,438.11 – 1,452.46
7631 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,438.79 rating
Confidence interval: 1,426.66 – 1,450.93
2482 votes
- Category
- industry_mathematical
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,440.16 rating
Confidence interval: 1,429.29 – 1,451.02
3112 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,443.57 rating
Confidence interval: 1,438.34 – 1,448.79
17247 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,406.79 rating
Confidence interval: 1,400.51 – 1,413.07
10684 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,412.67 rating
Confidence interval: 1,406.99 – 1,418.36
13555 votes
- Category
- instruction_following
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,358.28 rating
Confidence interval: 1,330.01 – 1,386.55
452 votes
- Category
- japanese
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,369.31 rating
Confidence interval: 1,348.15 – 1,390.47
799 votes
- Category
- korean
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,427.85 rating
Confidence interval: 1,422.13 – 1,433.56
13727 votes
- Category
- longer_query
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,435.13 rating
Confidence interval: 1,424.55 – 1,445.71
3139 votes
- Category
- math
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,426.86 rating
Confidence interval: 1,419.81 – 1,433.91
8336 votes
- Category
- multi_turn
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,408.79 rating
Confidence interval: 1,404.48 – 1,413.10
28486 votes
- Category
- non_english
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,424.43 rating
Confidence interval: 1,420.97 – 1,427.90
48095 votes
- Category
- overall
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,408.56 rating
Confidence interval: 1,392.44 – 1,424.68
1339 votes
- Category
- polish
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,423.43 rating
Confidence interval: 1,415.73 – 1,431.14
6099 votes
- Category
- russian
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
DeepSeek V3.2
1,423.67 rating
Confidence interval: 1,407.97 – 1,439.36
1533 votes
- Category
- spanish
- Evaluated configuration
- DeepSeek-V3.2
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,455.07 rating
Confidence interval: 1,445.02 – 1,465.12
3729 votes
- Category
- chinese
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,448.90 rating
Confidence interval: 1,442.66 – 1,455.13
10923 votes
- Category
- coding
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,399.19 rating
Confidence interval: 1,391.64 – 1,406.75
6883 votes
- Category
- creative_writing
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,436.70 rating
Confidence interval: 1,431.70 – 1,441.69
19617 votes
- Category
- english
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,414.66 rating
Confidence interval: 1,409.81 – 1,419.51
34030 votes
- Category
- exclude_ties
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,436.26 rating
Confidence interval: 1,426.04 – 1,446.48
3426 votes
- Category
- expert
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,428.74 rating
Confidence interval: 1,411.06 – 1,446.42
1243 votes
- Category
- french
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,407.93 rating
Confidence interval: 1,387.76 – 1,428.11
901 votes
- Category
- german
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,433.55 rating
Confidence interval: 1,429.12 – 1,437.98
27086 votes
- Category
- hard_prompts
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,445.39 rating
Confidence interval: 1,439.18 – 1,451.60
11113 votes
- Category
- hard_prompts_english
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,409.91 rating
Confidence interval: 1,403.19 – 1,416.63
9052 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,394.65 rating
Confidence interval: 1,387.84 – 1,401.45
8785 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,424.97 rating
Confidence interval: 1,414.81 – 1,435.14
3491 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,445.47 rating
Confidence interval: 1,438.29 – 1,452.64
7632 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,438.92 rating
Confidence interval: 1,426.78 – 1,451.06
2483 votes
- Category
- industry_mathematical
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,439.77 rating
Confidence interval: 1,428.91 – 1,450.63
3118 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,443.67 rating
Confidence interval: 1,438.44 – 1,448.90
17256 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,406.94 rating
Confidence interval: 1,400.66 – 1,413.22
10687 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,412.63 rating
Confidence interval: 1,406.94 – 1,418.32
13567 votes
- Category
- instruction_following
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,358.14 rating
Confidence interval: 1,329.82 – 1,386.46
452 votes
- Category
- japanese
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,369.73 rating
Confidence interval: 1,348.50 – 1,390.97
796 votes
- Category
- korean
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,428.02 rating
Confidence interval: 1,422.30 – 1,433.73
13732 votes
- Category
- longer_query
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,435.18 rating
Confidence interval: 1,424.60 – 1,445.76
3141 votes
- Category
- math
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,426.95 rating
Confidence interval: 1,419.90 – 1,434.00
8341 votes
- Category
- multi_turn
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,408.85 rating
Confidence interval: 1,404.54 – 1,413.17
28490 votes
- Category
- non_english
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,424.46 rating
Confidence interval: 1,420.99 – 1,427.92
48112 votes
- Category
- overall
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,408.46 rating
Confidence interval: 1,392.34 – 1,424.58
1340 votes
- Category
- polish
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,423.28 rating
Confidence interval: 1,415.57 – 1,431.00
6096 votes
- Category
- russian
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
DeepSeek V3.2
1,422.91 rating
Confidence interval: 1,407.20 – 1,438.63
1531 votes
- Category
- spanish
- Evaluated configuration
- deepseek-v3.2
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
DeepSeek V3.2
DeepSeek V3.2 / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| AWS BedrockDeepSeek v3.2Standard Global cross-region | Input | USD | 0.62 / 1M tokens |
| Output | USD | 1.85 / 1M tokens | |
| DeepInfradeepseek-ai/DeepSeek-V3.2Standard | Cached input | USD | 0.13 / 1M tokens |
| Input | USD | 0.26 / 1M tokens | |
| Output | USD | 0.38 / 1M tokens | |
| SambaNova CloudDeepSeek-V3.2Standard | Input | USD | 3 / 1M tokens |
| Output | USD | 4.5 / 1M tokens | |
| SiliconFlowdeepseek-ai/DeepSeek-V3.2Standard | Cached input | CNY | 0.4 / 1M tokens |
| Input | CNY | 4 / 1M tokens | |
| Output | CNY | 6 / 1M tokens |
Capabilities
- Context window
- 128,000 tokens
- Maximum input
- Reported value 1: 163,840 tokens*Reported value 2: 164,000 tokens*
- Maximum output
- 64,000 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes*
- Open weights
- Yes
- Knowledge cutoff
- 2024-07
- API mode
- Chat*
- Image input
- No*
- Audio input
- No*
- Prompt caching
- Yes*
- Tool choice
- Yes*
- Model license
- MIT License
Input modalities
- text
Output modalities
- text
Processing & platform
- Architecture
- deepseek_v32
System configuration
Detailed specifications
Specifications · 34 fields
- cache read input token cost
- 2.8e-8*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- 6.2e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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
- 2.8e-7*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- 3.1e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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 cache hit
- 2.8e-8*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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 flex
- 3.1e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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 priority
- 1.085e-6*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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
- deepseek*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- deepseek.v3.2*
- 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
- 163,840*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- 164,000*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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
- 163,840*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- 8,000*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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
- 8,000*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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
- 163,840*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- deepseek.v3.2*
- 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
- 1.85e-6*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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
- 4.0e-7*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- 9.25e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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 flex
- 9.25e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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 priority
- 3.2375e-6*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supports assistant prefill
- Yes*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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 audio input
- No*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- deepseek.v3.2*
- 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
- deepseek.v3.2*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- deepseek.v3.2*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- deepseek.v3.2*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v3.2*
- 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
- deepseek.v3.2*
- 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
- No*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- deepseek.v3.2*
- 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