DeepSeek V4 Flash
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsDeepSeek V4 Flash
AI model Released
- API mode
- Chat*
- Context window
- 1,000,000 tokens
- Maximum output
- 384,000 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.
Benchmark results
- Reported score · version unreported · intelligence40.30*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
DeepSeek V4 Flash
1,463.90 rating
Confidence interval: 1,452.61 – 1,475.19
3000 votes
- Category
- chinese
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,456.40 rating
Confidence interval: 1,450.23 – 1,462.56
15295 votes
- Category
- coding
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,402.59 rating
Confidence interval: 1,395.11 – 1,410.07
8541 votes
- Category
- creative_writing
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,440.78 rating
Confidence interval: 1,435.52 – 1,446.03
23116 votes
- Category
- english
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,424.18 rating
Confidence interval: 1,418.97 – 1,429.39
39279 votes
- Category
- exclude_ties
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,441.29 rating
Confidence interval: 1,432.65 – 1,449.94
5404 votes
- Category
- expert
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,438.46 rating
Confidence interval: 1,423.64 – 1,453.28
1989 votes
- Category
- french
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,417.84 rating
Confidence interval: 1,396.54 – 1,439.14
838 votes
- Category
- german
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,443.47 rating
Confidence interval: 1,438.74 – 1,448.19
34750 votes
- Category
- hard_prompts
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,448.81 rating
Confidence interval: 1,442.79 – 1,454.83
16217 votes
- Category
- hard_prompts_english
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,425.22 rating
Confidence interval: 1,418.32 – 1,432.12
10434 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,399.42 rating
Confidence interval: 1,392.56 – 1,406.27
11202 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,438.95 rating
Confidence interval: 1,429.22 – 1,448.68
4140 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,446.70 rating
Confidence interval: 1,439.38 – 1,454.02
8388 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,432.03 rating
Confidence interval: 1,420.66 – 1,443.39
2980 votes
- Category
- industry_mathematical
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,447.64 rating
Confidence interval: 1,437.25 – 1,458.04
3672 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,452.68 rating
Confidence interval: 1,447.23 – 1,458.14
21384 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,409.70 rating
Confidence interval: 1,403.20 – 1,416.20
12571 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,420.90 rating
Confidence interval: 1,415.12 – 1,426.68
17943 votes
- Category
- instruction_following
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,388.55 rating
Confidence interval: 1,363.92 – 1,413.19
652 votes
- Category
- japanese
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,382.17 rating
Confidence interval: 1,361.37 – 1,402.96
901 votes
- Category
- korean
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,433.95 rating
Confidence interval: 1,428.43 – 1,439.47
23338 votes
- Category
- longer_query
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,425.77 rating
Confidence interval: 1,414.06 – 1,437.49
2699 votes
- Category
- math
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,448.55 rating
Confidence interval: 1,441.32 – 1,455.79
9339 votes
- Category
- multi_turn
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,419.11 rating
Confidence interval: 1,414.20 – 1,424.01
28827 votes
- Category
- non_english
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,431.83 rating
Confidence interval: 1,427.82 – 1,435.85
51944 votes
- Category
- overall
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,435.25 rating
Confidence interval: 1,416.61 – 1,453.88
1025 votes
- Category
- polish
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,426.44 rating
Confidence interval: 1,417.99 – 1,434.89
5737 votes
- Category
- russian
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
DeepSeek V4 Flash
1,435.71 rating
Confidence interval: 1,419.78 – 1,451.64
1578 votes
- Category
- spanish
- Evaluated configuration
- DeepSeek-V4-Flash
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,462.78 rating
Confidence interval: 1,451.50 – 1,474.06
3009 votes
- Category
- chinese
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,456.61 rating
Confidence interval: 1,450.44 – 1,462.77
15288 votes
- Category
- coding
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,403.29 rating
Confidence interval: 1,395.82 – 1,410.77
8582 votes
- Category
- creative_writing
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,440.79 rating
Confidence interval: 1,435.53 – 1,446.05
23129 votes
- Category
- english
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,424.19 rating
Confidence interval: 1,418.98 – 1,429.41
39317 votes
- Category
- exclude_ties
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,441.10 rating
Confidence interval: 1,432.44 – 1,449.75
5404 votes
- Category
- expert
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,439.02 rating
Confidence interval: 1,424.19 – 1,453.85
2004 votes
- Category
- french
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,418.64 rating
Confidence interval: 1,397.33 – 1,439.95
841 votes
- Category
- german
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,443.38 rating
Confidence interval: 1,438.66 – 1,448.11
34768 votes
- Category
- hard_prompts
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,448.92 rating
Confidence interval: 1,442.91 – 1,454.94
16226 votes
- Category
- hard_prompts_english
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,425.02 rating
Confidence interval: 1,418.12 – 1,431.92
10441 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,399.68 rating
Confidence interval: 1,392.81 – 1,406.54
11211 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,438.51 rating
Confidence interval: 1,428.77 – 1,448.24
4148 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,446.51 rating
Confidence interval: 1,439.20 – 1,453.82
8412 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,432.35 rating
Confidence interval: 1,420.96 – 1,443.75
2975 votes
- Category
- industry_mathematical
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,448.01 rating
Confidence interval: 1,437.62 – 1,458.40
3681 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,452.85 rating
Confidence interval: 1,447.39 – 1,458.31
21378 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,409.87 rating
Confidence interval: 1,403.37 – 1,416.36
12604 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,420.81 rating
Confidence interval: 1,415.03 – 1,426.59
17963 votes
- Category
- instruction_following
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,388.93 rating
Confidence interval: 1,364.22 – 1,413.63
653 votes
- Category
- japanese
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,382.29 rating
Confidence interval: 1,361.46 – 1,403.12
899 votes
- Category
- korean
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,433.99 rating
Confidence interval: 1,428.47 – 1,439.51
23356 votes
- Category
- longer_query
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,426.46 rating
Confidence interval: 1,414.74 – 1,438.18
2697 votes
- Category
- math
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,448.48 rating
Confidence interval: 1,441.24 – 1,455.72
9346 votes
- Category
- multi_turn
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,419.15 rating
Confidence interval: 1,414.25 – 1,424.06
28857 votes
- Category
- non_english
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,431.84 rating
Confidence interval: 1,427.82 – 1,435.86
51987 votes
- Category
- overall
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,435.25 rating
Confidence interval: 1,416.62 – 1,453.88
1027 votes
- Category
- polish
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,427.04 rating
Confidence interval: 1,418.59 – 1,435.49
5745 votes
- Category
- russian
- Evaluated configuration
- deepseek-v4-flash
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
DeepSeek V4 Flash
1,435.53 rating
Confidence interval: 1,419.58 – 1,451.49
1578 votes
- Category
- spanish
- Evaluated configuration
- deepseek-v4-flash
- 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 V4 Flash
DeepSeek V4 Flash / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| DeepInfradeepseek-ai/DeepSeek-V4-FlashStandard | Cached input | USD | 0.018 / 1M tokens |
| Input | USD | 0.09 / 1M tokens | |
| Output | USD | 0.18 / 1M tokens | |
| SiliconFlowdeepseek-ai/DeepSeek-V4-FlashStandard 费用发生时段: 0点～2点/8点～24点 | Cached input | CNY | 0.3 / 1M tokens |
| Input | CNY | 3 / 1M tokens | |
| Output | CNY | 9 / 1M tokens | |
| SiliconFlowdeepseek-ai/DeepSeek-V4-FlashStandard 费用发生时段: 2点～8点 | Cached input | CNY | 0.15 / 1M tokens |
| Input | CNY | 1.5 / 1M tokens | |
| Output | CNY | 4.5 / 1M tokens | |
| SiliconFlowdeepseek-ai/DeepSeek-V4-FlashStandard | Cached input | CNY | 0.02 / 1M tokens |
| Input | CNY | 1 / 1M tokens | |
| Output | CNY | 2 / 1M tokens |
Capabilities
- Context window
- 1,000,000 tokens
- Maximum input
- 1,000,000 tokens*
- Maximum output
- 384,000 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes*
- Open weights
- Yes
- Knowledge cutoff
- 2025-05
- API mode
- Chat*
- Declared context window
- 1M*
- Model type
- LLM (MoE)*
- Declared modalities
- Text → Text*
- Image input
- Yes*
- Parallel tool calls
- Yes*
- Prompt caching
- Yes*
- System messages
- Yes*
- Tool choice
- Yes*
- Model license
- MIT
Input modalities
- text
Output modalities
- text
Processing & platform
- Architecture
- deepseek_v4
System configuration
Detailed specifications
Specifications 1 · 17 fields
- api providers
- DeepSeek, OpenRouter*
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
- DeepSeek*
- 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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- developer
- DeepSeek*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- input price
- 0.14*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- intelligence
- 40.3*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- license
- MIT (open)*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- max output
- 384K*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- min gpu
- 2× H100 80GB (4-bit)*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- modality
- Text → 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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- model type
- LLM (MoE)*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- name
- DeepSeek V4-Flash*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- open weights
- yes*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- output price
- 0.28*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- parameters
- 284B total / ~13B active (MoE)*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- release date
- 2026-04*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- vram q4
- ~140 GB*
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- vram q4 gb
- 140* GB
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
- DeepSeek*
- price_unit
- Not reported*
- price_tiers
- Not reported*
Specifications 2 · 44 fields
- cache creation input token cost
- 0.0*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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
- 0.0*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 6.0e-9*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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
- 6.0e-9*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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-7*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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-7*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 6.0e-9*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 6.0e-9*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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-v4-flash*
- 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-v4-flash*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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
- 393,216*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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
- 393,216*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 393,216*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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
- 393,216*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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-v4-flash*
- 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-v4-flash*
- 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.*
- off peak pricing
- cache_read_input_token_cost
- 3.0e-9*
- input_cost_per_token
- 1.5e-7*
- output_cost_per_token
- 6.0e-7*
- windows
- hours_utc
- 00:00-01:00*
- 04:00-06:00*
- 10:00-00:00*
- weekdays
- 1*
- 2*
- 3*
- 4*
- 5*
- hours_utc
- 00:00-00:00*
- weekdays
- 6*
- 7*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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.*
- off peak pricing
- cache_read_input_token_cost
- 3.0e-9*
- input_cost_per_token
- 1.5e-7*
- output_cost_per_token
- 6.0e-7*
- windows
- hours_utc
- 00:00-01:00*
- 04:00-06:00*
- 10:00-00:00*
- weekdays
- 1*
- 2*
- 3*
- 4*
- 5*
- hours_utc
- 00:00-00:00*
- weekdays
- 6*
- 7*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 1.2e-6*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- 1.2e-6*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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.*
- supported endpoints
- /v1/chat/completions*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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.*
- supported endpoints
- /v1/chat/completions*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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-v4-flash*
- 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-v4-flash*
- 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-v4-flash*
- 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-v4-flash*
- 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 streaming
- Yes*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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 streaming
- Yes*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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 function calling
- Yes*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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 function calling
- Yes*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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-v4-flash*
- 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-v4-flash*
- 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-v4-flash*
- 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-v4-flash*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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 system messages
- Yes*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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 system messages
- Yes*
Scope and conditions
- native_context
- provider
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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-v4-flash*
- 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-v4-flash*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek-v4-flash*
- 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
- deepseek*
- mode
- chat*
- full_native_model_id
- deepseek/deepseek-v4-flash*
- 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