geekradar
Int
Explore GeekRadar

More to explore

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

DeepSeek-R1

AI model Released

API mode
Chat*
Context window
128,000 tokens
Maximum output
32,768 tokens
Open weights
Yes

Capability & preference

General capability · ECI

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

DeepSeek-R1 138.8* DeepSeek-R1 · 95% interval 136.5–140.2

Human preference · Arena

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

DeepSeek-R1 1372.7 DeepSeek-R1 · 95% interval 1367.8–1377.5 · 18,524 votes · 2026-10-28

Model performance

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

DeepSeek-R1

Radar task score

Unrated

1/4 core tests · not enough evidence

1 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

DeepSeek-R1 69.2*% Approx. 95% interval: 63.2–75.2% · Older result

Novel problem solving

Mystery Game Puzzles · 25%

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

DeepSeek-R1 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

DeepSeek-R1 Not available

Factual answers

SimpleQA Verified · 25%

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

DeepSeek-R1 Not available

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

Benchmark results

  • Reported score · version unreported · intelligence20.10*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-R1

1,400.05 rating

Confidence interval: 1,382.01 – 1,418.09

1151 votes

Category
chinese
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

DeepSeek-R1

1,371.11 rating

Confidence interval: 1,359.36 – 1,382.86

2317 votes

Category
coding
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

DeepSeek-R1

1,353.91 rating

Confidence interval: 1,343.63 – 1,364.20

3289 votes

Category
creative_writing
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,385.06 rating

Confidence interval: 1,378.97 – 1,391.15

10721 votes

Category
english
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

DeepSeek-R1

1,345.74 rating

Confidence interval: 1,338.56 – 1,352.92

12504 votes

Category
exclude_ties
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

DeepSeek-R1

1,337.37 rating

Confidence interval: 1,317.72 – 1,357.03

848 votes

Category
expert
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,366.71 rating

Confidence interval: 1,324.48 – 1,408.93

188 votes

Category
french
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,384.48 rating

Confidence interval: 1,356.32 – 1,412.63

436 votes

Category
german
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

DeepSeek-R1

1,361.08 rating

Confidence interval: 1,352.16 – 1,370.00

4116 votes

Category
hard_prompts
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,374.61 rating

Confidence interval: 1,363.50 – 1,385.72

2656 votes

Category
hard_prompts_english
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

DeepSeek-R1

1,347.58 rating

Confidence interval: 1,333.71 – 1,361.45

1798 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

DeepSeek-R1

1,346.62 rating

Confidence interval: 1,336.84 – 1,356.40

3571 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

DeepSeek-R1

1,371.03 rating

Confidence interval: 1,353.46 – 1,388.60

1097 votes

Category
industry_legal_and_government
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

DeepSeek-R1

1,375.20 rating

Confidence interval: 1,364.94 – 1,385.45

3309 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,389.27 rating

Confidence interval: 1,374.55 – 1,403.99

1504 votes

Category
industry_mathematical
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

DeepSeek-R1

1,370.45 rating

Confidence interval: 1,349.84 – 1,391.06

830 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

DeepSeek-R1

1,374.85 rating

Confidence interval: 1,365.71 – 1,383.99

3954 votes

Category
industry_software_and_it_services
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

DeepSeek-R1

1,364.29 rating

Confidence interval: 1,356.15 – 1,372.44

5355 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

DeepSeek-R1

1,357.27 rating

Confidence interval: 1,349.81 – 1,364.74

6426 votes

Category
instruction_following
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

DeepSeek-R1

1,324.32 rating

Confidence interval: 1,298.42 – 1,350.23

468 votes

Category
japanese
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,329.37 rating

Confidence interval: 1,289.71 – 1,369.02

215 votes

Category
korean
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,354.69 rating

Confidence interval: 1,342.77 – 1,366.60

2303 votes

Category
longer_query
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,392.49 rating

Confidence interval: 1,378.48 – 1,406.51

1606 votes

Category
math
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,390.53 rating

Confidence interval: 1,378.65 – 1,402.40

2418 votes

Category
multi_turn
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,356.44 rating

Confidence interval: 1,349.66 – 1,363.22

7803 votes

Category
non_english
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,372.65 rating

Confidence interval: 1,367.81 – 1,377.50

18524 votes

Category
overall
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,354.14 rating

Confidence interval: 1,341.31 – 1,366.98

1904 votes

Category
russian
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

DeepSeek-R1

1,378.90 rating

Confidence interval: 1,325.97 – 1,431.84

114 votes

Category
spanish
Evaluated configuration
DeepSeek-R1
Evaluation type
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

DeepSeek-R1

1,400.12 rating

Confidence interval: 1,382.08 – 1,418.17

1151 votes

Category
chinese
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

DeepSeek-R1

1,371.21 rating

Confidence interval: 1,359.45 – 1,382.96

2317 votes

Category
coding
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

DeepSeek-R1

1,354.08 rating

Confidence interval: 1,343.80 – 1,364.37

3289 votes

Category
creative_writing
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,385.02 rating

Confidence interval: 1,378.93 – 1,391.11

10721 votes

Category
english
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

DeepSeek-R1

1,345.77 rating

Confidence interval: 1,338.59 – 1,352.95

12504 votes

Category
exclude_ties
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

DeepSeek-R1

1,337.41 rating

Confidence interval: 1,317.75 – 1,357.06

848 votes

Category
expert
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,366.35 rating

Confidence interval: 1,324.12 – 1,408.58

188 votes

Category
french
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,384.44 rating

Confidence interval: 1,356.30 – 1,412.58

436 votes

Category
german
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

DeepSeek-R1

1,361.08 rating

Confidence interval: 1,352.17 – 1,370.00

4116 votes

Category
hard_prompts
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,374.51 rating

Confidence interval: 1,363.40 – 1,385.62

2656 votes

Category
hard_prompts_english
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

DeepSeek-R1

1,347.63 rating

Confidence interval: 1,333.76 – 1,361.50

1798 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

DeepSeek-R1

1,346.70 rating

Confidence interval: 1,336.92 – 1,356.47

3571 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

DeepSeek-R1

1,370.77 rating

Confidence interval: 1,353.20 – 1,388.34

1097 votes

Category
industry_legal_and_government
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

DeepSeek-R1

1,375.19 rating

Confidence interval: 1,364.94 – 1,385.45

3309 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,389.28 rating

Confidence interval: 1,374.56 – 1,403.99

1504 votes

Category
industry_mathematical
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

DeepSeek-R1

1,370.53 rating

Confidence interval: 1,349.92 – 1,391.14

830 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

DeepSeek-R1

1,374.94 rating

Confidence interval: 1,365.80 – 1,384.08

3954 votes

Category
industry_software_and_it_services
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

DeepSeek-R1

1,364.36 rating

Confidence interval: 1,356.21 – 1,372.51

5355 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

DeepSeek-R1

1,357.27 rating

Confidence interval: 1,349.81 – 1,364.74

6426 votes

Category
instruction_following
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

DeepSeek-R1

1,324.19 rating

Confidence interval: 1,298.32 – 1,350.06

468 votes

Category
japanese
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,329.46 rating

Confidence interval: 1,289.81 – 1,369.10

215 votes

Category
korean
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,354.75 rating

Confidence interval: 1,342.84 – 1,366.66

2303 votes

Category
longer_query
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,392.47 rating

Confidence interval: 1,378.45 – 1,406.48

1606 votes

Category
math
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,390.54 rating

Confidence interval: 1,378.66 – 1,402.42

2418 votes

Category
multi_turn
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,356.54 rating

Confidence interval: 1,349.76 – 1,363.32

7803 votes

Category
non_english
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,372.65 rating

Confidence interval: 1,367.81 – 1,377.50

18524 votes

Category
overall
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,354.28 rating

Confidence interval: 1,341.45 – 1,367.12

1904 votes

Category
russian
Evaluated configuration
deepseek-r1
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

DeepSeek-R1

1,378.83 rating

Confidence interval: 1,325.87 – 1,431.78

114 votes

Category
spanish
Evaluated configuration
deepseek-r1
Evaluation type
human preference

Run it locally

Inference · memory estimate

DeepSeek-R1

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

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

DeepSeek-R1

DeepSeek-R1 / Pricing tiers 2
Provider / scopeRateCurrencyAmount / unit
AWS BedrockDeepSeek-R1Standard InputUSD1.35 / 1M tokens
AWS BedrockDeepSeek-R1Standard Global cross-region InputUSD1.35 / 1M tokens
OutputUSD5.4 / 1M tokens

Capabilities

Context window
128,000 tokens
Maximum input
65,536 tokens*
Maximum output
32,768 tokens
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Knowledge cutoff
2024-07
API mode
Chat*
Declared context window
128K*
Model type
LLM (MoE, reasoning)*
Declared modalities
Text → Text*
Prompt caching
Yes*
Tool choice
Yes*
Model license
MIT

Input modalities

  • text

Output modalities

  • text

Processing & platform

Architecture
deepseek_v3

System configuration

Detailed specifications

Specifications 1 · 16 fields
api providers
DeepSeek, DeepInfra, 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
128K*
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
0.5*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
DeepSeek*
price_unit
Not reported*
price_tiers
Not reported*
intelligence
20.1*
Scope and conditions
native_context
metadata
name
Convly AI Models Database*
description
Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
generated
2026-09-22T15:41:48+00:00*
model_count
43*
fields
  • slug*
  • name*
  • developer*
  • model_type*
  • modality*
  • parameters*
  • context_window*
  • max_output*
  • open_weights*
  • license*
  • release_date*
  • input_price*
  • output_price*
  • price_unit*
  • price_tiers*
  • vram_q4*
  • vram_q4_gb*
  • min_gpu*
  • intelligence*
  • api_providers*
  • official_url*
  • retired*
  • convly_url*
developer
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*
min gpu
Multi-GPU server*
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, reasoning)*
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 R1*
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
2.15*
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
DeepSeek*
price_unit
Not reported*
price_tiers
Not reported*
parameters
671B total / 37B 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
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
DeepSeek*
price_unit
Not reported*
price_tiers
Not reported*
vram q4
~400 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
400* 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 · 14 fields
cache read input token cost
1.4e-7*
Scope and conditions
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-r1*
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
5.5e-7*
Scope and conditions
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-r1*
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
1.4e-7*
Scope and conditions
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-r1*
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-r1*
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
65,536*
Scope and conditions
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-r1*
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
8,192*
Scope and conditions
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-r1*
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
8,192*
Scope and conditions
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-r1*
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-r1*
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
2.19e-6*
Scope and conditions
native_context
provider
deepseek*
mode
chat*
full_native_model_id
deepseek/deepseek-r1*
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-r1*
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-r1*
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-r1*
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-r1*
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-r1*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*

* Provisional data