GeekRadar / The comparison desk

COMPARE.

AI models

deepseek

DeepSeek V4 Pro

AI model Released Apr 24, 2026

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.

DeepSeek V4 Pro 149.1^* DeepSeek-V4-Pro · 95% interval 147.2–150.9

Human preference · Arena

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

DeepSeek V4 Pro 1451.1 DeepSeek-V4-Pro · 95% interval 1447.3–1455.0 · 57,572 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 V4 Pro

Tested configuration Radar task score

Unrated

3/4 core tests · not enough evidence

5 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

DeepSeek V4 Pro 89.6^*% Approx. 95% interval: 86.2–93.1% · 2026-06-16

Novel problem solving

Mystery Game Puzzles · 25%

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

DeepSeek V4 Pro Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

DeepSeek V4 Pro 45.3^*% Approx. 95% interval: 39.5–51.1% · 2026-06-17

Factual answers

SimpleQA Verified · 25%

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

DeepSeek V4 Pro 47.0^*% Approx. 95% interval: 43.9–50.1% · 2026-08-27

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

DeepSeek V4 Pro 96.7^*% Approx. 95% interval: 92.7–100.0% · 2026-06-17

Research mathematics

FrontierMath Tier 4 v2 · Separate result

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

DeepSeek V4 Pro 2.4^*% Approx. 95% interval: 0.0–7.2% · 2026-06-17

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 · intelligence44.30^*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.

Test version

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

DeepSeek V4 Pro

1,481.52 rating

Confidence interval: 1,470.79 – 1,492.26

3380 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,468.95 rating

Confidence interval: 1,463.07 – 1,474.84

17146 votes

Oct 28, 2026

Category: coding
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,446.30 rating

Confidence interval: 1,439.10 – 1,453.51

9709 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,458.97 rating

Confidence interval: 1,453.88 – 1,464.05

25284 votes

Oct 28, 2026

Category: english
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,449.77 rating

Confidence interval: 1,444.73 – 1,454.81

43583 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,462.61 rating

Confidence interval: 1,454.26 – 1,470.97

5922 votes

Oct 28, 2026

Category: expert
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,472.61 rating

Confidence interval: 1,458.21 – 1,487.01

2210 votes

Oct 28, 2026

Category: french
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,456.74 rating

Confidence interval: 1,437.50 – 1,475.98

995 votes

Oct 28, 2026

Category: german
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,460.98 rating

Confidence interval: 1,456.43 – 1,465.53

38501 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,465.55 rating

Confidence interval: 1,459.74 – 1,471.36

17844 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,443.00 rating

Confidence interval: 1,436.34 – 1,449.66

11378 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,430.81 rating

Confidence interval: 1,424.26 – 1,437.36

12804 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,464.41 rating

Confidence interval: 1,454.96 – 1,473.86

4487 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,470.01 rating

Confidence interval: 1,462.95 – 1,477.07

9171 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,455.37 rating

Confidence interval: 1,444.52 – 1,466.22

3293 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,465.55 rating

Confidence interval: 1,455.58 – 1,475.52

4060 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,468.42 rating

Confidence interval: 1,463.19 – 1,473.66

23647 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,447.34 rating

Confidence interval: 1,441.06 – 1,453.62

14120 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,445.24 rating

Confidence interval: 1,439.68 – 1,450.80

20026 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,445.40 rating

Confidence interval: 1,422.08 – 1,468.71

725 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,409.19 rating

Confidence interval: 1,390.35 – 1,428.02

1107 votes

Oct 28, 2026

Category: korean
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,457.35 rating

Confidence interval: 1,452.06 – 1,462.65

25924 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,442.50 rating

Confidence interval: 1,431.43 – 1,453.57

3061 votes

Oct 28, 2026

Category: math
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,467.43 rating

Confidence interval: 1,460.45 – 1,474.41

10354 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,439.01 rating

Confidence interval: 1,434.31 – 1,443.71

32288 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,451.13 rating

Confidence interval: 1,447.25 – 1,455.01

57572 votes

Oct 28, 2026

Category: overall
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,460.75 rating

Confidence interval: 1,442.90 – 1,478.59

1123 votes

Oct 28, 2026

Category: polish
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,453.02 rating

Confidence interval: 1,444.85 – 1,461.19

6314 votes

Oct 28, 2026

Category: russian
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,455.89 rating

Confidence interval: 1,440.76 – 1,471.02

1728 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: DeepSeek-V4-Pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,480.82 rating

Confidence interval: 1,470.09 – 1,491.55

3389 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,469.32 rating

Confidence interval: 1,463.43 – 1,475.21

17136 votes

Oct 15, 2026

Category: coding
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,445.88 rating

Confidence interval: 1,438.67 – 1,453.09

9726 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,459.34 rating

Confidence interval: 1,454.25 – 1,464.43

25292 votes

Oct 15, 2026

Category: english
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,449.78 rating

Confidence interval: 1,444.73 – 1,454.83

43602 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,463.11 rating

Confidence interval: 1,454.73 – 1,471.48

5913 votes

Oct 15, 2026

Category: expert
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,472.73 rating

Confidence interval: 1,458.27 – 1,487.19

2211 votes

Oct 15, 2026

Category: french
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,458.00 rating

Confidence interval: 1,438.70 – 1,477.29

997 votes

Oct 15, 2026

Category: german
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,461.30 rating

Confidence interval: 1,456.75 – 1,465.86

38511 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,466.05 rating

Confidence interval: 1,460.23 – 1,471.86

17840 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,443.29 rating

Confidence interval: 1,436.63 – 1,449.95

11386 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,430.46 rating

Confidence interval: 1,423.90 – 1,437.01

12801 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,464.17 rating

Confidence interval: 1,454.71 – 1,473.63

4494 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,470.11 rating

Confidence interval: 1,463.04 – 1,477.18

9166 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,455.16 rating

Confidence interval: 1,444.29 – 1,466.04

3288 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,465.51 rating

Confidence interval: 1,455.54 – 1,475.48

4066 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,468.95 rating

Confidence interval: 1,463.71 – 1,474.19

23637 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,446.96 rating

Confidence interval: 1,440.68 – 1,453.25

14140 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,445.13 rating

Confidence interval: 1,439.56 – 1,450.70

20027 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,445.57 rating

Confidence interval: 1,422.06 – 1,469.07

722 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,409.13 rating

Confidence interval: 1,390.28 – 1,427.97

1111 votes

Oct 15, 2026

Category: korean
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,457.40 rating

Confidence interval: 1,452.11 – 1,462.70

25932 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,442.80 rating

Confidence interval: 1,431.72 – 1,453.87

3063 votes

Oct 15, 2026

Category: math
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,467.38 rating

Confidence interval: 1,460.40 – 1,474.36

10357 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,438.78 rating

Confidence interval: 1,434.08 – 1,443.48

32302 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,451.16 rating

Confidence interval: 1,447.28 – 1,455.04

57594 votes

Oct 15, 2026

Category: overall
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,461.21 rating

Confidence interval: 1,443.35 – 1,479.07

1124 votes

Oct 15, 2026

Category: polish
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,452.46 rating

Confidence interval: 1,444.29 – 1,460.63

6319 votes

Oct 15, 2026

Category: russian
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

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

DeepSeek V4 Pro

1,456.25 rating

Confidence interval: 1,441.10 – 1,471.40

1731 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: deepseek-v4-pro
Evaluation type: human preference

Run it locally

Inference · memory estimate

DeepSeek V4 Pro

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

Input tokens / monthOutput tokens / month

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

DeepSeek V4 Pro

Provider offer

DeepSeek V4 Pro / Pricing tiers 2

Provider / scope	Rate	Currency	Amount / unit
DeepInfradeepseek-ai/DeepSeek-V4-ProStandard	Cached input	USD	0.1 / 1M tokens
	Input	USD	1.3 / 1M tokens
	Output	USD	2.6 / 1M tokens
SiliconFlowdeepseek-ai/DeepSeek-V4-ProStandard	Cached input	CNY	1 / 1M tokens
	Input	CNY	12 / 1M tokens
	Output	CNY	24 / 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: No^*
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

0.435^*

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

44.3^*

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

Multi-GPU server (e.g. 8× H100 80GB)^*

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-Pro^*

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

0.87^*

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

1.6T total / ~49B 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

~800 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

800^* 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-pro^*
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-pro^*
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

4.4e-8^*

Scope and conditions

native_context

provider: deepseek^*
mode: chat^*
full_native_model_id: deepseek-v4-pro^*
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

4.4e-8^*

Scope and conditions

native_context

provider: deepseek^*
mode: chat^*
full_native_model_id: deepseek/deepseek-v4-pro^*
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

1.32e-6^*

Scope and conditions

native_context

provider: deepseek^*
mode: chat^*
full_native_model_id: deepseek-v4-pro^*
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

1.32e-6^*

Scope and conditions

native_context

provider: deepseek^*
mode: chat^*
full_native_model_id: deepseek/deepseek-v4-pro^*
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

4.4e-8^*

Scope and conditions

native_context

provider: deepseek^*
mode: chat^*
full_native_model_id: deepseek/deepseek-v4-pro^*
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

4.4e-8^*

Scope and conditions

native_context

provider: deepseek^*
mode: chat^*
full_native_model_id: deepseek-v4-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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

2.2e-8^*

input_cost_per_token

6.6e-7^*

output_cost_per_token

1.98e-6^*

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-pro^*
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

2.2e-8^*

input_cost_per_token

6.6e-7^*

output_cost_per_token

1.98e-6^*

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-pro^*
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

3.96e-6^*

Scope and conditions

native_context

provider: deepseek^*
mode: chat^*
full_native_model_id: deepseek/deepseek-v4-pro^*
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

3.96e-6^*

Scope and conditions

native_context

provider: deepseek^*
mode: chat^*
full_native_model_id: deepseek-v4-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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-pro^*
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: deepseek^*
mode: chat^*
full_native_model_id: deepseek-v4-pro^*
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: deepseek^*
mode: chat^*
full_native_model_id: deepseek/deepseek-v4-pro^*
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