Mistral Large 3
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsMistral Large 3
AI model Released
- API mode
- Chat*
- Context window
- 262,144 tokens
- Maximum output
- 262,144 tokens
- Open weights
- Yes
Capability & preference
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 · intelligence15.90*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
Mistral Large 3
1,446.49 rating
Confidence interval: 1,438.86 – 1,454.12
6747 votes
- Category
- chinese
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Mistral Large 3
1,448.70 rating
Confidence interval: 1,444.02 – 1,453.37
22209 votes
- Category
- coding
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Mistral Large 3
1,386.49 rating
Confidence interval: 1,381.07 – 1,391.91
15993 votes
- Category
- creative_writing
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Mistral Large 3
1,439.43 rating
Confidence interval: 1,435.57 – 1,443.28
36501 votes
- Category
- english
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Mistral Large 3
1,420.25 rating
Confidence interval: 1,416.43 – 1,424.08
64691 votes
- Category
- exclude_ties
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Mistral Large 3
1,421.26 rating
Confidence interval: 1,414.32 – 1,428.20
8478 votes
- Category
- expert
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Mistral Large 3
1,454.88 rating
Confidence interval: 1,441.87 – 1,467.90
2598 votes
- Category
- french
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Mistral Large 3
1,439.18 rating
Confidence interval: 1,422.61 – 1,455.74
1446 votes
- Category
- german
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Mistral Large 3
1,430.24 rating
Confidence interval: 1,426.77 – 1,433.70
54049 votes
- Category
- hard_prompts
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Mistral Large 3
1,437.29 rating
Confidence interval: 1,432.64 – 1,441.95
22376 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Mistral Large 3
1,417.61 rating
Confidence interval: 1,412.43 – 1,422.80
16327 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Mistral Large 3
1,386.95 rating
Confidence interval: 1,381.99 – 1,391.90
19669 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Mistral Large 3
1,440.33 rating
Confidence interval: 1,432.74 – 1,447.92
6699 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Mistral Large 3
1,445.42 rating
Confidence interval: 1,440.05 – 1,450.80
14433 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Mistral Large 3
1,423.82 rating
Confidence interval: 1,414.75 – 1,432.89
4728 votes
- Category
- industry_mathematical
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Mistral Large 3
1,446.49 rating
Confidence interval: 1,438.51 – 1,454.48
6181 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Mistral Large 3
1,450.69 rating
Confidence interval: 1,446.65 – 1,454.73
32925 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Mistral Large 3
1,397.32 rating
Confidence interval: 1,392.61 – 1,402.02
22190 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Mistral Large 3
1,404.22 rating
Confidence interval: 1,399.96 – 1,408.48
28681 votes
- Category
- instruction_following
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Mistral Large 3
1,395.71 rating
Confidence interval: 1,375.77 – 1,415.66
1027 votes
- Category
- japanese
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Mistral Large 3
1,383.69 rating
Confidence interval: 1,367.28 – 1,400.10
1491 votes
- Category
- korean
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Mistral Large 3
1,414.43 rating
Confidence interval: 1,410.23 – 1,418.63
33745 votes
- Category
- longer_query
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Mistral Large 3
1,414.93 rating
Confidence interval: 1,406.32 – 1,423.54
5038 votes
- Category
- math
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Mistral Large 3
1,430.13 rating
Confidence interval: 1,424.71 – 1,435.56
14803 votes
- Category
- multi_turn
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Mistral Large 3
1,413.81 rating
Confidence interval: 1,410.39 – 1,417.23
51811 votes
- Category
- non_english
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Mistral Large 3
1,428.28 rating
Confidence interval: 1,425.49 – 1,431.07
88325 votes
- Category
- overall
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Mistral Large 3
1,440.71 rating
Confidence interval: 1,427.26 – 1,454.16
1917 votes
- Category
- polish
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Mistral Large 3
1,410.42 rating
Confidence interval: 1,404.34 – 1,416.50
10719 votes
- Category
- russian
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Mistral Large 3
1,438.83 rating
Confidence interval: 1,426.55 – 1,451.11
2682 votes
- Category
- spanish
- Evaluated configuration
- Mistral Large 3
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Mistral Large 3
1,447.08 rating
Confidence interval: 1,439.30 – 1,454.86
6405 votes
- Category
- chinese
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Mistral Large 3
1,448.53 rating
Confidence interval: 1,443.79 – 1,453.26
21177 votes
- Category
- coding
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Mistral Large 3
1,385.98 rating
Confidence interval: 1,380.46 – 1,391.49
15096 votes
- Category
- creative_writing
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Mistral Large 3
1,439.43 rating
Confidence interval: 1,435.53 – 1,443.33
34943 votes
- Category
- english
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Mistral Large 3
1,420.09 rating
Confidence interval: 1,416.22 – 1,423.97
61597 votes
- Category
- exclude_ties
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Mistral Large 3
1,420.86 rating
Confidence interval: 1,413.79 – 1,427.92
8058 votes
- Category
- expert
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Mistral Large 3
1,455.89 rating
Confidence interval: 1,442.49 – 1,469.29
2420 votes
- Category
- french
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Mistral Large 3
1,436.16 rating
Confidence interval: 1,419.27 – 1,453.05
1375 votes
- Category
- german
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Mistral Large 3
1,429.84 rating
Confidence interval: 1,426.33 – 1,433.35
51413 votes
- Category
- hard_prompts
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Mistral Large 3
1,437.05 rating
Confidence interval: 1,432.34 – 1,441.77
21373 votes
- Category
- hard_prompts_english
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Mistral Large 3
1,417.63 rating
Confidence interval: 1,412.38 – 1,422.89
15657 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Mistral Large 3
1,386.22 rating
Confidence interval: 1,381.19 – 1,391.25
18604 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Mistral Large 3
1,439.92 rating
Confidence interval: 1,432.19 – 1,447.64
6416 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Mistral Large 3
1,445.21 rating
Confidence interval: 1,439.75 – 1,450.67
13768 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Mistral Large 3
1,423.93 rating
Confidence interval: 1,414.64 – 1,433.22
4449 votes
- Category
- industry_mathematical
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Mistral Large 3
1,446.32 rating
Confidence interval: 1,438.20 – 1,454.44
5898 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Mistral Large 3
1,450.49 rating
Confidence interval: 1,446.39 – 1,454.58
31410 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Mistral Large 3
1,396.54 rating
Confidence interval: 1,391.76 – 1,401.31
21026 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Mistral Large 3
1,403.49 rating
Confidence interval: 1,399.17 – 1,407.80
27184 votes
- Category
- instruction_following
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Mistral Large 3
1,395.61 rating
Confidence interval: 1,374.76 – 1,416.46
934 votes
- Category
- japanese
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Mistral Large 3
1,384.46 rating
Confidence interval: 1,367.72 – 1,401.20
1435 votes
- Category
- korean
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Mistral Large 3
1,413.66 rating
Confidence interval: 1,409.40 – 1,417.91
32019 votes
- Category
- longer_query
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Mistral Large 3
1,414.74 rating
Confidence interval: 1,405.95 – 1,423.52
4788 votes
- Category
- math
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Mistral Large 3
1,429.79 rating
Confidence interval: 1,424.29 – 1,435.29
14126 votes
- Category
- multi_turn
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Mistral Large 3
1,413.61 rating
Confidence interval: 1,410.14 – 1,417.07
49252 votes
- Category
- non_english
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Mistral Large 3
1,428.16 rating
Confidence interval: 1,425.34 – 1,430.99
84205 votes
- Category
- overall
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Mistral Large 3
1,440.74 rating
Confidence interval: 1,427.14 – 1,454.35
1864 votes
- Category
- polish
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Mistral Large 3
1,411.45 rating
Confidence interval: 1,405.26 – 1,417.64
10153 votes
- Category
- russian
- Evaluated configuration
- mistral-large-3
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Mistral Large 3
1,437.81 rating
Confidence interval: 1,425.21 – 1,450.41
2537 votes
- Category
- spanish
- Evaluated configuration
- mistral-large-3
- 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.
Mistral Large 3
Mistral Large 3 / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| AWS BedrockMistral Large 3Standard Global cross-region | Input | USD | 0.5 / 1M tokens |
| Output | USD | 1.5 / 1M tokens |
Capabilities
- Context window
- 262,144 tokens
- Maximum input
- 262,144 tokens*
- Maximum output
- 262,144 tokens
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes*
- Open weights
- Yes
- Knowledge cutoff
- 2024-11
- API mode
- Chat*
- Declared context window
- 256K*
- Model type
- LLM (MoE)*
- Declared modalities
- Text → Text*
- Image input
- Yes*
- Tool choice
- Yes*
- Model license
- Apache 2.0
Input modalities
- text
- image
Output modalities
- text
System configuration
Detailed specifications
Specifications 1 · 16 fields
- api providers
- Mistral, 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
- Mistral AI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- context window
- 256K*
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
- Mistral AI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- developer
- Mistral AI*
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
- Mistral AI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- input price
- 2*
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
- Mistral AI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- intelligence
- 15.9*
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
- Mistral AI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- license
- Apache 2.0 (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
- Mistral AI*
- 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
- Mistral AI*
- 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
- Mistral AI*
- 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
- Mistral AI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- name
- Mistral Large 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
- Mistral AI*
- 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
- Mistral AI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- output price
- 6*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Mistral AI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- parameters
- 675B total / 41B 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
- Mistral AI*
- 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
- Mistral AI*
- 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
- Mistral AI*
- 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
- Mistral AI*
- price_unit
- Not reported*
- price_tiers
- Not reported*
Specifications 2 · 13 fields
- cache read input token cost
- 5.0e-8*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- 5.0e-7*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- mistral*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- 262,144*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- 262,144*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- 262,144*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per token
- 1.5e-6*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-large-3*
- 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