Mistral Medium 3.5
Closed weights. No supported local deployment or GPU requirement is published.
GeekRadar / The comparison desk
COMPARE.
AI modelsMistral Medium 3.5
AI model Released
- API mode
- Chat*
- Context window
- 262,144 tokens
- Maximum output
- 209,715 tokens
- Open weights
- No
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
Recorded results
Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Arena text preference / chinesehuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,445.45 rating
Confidence interval: 1,421.92 – 1,468.98
613 votes
- Category
- chinese
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,460.09 rating
Confidence interval: 1,449.40 – 1,470.78
3296 votes
- Category
- coding
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,373.81 rating
Confidence interval: 1,360.16 – 1,387.46
2070 votes
- Category
- creative_writing
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,432.87 rating
Confidence interval: 1,424.45 – 1,441.29
5671 votes
- Category
- english
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,410.08 rating
Confidence interval: 1,401.82 – 1,418.34
8933 votes
- Category
- exclude_ties
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,431.51 rating
Confidence interval: 1,414.62 – 1,448.41
1210 votes
- Category
- expert
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,448.87 rating
Confidence interval: 1,419.03 – 1,478.70
449 votes
- Category
- french
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,453.31 rating
Confidence interval: 1,409.82 – 1,496.81
174 votes
- Category
- german
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,436.51 rating
Confidence interval: 1,428.87 – 1,444.16
7650 votes
- Category
- hard_prompts
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,445.17 rating
Confidence interval: 1,435.16 – 1,455.17
3862 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,426.09 rating
Confidence interval: 1,413.42 – 1,438.76
2262 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,381.70 rating
Confidence interval: 1,369.76 – 1,393.63
2690 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,437.03 rating
Confidence interval: 1,416.85 – 1,457.21
893 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,428.00 rating
Confidence interval: 1,414.37 – 1,441.63
1942 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,440.55 rating
Confidence interval: 1,417.67 – 1,463.43
649 votes
- Category
- industry_mathematical
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,409.14 rating
Confidence interval: 1,388.42 – 1,429.86
848 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,457.94 rating
Confidence interval: 1,448.78 – 1,467.09
4599 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,383.97 rating
Confidence interval: 1,372.73 – 1,395.21
2991 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,415.02 rating
Confidence interval: 1,405.07 – 1,424.96
3828 votes
- Category
- instruction_following
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,384.30 rating
Confidence interval: 1,340.76 – 1,427.84
187 votes
- Category
- korean
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,415.01 rating
Confidence interval: 1,406.00 – 1,424.01
5101 votes
- Category
- longer_query
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,432.30 rating
Confidence interval: 1,408.02 – 1,456.59
567 votes
- Category
- math
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,423.27 rating
Confidence interval: 1,409.34 – 1,437.20
1923 votes
- Category
- multi_turn
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,404.56 rating
Confidence interval: 1,396.44 – 1,412.68
6120 votes
- Category
- non_english
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,420.77 rating
Confidence interval: 1,414.40 – 1,427.14
11791 votes
- Category
- overall
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,429.63 rating
Confidence interval: 1,392.56 – 1,466.70
233 votes
- Category
- polish
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,396.20 rating
Confidence interval: 1,379.13 – 1,413.28
1236 votes
- Category
- russian
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1,410.79 rating
Confidence interval: 1,379.76 – 1,441.81
389 votes
- Category
- spanish
- Evaluated configuration
- Mistral Medium 3.5
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,444.02 rating
Confidence interval: 1,420.59 – 1,467.45
620 votes
- Category
- chinese
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,460.79 rating
Confidence interval: 1,450.10 – 1,471.49
3293 votes
- Category
- coding
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,373.89 rating
Confidence interval: 1,360.24 – 1,387.54
2073 votes
- Category
- creative_writing
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,433.20 rating
Confidence interval: 1,424.77 – 1,441.62
5651 votes
- Category
- english
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,410.39 rating
Confidence interval: 1,402.12 – 1,418.66
8927 votes
- Category
- exclude_ties
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,432.34 rating
Confidence interval: 1,415.42 – 1,449.26
1208 votes
- Category
- expert
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,448.79 rating
Confidence interval: 1,419.05 – 1,478.53
452 votes
- Category
- french
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,453.13 rating
Confidence interval: 1,409.58 – 1,496.68
174 votes
- Category
- german
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,436.67 rating
Confidence interval: 1,429.03 – 1,444.32
7648 votes
- Category
- hard_prompts
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,445.28 rating
Confidence interval: 1,435.26 – 1,455.30
3851 votes
- Category
- hard_prompts_english
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,426.25 rating
Confidence interval: 1,413.56 – 1,438.93
2257 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,382.14 rating
Confidence interval: 1,370.16 – 1,394.11
2681 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,437.99 rating
Confidence interval: 1,417.80 – 1,458.17
890 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,428.37 rating
Confidence interval: 1,414.73 – 1,442.00
1940 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,440.58 rating
Confidence interval: 1,417.75 – 1,463.40
652 votes
- Category
- industry_mathematical
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,408.34 rating
Confidence interval: 1,387.57 – 1,429.12
845 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,458.39 rating
Confidence interval: 1,449.23 – 1,467.56
4593 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,384.37 rating
Confidence interval: 1,373.13 – 1,395.61
2988 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,415.21 rating
Confidence interval: 1,405.27 – 1,425.15
3831 votes
- Category
- instruction_following
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,384.39 rating
Confidence interval: 1,340.89 – 1,427.89
189 votes
- Category
- korean
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,415.58 rating
Confidence interval: 1,406.58 – 1,424.59
5095 votes
- Category
- longer_query
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,431.17 rating
Confidence interval: 1,406.85 – 1,455.49
565 votes
- Category
- math
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,424.16 rating
Confidence interval: 1,410.23 – 1,438.09
1917 votes
- Category
- multi_turn
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,404.66 rating
Confidence interval: 1,396.54 – 1,412.78
6127 votes
- Category
- non_english
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,420.97 rating
Confidence interval: 1,414.59 – 1,427.34
11778 votes
- Category
- overall
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,429.70 rating
Confidence interval: 1,392.62 – 1,466.79
233 votes
- Category
- polish
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,394.75 rating
Confidence interval: 1,377.65 – 1,411.85
1235 votes
- Category
- russian
- Evaluated configuration
- mistral-medium-3.5
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1,410.77 rating
Confidence interval: 1,379.72 – 1,441.81
389 votes
- Category
- spanish
- Evaluated configuration
- mistral-medium-3.5
- 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 Medium 3.5
Capabilities
- Context window
- 262,144 tokens
- Maximum input
- 262,144 tokens*
- Maximum output
- 209,715 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes*
- Open weights
- No
- API mode
- Chat*
- Image input
- Yes*
- Tool choice
- Yes*
- Model license
- Modified MIT
Input modalities
- text
- image
Output modalities
- text
System configuration
Detailed specifications
Specifications · 30 fields
- cache read input token cost
- 1.5e-7*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3.5*
- 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
- 1.5e-7*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3-5*
- 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
- 1.5e-6*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3-5*
- 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
- 1.5e-6*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3.5*
- 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-medium-3-5*
- 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-medium-3.5*
- 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-medium-3-5*
- 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-medium-3.5*
- 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-medium-3.5*
- 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-medium-3-5*
- 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-medium-3.5*
- 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-medium-3-5*
- 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-medium-3.5*
- 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-medium-3-5*
- 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
- 7.5e-6*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3-5*
- 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
- 7.5e-6*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3.5*
- 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.*
- reasoning effort levels
- none*
- high*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3-5*
- 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.*
- reasoning effort levels
- none*
- high*
Scope and conditions
- native_context
- provider
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3.5*
- 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-medium-3.5*
- 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-medium-3-5*
- 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-medium-3.5*
- 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-medium-3-5*
- 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
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3-5*
- 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
- mistral*
- mode
- chat*
- full_native_model_id
- mistral/mistral-medium-3.5*
- 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-medium-3-5*
- 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-medium-3.5*
- 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-medium-3-5*
- 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-medium-3.5*
- 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-medium-3.5*
- 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-medium-3-5*
- 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