MiniMax-M2.5
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsMiniMax-M2.5
AI model Released
- API mode
- Chat*
- Context window
- 204,800 tokens
- Maximum output
- 131,072 tokens
- Open weights
- Yes
Capability & preference
General capability · ECI
A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
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
MiniMax-M2.5
1,392.80 rating
Confidence interval: 1,381.32 – 1,404.29
2871 votes
- Category
- chinese
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,380.36 rating
Confidence interval: 1,373.95 – 1,386.78
11338 votes
- Category
- coding
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,330.04 rating
Confidence interval: 1,322.25 – 1,337.84
6662 votes
- Category
- creative_writing
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,379.71 rating
Confidence interval: 1,374.42 – 1,385.00
18757 votes
- Category
- english
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,326.22 rating
Confidence interval: 1,321.01 – 1,331.44
32309 votes
- Category
- exclude_ties
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,378.68 rating
Confidence interval: 1,368.61 – 1,388.75
3776 votes
- Category
- expert
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,363.07 rating
Confidence interval: 1,345.08 – 1,381.05
1298 votes
- Category
- french
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,360.41 rating
Confidence interval: 1,336.48 – 1,384.33
644 votes
- Category
- german
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,371.90 rating
Confidence interval: 1,367.12 – 1,376.68
26849 votes
- Category
- hard_prompts
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,383.47 rating
Confidence interval: 1,377.19 – 1,389.75
12178 votes
- Category
- hard_prompts_english
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,356.31 rating
Confidence interval: 1,349.20 – 1,363.42
8377 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,328.37 rating
Confidence interval: 1,321.29 – 1,335.44
8396 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,365.98 rating
Confidence interval: 1,355.03 – 1,376.94
3301 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,369.31 rating
Confidence interval: 1,361.76 – 1,376.86
7134 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,378.98 rating
Confidence interval: 1,366.52 – 1,391.43
2401 votes
- Category
- industry_mathematical
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,357.08 rating
Confidence interval: 1,345.94 – 1,368.21
3216 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,382.80 rating
Confidence interval: 1,377.24 – 1,388.36
16476 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,345.00 rating
Confidence interval: 1,338.47 – 1,351.52
10078 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,352.80 rating
Confidence interval: 1,346.93 – 1,358.68
13756 votes
- Category
- instruction_following
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,171.91 rating
Confidence interval: 1,134.16 – 1,209.65
369 votes
- Category
- japanese
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,232.96 rating
Confidence interval: 1,208.87 – 1,257.05
729 votes
- Category
- korean
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,365.63 rating
Confidence interval: 1,359.87 – 1,371.38
16251 votes
- Category
- longer_query
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,377.84 rating
Confidence interval: 1,366.04 – 1,389.65
2549 votes
- Category
- math
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,363.86 rating
Confidence interval: 1,356.46 – 1,371.27
7713 votes
- Category
- multi_turn
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,337.83 rating
Confidence interval: 1,333.01 – 1,342.64
24026 votes
- Category
- non_english
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,359.12 rating
Confidence interval: 1,355.25 – 1,362.99
42783 votes
- Category
- overall
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,333.79 rating
Confidence interval: 1,314.47 – 1,353.10
929 votes
- Category
- polish
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,358.70 rating
Confidence interval: 1,350.13 – 1,367.28
5228 votes
- Category
- russian
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
MiniMax-M2.5
1,353.13 rating
Confidence interval: 1,336.70 – 1,369.56
1481 votes
- Category
- spanish
- Evaluated configuration
- MiniMax-M2.5
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,392.84 rating
Confidence interval: 1,381.36 – 1,404.31
2875 votes
- Category
- chinese
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,380.38 rating
Confidence interval: 1,373.97 – 1,386.80
11358 votes
- Category
- coding
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,330.15 rating
Confidence interval: 1,322.35 – 1,337.95
6671 votes
- Category
- creative_writing
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,379.94 rating
Confidence interval: 1,374.65 – 1,385.23
18780 votes
- Category
- english
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,326.30 rating
Confidence interval: 1,321.09 – 1,331.51
32334 votes
- Category
- exclude_ties
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,378.00 rating
Confidence interval: 1,367.94 – 1,388.06
3787 votes
- Category
- expert
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,362.74 rating
Confidence interval: 1,344.75 – 1,380.73
1303 votes
- Category
- french
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,361.57 rating
Confidence interval: 1,337.59 – 1,385.54
643 votes
- Category
- german
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,372.02 rating
Confidence interval: 1,367.24 – 1,376.80
26877 votes
- Category
- hard_prompts
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,383.63 rating
Confidence interval: 1,377.35 – 1,389.91
12199 votes
- Category
- hard_prompts_english
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,356.36 rating
Confidence interval: 1,349.25 – 1,363.48
8383 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,328.58 rating
Confidence interval: 1,321.51 – 1,335.66
8401 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,365.74 rating
Confidence interval: 1,354.78 – 1,376.70
3304 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,369.10 rating
Confidence interval: 1,361.55 – 1,376.65
7139 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,378.14 rating
Confidence interval: 1,365.70 – 1,390.58
2412 votes
- Category
- industry_mathematical
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,357.51 rating
Confidence interval: 1,346.39 – 1,368.64
3222 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,382.91 rating
Confidence interval: 1,377.35 – 1,388.47
16498 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,345.21 rating
Confidence interval: 1,338.67 – 1,351.74
10072 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,352.87 rating
Confidence interval: 1,346.99 – 1,358.74
13776 votes
- Category
- instruction_following
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,171.07 rating
Confidence interval: 1,133.12 – 1,209.01
368 votes
- Category
- japanese
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,232.58 rating
Confidence interval: 1,208.47 – 1,256.69
730 votes
- Category
- korean
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,365.59 rating
Confidence interval: 1,359.84 – 1,371.35
16279 votes
- Category
- longer_query
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,377.67 rating
Confidence interval: 1,365.85 – 1,389.48
2556 votes
- Category
- math
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,363.54 rating
Confidence interval: 1,356.14 – 1,370.95
7726 votes
- Category
- multi_turn
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,337.75 rating
Confidence interval: 1,332.93 – 1,342.56
24035 votes
- Category
- non_english
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,359.12 rating
Confidence interval: 1,355.26 – 1,362.99
42815 votes
- Category
- overall
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,333.74 rating
Confidence interval: 1,314.41 – 1,353.07
929 votes
- Category
- polish
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,358.52 rating
Confidence interval: 1,349.94 – 1,367.10
5225 votes
- Category
- russian
- Evaluated configuration
- minimax-m2.5
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
MiniMax-M2.5
1,354.02 rating
Confidence interval: 1,337.54 – 1,370.50
1475 votes
- Category
- spanish
- Evaluated configuration
- minimax-m2.5
- 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.
MiniMax-M2.5
Capabilities
- Context window
- 204,800 tokens
- Maximum input
- Reported value 1: 1,000,000 tokens*Reported value 2: 196,000 tokens*
- Maximum output
- 131,072 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes*
- Open weights
- Yes
- API mode
- Chat*
- Image input
- No*
- Audio input
- No*
- Prompt caching
- Yes*
- System messages
- Yes*
- Tool choice
- Yes*
Input modalities
- text
Output modalities
- text
Processing & platform
- Architecture
- minimax_m2
System configuration
Detailed specifications
Specifications · 32 fields
- cache creation input token cost
- 3.75e-7*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- 3.0e-8*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- 3.0e-7*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- 3.0e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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 batches
- 1.5e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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 flex
- 1.5e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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 priority
- 5.25e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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
- minimax*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- bedrock_converse*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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
- 1,000,000*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- 196,000*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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
- 8,000*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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
- 8,192*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- 8,000*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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
- 1.2e-6*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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
- 1.2e-6*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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 batches
- 6.0e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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 flex
- 6.0e-7*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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 priority
- 2.1e-6*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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 audio input
- No*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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 prompt caching
- Yes*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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 system messages
- Yes*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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 system messages
- Yes*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- minimax*
- mode
- chat*
- full_native_model_id
- minimax/MiniMax-M2.5*
- 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
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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
- No*
Scope and conditions
- native_context
- provider
- bedrock_converse*
- mode
- chat*
- full_native_model_id
- minimax.minimax-m2.5*
- 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