Cohere: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Cohere for your use-case.
Most Intelligent
Command A+Intelligence Index
Total 3 models
Fastest
Command A+North Mini CodeCommand AOutput speed
Total 3 models
Lowest Price
Command A+North Mini CodeCommand ABlended price (per 1M tokens)
Total 3 models
Cohere offers 3 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For output speed, the fastest models are Command A+ (148 t/s), North Mini Code (70 t/s), and Command A (18 t/s).
- For latency, Command A (1.87s), Command A+ (14.00s), and North Mini Code (29.19s) offer the lowest time to first answer token.
- For pricing, Command A+ ($0.00), North Mini Code ($0.00), and Command A ($3.25) offer the lowest blended prices per 1M tokens.
- For context window size, Command A (288k), North Mini Code (256k), and Command A+ (200k) support the largest context windows on Cohere.
Intelligence Evaluations
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic real-world work tasks, Elo
Agentic interactive 3D experiences, Elo
Product and brand videos designed in code, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
Cache Behaviour
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Key definitions
Frequently Asked Questions
Common questions about Cohere
Cohere offers 3 models that we track: Command A+, North Mini Code, and Command A.
The most intelligent model available on Cohere is Command A+ with an Intelligence Index score of 6.
The fastest model on Cohere by output speed is Command A+ at 148.2 tokens per second.
The model with the lowest time to first answer token on Cohere is Command A at 1.87s. Lower latency means faster initial response time.
The most affordable model on Cohere by blended price is Command A+ at $0.00 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Cohere range from $0.00 per 1M tokens for Command A+ to $3.25 per 1M tokens for Command A.
2 of 3 models on Cohere support JSON mode for structured output.
Yes, all 3 models on Cohere support function calling (tool use).
Yes, Cohere offers 2 reasoning models: Command A+ and North Mini Code. Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 3 models on Cohere are open weight models.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Cohere, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.