Cohere: Models Intelligence, Performance & Price

Cohere
Cohere

Analysis of Cohere's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Cohere for your use-case.

Most Intelligent

Updated
#1
Command A+
Command A+
37
#2
North Mini Code
North Mini Code
28
#3
Command A
Command A
13

Intelligence index

Total 3 models

Fastest

#1
Command A+
Command A+
198 t/s
#2
North Mini Code
North Mini Code
184 t/s
#3
Command A
Command A
70 t/s

Output speed

Total 3 models

Lowest Price

#1
Command A
Command A
$3.25

Blended price (per 1M tokens)

Total 3 models

Indicates a reasoning model

Cohere offers 3 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.

  • For intelligence, the top models on Cohere are Command A+ (37), North Mini Code (28), Command A (13).
  • For output speed, the fastest models are Command A+ (198 t/s), North Mini Code (184 t/s), Command A (70 t/s).
  • For latency, North Mini Code (0.30s), Command A+ (0.39s), Command A (1.57s) offer the lowest time to first token.
  • For context window size, Command A (288k), North Mini Code (256k), Command A+ (200k) support the largest context windows on Cohere.

Highlights

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M tokens (blended) · Lower is better

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index · Higher is better

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2Updated

Agentic real-world work tasks, (Elo-500)/2000

No data available
Terminal-Bench v2.1New

Agentic coding & terminal use

No data available
𝜏³-BankingNew

Agentic tool use

No data available
AA-LCR

Long context reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

SciCode

Coding

IFBench

Instruction following

CritPt

Physics reasoning

APEX-Agents-AA

Long-horizon agentic tasks

No data available
ITBench-AA

Kubernetes incident root-cause analysis

No data available
MMMU-Pro

Visual reasoning

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence vs. Price

Blended at 7:2:1 (cache-input-output) · Artificial Analysis Intelligence Index · USD per 1M tokens (blended)
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Context Window

Context Window

Context window: tokens limit · Higher is better

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

JSON Mode & Function Calling

Function (Tool) Calling & JSON Mode

ModelsFunction callingJSON Mode
Command A+, Cohere logoCommand A+, Cohere
North Mini Code, Cohere logoNorth Mini Code, Cohere
Command A, Cohere logoCommand A, Cohere

Indicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.

Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.

Pricing

Intelligence vs. Price

Blended at 7:2:1 (cache-input-output) · Artificial Analysis Intelligence Index · USD per 1M tokens (blended)
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Performance Summary

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended) · 10,000 input tokens
Most attractive quadrant
Cohere

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better · 10,000 input tokens

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token

Seconds to first token received · Lower is better

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

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

End-to-end response time: end-to-end seconds to output 500 tokens · USD per 1M tokens (blended)
Most attractive quadrant
Cohere

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Key definitions

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.

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 37.

The fastest model on Cohere by output speed is Command A+ at 197.6 tokens per second.

The model with the lowest time to first token on Cohere is North Mini Code at 0.30s. Lower latency means faster initial response time.

The most affordable model on Cohere by blended price is Command A at $3.25 per 1M tokens (7:2:1 cache hit/input/output ratio).

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.