As of August 20, 2026, Command R+ is 58% cheaper per million tokens than Composer 2. Command R+ is $0.25 / $1.00 per million input/output tokens versus Composer 2 at $0.50 / $2.50. Sources: https://anotherwrapper.com/tools/llm-pricing and https://cursor.com/docs/models/cursor-composer-2
Sources: AnotherWrapper LLM pricing (https://anotherwrapper.com/tools/llm-pricing); Cursor pricing (https://cursor.com/docs/models/cursor-composer-2)
Command R+
Cohere
Input
$0.25
Output
$1.00
Composer 2
Cursor
Input
$0.50
Output
$2.50
Token pricing, specs, and benchmarks side by side
Command R+Composer 2Verdict
Both models are closely matched on benchmarks. Command R+ has the pricing advantage, making it the better value unless Composer 2's specific capabilities are critical to your workflow.
As of August 20, 2026, Command R+ is 58% cheaper on blended LLM API pricing. Command R+ costs $0.25 per million input tokens and $1.00 per million output tokens ($1.25 blended 1M-in + 1M-out). Composer 2 costs $0.50 / $2.50 per million tokens ($3.00 blended). Sources: https://anotherwrapper.com/tools/llm-pricing and https://cursor.com/docs/models/cursor-composer-2. The cheapest LLM for your app still depends on how many output tokens you generate.
Command R+ Cohere API pricing is $0.25 input and $1.00 output per million tokens via Cohere. Composer 2 Cursor API pricing is $0.50 input and $2.50 output per million tokens via Cursor. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
Neither Command R+ nor Composer 2 has a published SWE-bench or LiveCodeBench score on this page yet. Use the comparison table for the evals that do exist.
Command R+ supports a 128K token context window, while Composer 2 supports 200K tokens. Composer 2 offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
Shared benchmark scores for Command R+ and Composer 2 are still limited. Check the comparison table for the evals each model has published. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.
Both Command R+ and Composer 2 are production API models. For cost-sensitive production traffic, Command R+ has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.
Yes. Call Command R+ through Cohere and Composer 2 through Cursor with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.
List rates are the latest published Cohere API pricing and Cursor API pricing, quoted per million tokens. Official rate sheets: https://anotherwrapper.com/tools/llm-pricing and https://cursor.com/docs/models/cursor-composer-2. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.
Command R+ supports up to 128K output tokens per request, while Composer 2 supports up to an unspecified number of output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
Command R+ has a measured throughput of approximately 59 tokens/second. Throughput data for Composer 2 is not yet available. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Command R+ or Composer 2 from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
This comparison covers API pricing, context window, throughput, and benchmark scores. Command R+ costs $0.25/M input and $1.00/M output. Composer 2 costs $0.50/M input and $2.50/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
280 models across 33 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
