Which is cheaper, Composer 2 or Devstral Medium?
As of August 20, 2026, Devstral Medium is 20% cheaper on blended LLM API pricing. Devstral Medium costs $0.40 per million input tokens and $2.00 per million output tokens ($2.40 blended 1M-in + 1M-out). Composer 2 costs $0.50 / $2.50 per million tokens ($3.00 blended). Sources: https://cursor.com/docs/models/cursor-composer-2 and https://docs.mistral.ai/platform/pricing/. The cheapest LLM for your app still depends on how many output tokens you generate.
How much does Composer 2 vs Devstral Medium cost per million tokens?
Composer 2 Cursor API pricing is $0.50 input and $2.50 output per million tokens via Cursor. Devstral Medium Mistral API pricing is $0.40 input and $2.00 output per million tokens via Mistral AI. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
Which is better for coding, Composer 2 or Devstral Medium?
Devstral Medium has a published SWE-bench Verified score of 61.6%. Composer 2 does not have that eval on this page yet.
What is the context window for Composer 2 vs Devstral Medium?
Composer 2 supports a 200K token context window, while Devstral Medium supports 128K 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.
Which model performs better on benchmarks, Composer 2 or Devstral Medium?
Shared benchmark scores for Composer 2 and Devstral Medium 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.
Is Composer 2 or Devstral Medium better for production use?
Both Composer 2 and Devstral Medium are production API models. For cost-sensitive production traffic, Devstral Medium 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.
Can I switch between Composer 2 and Devstral Medium in my app?
Yes. Call Composer 2 through Cursor and Devstral Medium through Mistral AI 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.
How accurate is this Composer 2 vs Devstral Medium pricing data?
List rates are the latest published Cursor API pricing and Mistral API pricing, quoted per million tokens. Official rate sheets: https://cursor.com/docs/models/cursor-composer-2 and https://docs.mistral.ai/platform/pricing/. 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.
What is the output token limit for Composer 2 and Devstral Medium?
Composer 2 supports up to an unspecified number of output tokens per request, while Devstral Medium supports up to 128K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
Which model has better throughput, Composer 2 or Devstral Medium?
Devstral Medium has a measured throughput of approximately 137.1 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.
How do I switch the models in this Composer 2 vs Devstral Medium comparison?
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Composer 2 or Devstral Medium from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
