Codestral vs Grok Build 0.1: pricing compared
For a 30-step coding agent run, Codestral is 4.7x cheaper ($0.13 vs $0.60). Prices verified 2026-10-18.
| Codestral | Grok Build 0.1 | |
|---|---|---|
| Provider | Mistral AI | xAI |
| Input / 1M | $0.30 | $1.00 |
| Cached input / 1M | $0.03 | $0.20 |
| Output / 1M | $0.90 | $2.00 |
| Batch discount | 50% | — |
| Context window | 128K | 256K |
| Long-context tier | none | above 200K |
Cost on real workloads
| Workload | Codestral | Grok Build 0.1 |
|---|---|---|
| 10,000 chatbot replies 2,000 input + 400 output tokens each, 50% of the prompt cached | $6.90 | $20.00 |
| One 30-step coding agent run 12K system + tools prompt, 1K output and 3K tool result per step, caching on | $0.13 | $0.60 |
| 1M documents classified (batch) 600 input + 20 output tokens each, batch API where available | $99.00 | $640 |
Price is only half the decision: a cheaper model that needs more steps or retries can cost more per finished task. Run your own numbers in the calculator (both models pinned), or see how both rank in the use-case guides.
FAQ
Is Codestral cheaper than Grok Build 0.1?
For a typical 30-step coding agent run with caching, Codestral costs $0.13 and Grok Build 0.1 costs $0.60, so Codestral is 4.7x cheaper. Per 1M tokens, Codestral is $0.30 / $0.90 and Grok Build 0.1 is $1.00 / $2.00.
Which has the bigger context window?
Codestral: 128,000 tokens. Grok Build 0.1: 256,000 tokens.