Codestral
Last verified August 24, 2026 · Mistral pricing ↗$0.300/1M input · $0.900/1M output · 256K context · Mistral
Codestral costs $0.300 per 1M input tokens and $0.900 per 1M output tokens from Mistral, with a 256K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0008, or $8.10 per 10,000 requests. On that workload it is cheaper than 126 of the 172 other buyable models tracked here.
Count Tokens
—
Tokens
—
Input Cost
—
Output Cost
Estimate Monthly Cost
Monthly Cost Estimator
Quick:
<$0.0001/mo
Pick a preset above or enter custom usage
What Codestral Costs Per Request
At $0.300 per 1M input and $0.900 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0008 | $8.10 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.0029 | $29.40 |
| Coding-agent step | 30,000 / 2,000 | $0.011 | $108.00 |
Codestral vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| Codestral Mistral | $0.300 | $0.900 | 256K | $0.0029 |
| Mistral Small 4 Mistral | $0.150 | $0.600 | 256K | $0.0016 |
| Particle-1 Particle AI | $0.250 | $1.00 | 1.0M | $0.0026 |
| Llama 4 Maverick Meta | $0.270 | $0.850 | 1.0M | $0.0027 |
Alternatives to Codestral
Cheaper Alternative
Llama 4 Maverick
$0.270 in · $0.850 out · Meta
7% cheaper with same or larger context
Premium UpgradeParticle-1
$0.250 in · $1.00 out · Particle AI
Upgrade with 1049K context and 131K max output
Same ProviderMistral Small 4
$0.150 in · $0.600 out · Mistral
38% cheaper in Mistral ecosystem
Pricing Details
MistralCode-specialized model. API ID: codestral-2508. Estimated tokens.
Input / 1M tokens
$0.3
Output / 1M tokens
$0.9
Context Window
256K
Max Output
33K
Price History
No price change recorded since 2026-07-27, when this site started tracking this model.
Frequently Asked Questions
Common questions about Codestral pricing and usage
How much does Codestral cost?
Codestral costs $0.3 per 1 million input tokens and $0.9 per 1 million output tokens. This pricing is set by Mistral.
What tokenizer does Codestral use?
Codestral uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.
What is Codestral's context window?
Codestral supports a context window of 256K tokens (256,000 tokens). The maximum output length is 33K tokens.
How does Codestral compare to other models?
On an 8,000-token-in, 600-token-out RAG answer, Codestral costs $0.0029 per request. The nearest-priced alternatives cost: Mistral Small 4 (Mistral) $0.0016, Particle-1 (Particle AI) $0.0026, Llama 4 Maverick (Meta) $0.0027. The table above lists their full rates and context windows.
How do I count tokens for Codestral?
Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Codestral using the cl100k_base tokenizer.