CodestralPricing & API costs
Codestral model in Mistral's official model directory.
- Input
- $0.30
- Output
- $0.90
- Cached input
- $0.03
$5.25 for 10,000 short requests at 1K input + 250 output tokens each.
Official pricingContext window
Not published
Maximum output
Not published
Release date
Not published
API model ID
codestralModel overview
Understand the model before estimating your workload.
Use the model ID codestral through the provider's direct API. The prices and limits on this page apply to that specific listing, with source data checked on 2026-10-12.
Pricing
Rates are grouped by usage type and available tier.
Per 1M tokens
Input
$0.30
Cached input
$0.03
Output
$0.90
Batch pricing
Batch requests are charged at 50% of standard rates.
What does it cost in practice?
Three example workloads, calculated from this model’s token rates.
| Workload | Tokens / request | Per request | 10,000 requests |
|---|---|---|---|
| Short conversationA compact prompt with a brief answer. | 1,000 in / 250 out | $0.000525 | $5.25 |
| Document analysisA longer document with a focused summary or extraction. | 8,000 in / 750 out | $0.003075 | $30.75 |
| Code generationRepository context followed by a longer generated response. | 4,000 in / 2,000 out | $0.003 | $30.00 |
Where the short-conversation budget goes
Input $3.00 · Output $2.25 · 10,000 requests
$5.25
Planning estimates using the listed token rates, with no caching, retries, batch discount, or tool fees. These examples assume text usage; images, audio, video, and higher rate tiers can change your bill. Each agent step is a separate request.
With 50% of input tokens served from cache, the short-conversation example costs $3.90 per 10,000 requests, compared with $5.25 without cache hits. Cache-write fees are excluded.
Use your own workloadHow billing works
The details that turn a token rate into an actual bill.
Separate input from output
For Codestral, multiply input and output token counts by their respective rates, then divide by one million. Conversation history and retrieved context contribute to input usage each time they are sent.
Cache hits have their own rate
The listed cached-input price is $0.03 per million tokens. Reusing a prompt does not automatically qualify: use the provider's reported cached-token count, and account for any cache-write or storage charges.
Check discounts and rate tiers
Eligible batch requests use 50% of the standard token rate in this listing. Batch work is asynchronous; check supported endpoints and turnaround times. Review the provider's pricing terms for workload-specific conditions.
Account for the complete workflow
Retries, follow-up calls, and agent tool loops increase request counts. Search, storage, and other tool charges can be billed separately from model inference. Use actual API usage logs to calibrate a budget before scaling traffic.
Capabilities and limits
What the API supports and where limits apply.
- Provider
- Mistral
- Model type
- Text tokens
- Family
- mistral
- Access
- Direct API
- Modalities
- Text
- Context window
- Not published
- Max output
- Not published
- Released
- Not published
- Deprecation date
- Not announced
Compare API channels
Check the model ID, rate, and limit for each access route.
The same model can have a different ID, price, or output limit depending on how you access it. These are the channels currently tracked in this catalog; they are not a complete list of every hosting provider.
Text: $0.30 input · $0.03 cached input · $0.90 output / 1M tokens
Sources
Official pages and the date this information was checked.
- Last checked
- 2026-10-12
- Source links
- 3
Next step
Estimate costs with this model.
Recommended for
Frequently asked questions
Mistral pricing checked on 2026-10-12: Text: $0.30 input · $0.03 cached input · $0.90 output / 1M tokens. These rates apply to the listed API model ID.
A context window is not recorded for codestral. Check the linked model documentation for the current limit.
The recorded status is Active. Use the exact model ID codestral and confirm that your API account has access.
At 1,000 input and 250 output tokens per request, 10,000 requests cost an estimated $5.25 at the listed rates. This example has no cache hits, retries, batch discount, or tool fees. Tiered pricing and multimodal usage can change the total.
Cached input is listed at $0.03 per million tokens. Only tokens the provider recognizes as cache hits receive that rate. The listed batch rate is 50% of the standard rate for eligible requests. Check eligibility and cache-write charges in the pricing documentation.
Recent updates
Availability changed in the provider's model list.
View sourceAdded to the model directory.
View source