Skip to content
CostPerPrompt

Codestral 2508 API Pricing

Mistral · context window 256K · prices updated 2026-09-15

Input per 1M tokens
$0.3
Output per 1M tokens
$0.9
Cached input per 1M
$0.03
90% cheaper than fresh input

Where Codestral 2508 sits on price

At $0.9 per million output tokens, Codestral 2508 is a mid tier model — 2.3× cheaper than the median output price of $2.08, which puts it cheaper than 71% and pricier than 29% of the models we track. It sits 15th cheapest of the 25 Mistral models we track. Output is only 3.0× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.

Output tokens per $1
1,111,111
One full context fill
$0.0768
Cheaper than
71% of tracked models

Cached input is 90% cheaper. On an input-heavy workload you need roughly a 28% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.

What real workloads cost on Codestral 2508

These three workloads are the ones teams actually run on a mid-priced model — a $0.9/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. $0.0028 $41.40
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0014 $405
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0003 $8.55

Model your exact traffic in the API cost calculator — it preloads Codestral 2508 with caching and batch options.

Codestral 2508 price history

Codestral 2508's price has not moved since we began tracking it on Aug 2, 2026 — 44 days of stability in a market where 78 of the 334 models we track have repriced over the same period, including 7 of Mistral's own 25 models.

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

Codestral 2508 vs Qwen3.6 35B A3B

The closest-priced alternative from another vendor is Qwen3.6 35B A3B (Alibaba (Qwen)) — priced within a rounding error on output, with $0.2 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Qwen3.6 35B A3B pricing →

Cheaper alternatives

More Mistral models

Frequently asked questions

How much does the Codestral 2508 API cost?

Codestral 2508 costs $0.3 per million input tokens and $0.9 per million output tokens, with cached input at $0.03 per million (90% cheaper). That works out to roughly 1,111,111 output tokens per dollar.

What does the support chatbot workload cost on Codestral 2508?

Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0028 per request and $41.40 per month on Codestral 2508. Conversation history re-sent each turn — the classic prompt-caching win.

What does it cost to fill Codestral 2508's 256K context window?

Sending 256K of input in a single request costs $0.0768 at $0.3 per million tokens — before any output. With prompt caching that same fill drops to about $0.0077 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

Is Codestral 2508 worth the price?

Codestral 2508 sits in the middle of the market (15 of 25 by price within Mistral). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.