VERIFIED PRICECODE AGENT256KTEXT MODELNO CACHE SKU
Devstral 2 API Pricing
Devstral 2 is Mistral's frontier code-agent model at $0.40/$2.00 per million tokens. $0.4/M input, $2/M output. The official card highlights software-engineering agent use and 256K context.
Input - per 1M tokens
$0.40/M
Source Mistral active
Output - per 1M tokens
$2.00/M
Use for cost checks active
Cached input
$0.40/M
Cache no separate SKU not listed
Effective - agentic blend
$0.53/M
92/8 split - 82% cache
§ 01 / TERMINAL
Run the numbers.
Calculator pre-loaded with Devstral 2 rates. Tweak spend, output mix, or cache hit rate to compare this model with nearby alternatives.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
AGENT LOOP
Repo-wide bug fix
$0.046/task
LONG DOC
Reading 100-page contracts
$0.086/doc
RAG SUPPORT
Support agent ticket triage
$0.004/ticket
ASSISTANT TURN
Research planning turn
$0.009/turn
§ 03 / TOKENIZER
Paste text. See tokens. See cost.
Calibrated · measured on the vendor's tokenizer · 2026-06-10 Auto-counts as you type
Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (mistralai/Mistral-Nemo-Instruct-2407, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.
Characters 256
Words 39
Tokens (estimated) 50 tokens
Cost as input · uncached $0.000020 USD
Cost as output · uncached $0.000100 USD
Cost as cached input $0.000020 USD
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Devstral 2 | $0.40 cache $0.40 | $2.00 | $0.53 current page | 256K | Coding and software agents |
| Mistral Large 3 | $0.50 cache $0.50 | $1.50 | $0.58 pricier | 256K | Open-weight multimodal work |
| Mistral Small 4 | $0.15 cache $0.15 | $0.60 | $0.19 cheaper | 256K | Low-cost Mistral workloads |
| Mistral Medium 3.5 | $1.50 cache $1.50 | $7.50 | $1.98 pricier | 256K | Agentic and coding workloads |
| GPT-5.4 mini | $0.75 cache $0.07 | $4.50 | $0.54 pricier | 400K | Open-weight multimodal work |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $1.92 pricier | 1M | Open-weight multimodal work |
By comparison
Frequently asked.
Short answers for teams checking Devstral 2 pricing, status, and migration choices.
Q · 01 Is Devstral 2 still available? +
Devstral 2 is listed as active/current in the pricing snapshot and was checked against the vendor page used for this entry.
Q · 02 How much does Devstral 2 cost? +
Devstral 2 is listed at $0.4/M input and $2/M output.
Q · 03 Is cached-input pricing included? +
No separate cached-input SKU is listed for this entry, so the calculator treats cached input as undiscounted.
Q · 04 What should teams compare it against? +
Use the shelf to compare nearby current models. Snapshot replacement:
current same-provider models.Q · 05 Why keep this page? +
These pages preserve live price checks, preview economics, and migration context in one consistent calculator format.