Context Window
131,072
Input tokens
Full-context input ≈ $0.05
Model Cost Profile
Developer: mistralai· Tokenizer: Mistral · Quantization: unknown
Canonical ID: mistralai/devstral-medium-2507
Pricing updated Apr 22, 2026
Live Pricing
Input: $0.4000
Output: $2.00
Last synced Apr 22, 2026 · MMLU score via public benchmark data
Mistral: Devstral Medium, developed by mistralai, offers a substantial context window of 131,072 tokens, making it suitable for applications requiring extensive data processing, such as document analysis and conversational AI. With an input price of $0.40 per 1 million tokens and an output price of $2.00 per 1 million tokens, teams can effectively manage budget considerations while scaling their projects. This model is particularly beneficial for enterprises needing to handle large volumes of text data efficiently, enabling more nuanced and context-aware interactions.
Context Window
131,072
Input tokens
Full-context input ≈ $0.05
Max Output
—
Not specified
Input Price / 1M
$0.4000
Prompt tokens
Output Price / 1M
$2.00
Completion tokens
Top Benchmark
70.8
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Mistral: Devstral Medium. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.4000
Current Output / 1M
$2.00
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.4000 |
| Output (Completion) | $2.00 |
| Cache Read | $0.0400 |
Estimate monthly spend for Mistral: Devstral Medium based on your workload.
Estimated Monthly Cost
$34
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.