Context Window
2,824
Input tokens
Full-context input ≈ $0.00
Model Cost Profile
Developer: mistralai· Tokenizer: Mistral · Instruct: mistral · Quantization: unknown
Canonical ID: mistralai/mistral-7b-instruct-v0.1
Pricing updated Apr 22, 2026
Live Pricing
Input: $0.1100
Output: $0.1900
Last synced Apr 22, 2026 · MMLU score via public benchmark data
Mistral 7B Instruct v0.1, developed by mistralai, is designed for applications requiring nuanced instruction-following capabilities, making it suitable for customer service automation and content generation. With a context window of 2824 tokens, this model allows for comprehensive interactions, enabling teams to maintain context over longer conversations or documents. The pricing structure, at $0.11 per 1 million tokens for input and $0.19 per 1 million tokens for output, offers cost-effective scalability for businesses looking to integrate advanced AI solutions.
Context Window
2,824
Input tokens
Full-context input ≈ $0.00
Max Output
—
Not specified
Input Price / 1M
$0.1100
Prompt tokens
Output Price / 1M
$0.1900
Completion tokens
Top Benchmark
24.5
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Mistral: Mistral 7B Instruct v0.1. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.1100
Current Output / 1M
$0.1900
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
99.7%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.1100 |
| Output (Completion) | $0.1900 |
Estimate monthly spend for Mistral: Mistral 7B Instruct v0.1 based on your workload.
Estimated Monthly Cost
$5.03
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.