Mistral AI Model Pricing & Calculator Open-Weight / Self-Hostable

Mistral: Codestral 2508 API Cost Calculator

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

Interactive Monthly Spend Estimator

Adjust sliders to calculate your daily and monthly bill for Mistral: Codestral 2508.

Estimated Daily API Cost $0.00
Estimated Monthly API Cost (30 days) $0.00
24/7 Dedicated NVIDIA RTX 4090 (24GB VRAM) Self-Host Cost $280.80/mo

Official Token Pricing & Specs

Model ID mistralai/codestral-2508
Provider Mistral AI
Weight Availability Open-Weight (Downloadable GGUF / Safetensors)
Input Price (per 1M tokens) $0.30
Output Price (per 1M tokens) $0.90
Max Context Window 256,000 tokens
VRAM Needed (4-Bit Q4 / FP16) 14.3 GB / 48.4 GB โ†’
API vs. GPU Daily Break-Even ~19.5M tokens/day
Rent GPUs on Vast.ai (Save up to 70%) Deploy on RunPod (From $0.20/hr)
Cheapest RTX 4090 & H100 Rentals

Stop Overpaying for High-Volume AI Inference

Running Mistral: Codestral 2508 at scale? Deploy pre-configured vLLM or Ollama pods on dedicated H100, A100, or RTX 4090 GPUs by the second.

Rent GPUs on Vast.ai (Save up to 70%) โ†’

๐Ÿš€ Deploy & Run Commands (Ollama, vLLM & Cloud GPU Docker)

Recommended TP: 1x GPU

Copy and paste to run Mistral: Codestral 2508 locally or launch an OpenAI-compatible API server on a Cloud GPU pod:

1. Ollama (Local 4-Bit GGUF)
ollama run codestral:22b
2. vLLM (OpenAI-Compatible Production API)
vllm serve mistralai/Codestral-22B-v0.1 --max-model-len 32768 --tensor-parallel-size 1 --gpu-memory-utilization 0.92
3. Docker / Cloud GPU Pod (RunPod & Vast.ai)
docker run --gpus all -p 8000:8000 --ipc=host vllm/vllm-openai:latest --model mistralai/Codestral-22B-v0.1 --tensor-parallel-size 1
4. Local GPU Compatibility CLI Check (Detects nvidia-smi / Apple Silicon)
curl -sL https://stigla610.github.io/ai-cost-engine/tokenbench.py | python3 -
Launch vLLM / Ollama Template on RunPod โ†’ Rent Cheap GPUs on Vast.ai โ†’

Compare Mistral: Codestral 2508 With Other Popular Models