Mistral AI Platform Serverless AI Token Pricing & API Rates
Verified RatesTier 4 European Datacenter (GDPR Compliant)Real-time verified rates (Updated 2026)
Mistral AI Platform Serverless AI Token Pricing (5 Models)
| Model | Category | Cold Start | Context | Input ($/1M or Unit) | Output / 1M Tokens | Speed | Actions |
|---|---|---|---|---|---|---|---|
| Ministral-8B-2410 | LLM | 0s Instant | 128K | $0.10 | $0.10 | 140 tps | API Docs |
| Mistral-Embed | EMBEDDING | 0s Instant | 8K | $0.10 | — | 200 tps | API Docs |
| Codestral-2501 | LLM | 0s Instant | 256K | $0.30 | $0.90 | 110 tps | API Docs |
| Mistral-Large-2-2411 | REASONING | 0s Instant | 128K | $2.00 | $6.00 | 90 tps | API Docs |
| Pixtral-Large-2411 | VISION | 0s Instant | 128K | $2.00 | $6.00 | 85 tps | API Docs |
Simulate monthly input and output token volume on Mistral AI Platform and compare your savings against OpenAI GPT-4o and Claude 3.5.
Open Mistral AI Platform Cost CalculatorCompare alternative inference platforms like Groq, Together AI, and DeepInfra on token latency, context windows, and pricing.
View Alternatives ComparisonMistral AI Platform Pricing FAQ & Cost Guide
How does serverless token billing work on Mistral AI Platform?
Mistral AI Platform meters exact input (prompt) and output (completion) tokens. You only pay for what your application generates. There is zero baseline server provisioning cost or ongoing hourly commitment.
Does Mistral AI Platform charge for stopped instances or idle storage?
No. Mistral AI Platform is a purely serverless platform. When your application receives zero traffic, your hourly billing is strictly $0.00. There are no persistent disk fees or stopped instance retention charges.
Are there hidden egress or bandwidth fees?
Egress on Mistral AI Platform is billed at Free / Included in Token Rate.
What payment methods does Mistral AI Platform accept?
Mistral AI Platform accepts standard credit card billing and enterprise invoicing with verified business accounts.