Official API pricing and token cost benchmarks for Mistral Small 24b by Mistral. Currently billed at $0.050 / 1M in and $0.080 / 1M out. Mistral Small 24b is an ultra-fast, high-throughput model optimized for sub-second latency, high-concurrency streaming, real-time chatbots, and cost-effective bulk classification.
≈ $0.000050 per 1K tokens
1.6x higher than input
No prompt caching published
~44 standard pages
Standard per-token rate cards can feel abstract. Below is what calling Mistral Small 24b actually costs across standardized enterprise workloads and engineering production loops.
How context length and prefix caching impact your bill at scale, and engineering strategies to optimize token throughput.
$0.0016
1 full load of 32,768 tokens at standard input rates.
$0.0016
Prompt caching rate not published for this model.
1.6x
Output tokens cost 1.6x more than standard input tokens.
Because generation costs 1.6x more than input processing, using strict JSON schemas (Structured Outputs) to suppress conversational pleasantries directly lowers per-query cost by 40%–70%.
Keep prompt templates modular so system instructions can be re-used efficiently across parallel calls.
Current pricing specifications for Mistral Small 24b via Deepinfra.
| Specification / Metric | Published Rate / Limit |
|---|---|
| Standard Input TokensPrompt, system instructions, and tool schemas | $0.050 / 1M tokens |
| Standard Output TokensGenerated text, reasoning steps, and tool calls | $0.080 / 1M tokens |
| Prompt Cache ReadCache hit on pre-loaded static prompt prefixes | Standard input rate |
| Prompt Cache Write / CreationInitial write to ephemeral prompt cache memory | Standard input rate |
| Context Window SizeMaximum combined input tokens per single request | 32,768 tokens (~44 pages) |
| Max Generation LengthMaximum output tokens generated per completion | 32,768 tokens |
| Batch API PricingAsynchronous workloads completed within 24 hours | 50% off standard token rates |
Comparable fast-tier models with their current per-token rates and cost differential.
| Model | Provider | Context | Input / 1M | Output / 1M | Input Cost Delta |
|---|---|---|---|---|---|
| Gpt 5.4 Mini | OpenAI | 272K | $0.750 | $4.50 | +1400% higher |
| Gemini 3.5 Flash | 1.0M | $1.50 | $9.00 | +2900% higher |
Tier Positioning: Mistral Small 24b is an ultra-fast, high-throughput model optimized for sub-second latency, high-concurrency streaming, real-time chatbots, and cost-effective bulk classification. Compared to other fast-tier models, Mistral Small 24b offers a competitive rate card at $0.050 / 1M input and $0.080 / 1M output tokens.
Technical pricing details, caching rules, and budgeting considerations.
Mistral Small 24b costs $0.050 per 1 million input tokens and $0.080 per 1 million output tokens. If prompt caching is active, cache reads cost standard rates per 1M tokens.
Yes. Most major providers (including OpenAI, Anthropic, and Google) offer a 50% discount on standard token pricing for asynchronous Batch API jobs completed within a 24-hour turnaround window.
Prompt caching rates are not published for this specific tier or are included within base token pricing. Structure your system prompts to remain concise to minimize raw input cost.
Use our interactive AI Cost Calculator to input your exact daily request volume, average prompt token count, completion length, and prompt cache hit ratio. It generates precise cost forecasts across all models simultaneously.
Simulate real-world token consumption, model mixtures, and prompt cache savings with the DevFlow AI Cost Calculator.
