跳转到主内容
AIpricly

Mistralai · 发布于 2025-01-30 · text model

Mistral Small 3

跳转到 OpenRouter · 推荐链接 · 查看披露 →

输入价格$0.05/百万 tokens
输出价格$0.08/百万 tokens
上下文33Ktokens
P50 延迟—s首字延迟
吞吐量tok/s

完整定价详情

全部价格按美元 / 百万 token 计 · 所有隐性成本已揭示
Pricing tierInputOutputNotes
Standard
Pay-as-you-go API rate card
$0.05$0.08Default if no headers set
With prompt caching
Cached read · cache write
$0.01−90%$0.08Cache writes priced at standard input ($0.05); cached reads 90% off. Requires cache_control header.
Batch API (50% off)
24h SLA, async
$0.02−50%$0.04−50%Send up to 50K requests in one batch; results within 24h
Image input (vision)
Per image, low/high detail differ
$0.05 + image fee$0.08$0.50 per 1024×1024 image at high detail; low detail ~$0.10
Reasoning tokens
Hidden chain-of-thought tokens
$0.05$0.08 × ~3-8When using reasoning.effort: high, output tokens include hidden reasoning. Real cost can be 3-8× headline output.
Structured output
JSON mode + schema
$0.05$0.08No extra cost; first call may be slower (~2x latency) due to schema compilation

能力

Vision (image understanding)Function callingStructured output (JSON schema)Reasoning modeMultilingual (32+ langs)Batch APIAudio I/OFine-tuning

常见场景月度费用

默认用量假设

考虑这些替代方案

同厂商更多模型:Mistralai