Mistral AI

Saba

$0.20 per 1M input tokens and $0.60 per 1M output tokens · 33K context · tools, JSON.

Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026

$0.20
input / 1M tokens
$0.60
output / 1M tokens
$0.02
cached input / 1M
33K
context window
26K
max output
6.5
Artificial Analysis intelligence index

What Saba costs per month

Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.

WorkloadPer month
Customer chatbot
1,000 conversations a day, 8 turns each
$83.52
Document Q&A (RAG)
500 questions a day over retrieved documents
$20.88
Coding / tool-using agent
200 tasks a day, long tool-heavy contexts
$37.80
Content generation
30 long articles a day
$1.89
Classification / extraction
100,000 short items a day
$207

Price history

We started tracking Saba on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.

Where to run Saba: 3 providers

Mistral is the cheapest at $0.20 input / $0.60 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.

ProviderInput / 1MOutput / 1MContextUptimeNotes
Mistral$0.20$0.6033K100% —
Mistral$0.20$0.6033K100% —
Mistral$0.22$0.6633K— —

Cheaper alternatives to Saba

Models with the same tool calling, structured output for at least 20% less (3:1 input/output mix), most capable first.

Cheaper alternatives to Saba
Model Input / 1M Output / 1M Context Capabilities
Claude Haiku 5.5
Anthropic
$0.10 $0.50 1M visiontoolsreasoningJSON
GLM 5.3 Flash
Z.ai
$0.041 $0.12 1.05M visiontoolsreasoningJSONopen weights
Ling 3.1 Flash
inclusionAI
$0.075 $0.225 262K toolsreasoningJSON
GPT-6 Luna
OpenAI
$0.10 $0.50 1.05M visiontoolsreasoningJSON
MiMo-V2.6-Flash
Xiaomi
$0.14 $0.28 1.05M visionaudiotoolsreasoningJSONopen weights

How to pay less for Saba

For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $122 a month at list price without caching:

OptionPer monthYou save
Move to Claude Haiku 5.5 (similar capabilities)$58.56$63.84 (52%)
Use prompt caching (60% of input cached)$83.52$38.88 (32%)

Other workloads: cut-your-bill tool for Saba.

Specifications

Model IDmistralai/mistral-saba
Inputtext, file
Outputtext
Tool callingYes
Structured outputYes
Reasoning modeNo
Open weightsNo
Knowledge cutoff2024-09-30
ReleasedFeb 17, 2025

FAQ

How much does Saba cost?
$0.20 per million input tokens and $0.60 per million output tokens; cached input costs $0.02 per million. Prices as of Oct 21, 2026.
What is the context window of Saba?
33K tokens, with up to 26K output tokens per response.
Does Saba support images, tools and structured output?
Images as input: no. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: no.
What are cheaper alternatives to Saba?
Models with the same key capabilities for at least 20% less include Claude Haiku 5.5 ($0.10 / $0.50), GLM 5.3 Flash ($0.041 / $0.12), Ling 3.1 Flash ($0.075 / $0.225).

More from Mistral AI: all Mistral AI models · how we collect prices