Saba API Pricing 2026

Compare pricing, benchmarks, and providers for Saba. Find the best value for your use case.

Best LLMs for OpenClaw— Vote for which model works best with OpenClaw

112 out of our 301 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Last updated: February 15, 2026 at 08:07 AM

Overview

Saba was released on February 17, 2025. Pricing starts at $0.200 per million input tokens and $0.600 per million output tokens. The model supports a context window of up to 33K tokens. API access is available through Mistral AI.

Context Window

33K

tokens

Pricing

Input$0.200

Output$0.600

per 1M tokens

Speed

Output-

TTFT-

median latency

Capabilities

Text only

Pricing Comparison

Compare Saba with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Provider	Model	Input $/M	Output $/M	Coding	MMLU	GPQA	Context	Actions
MI Mistral AI	Saba	$0.200	$0.600	—	61.1	42.4	32,768	Try
QW Qwen	QwQ 32B	$0.150	$0.400	63.1	76.4	59.3	32,768	Try
QW Qwen	Qwen2.5 VL 72B Instruct	$0.150	$0.600	—	—	—	32,768	Try
QW Qwen	Qwen3 Next 80B A3B Thinking	$0.150	$1.200	—	—	—	128,000	Try
O OpenAI	GPT-4o-mini	$0.150	$0.600	23.4	64.8	42.6	128,000	Try
TD Thedrummer	Rocinante 12B	$0.170	$0.430	—	27.5	5.5	32,768	Try
AR Arcee AI	Spotlight	$0.180	$0.180	—	—	—	131,072	Try
M Meta-llama	Llama Guard 4 12B	$0.180	$0.180	—	—	—	163,840	Try
DS Deepseek	DeepSeek V3 0324	$0.190	$0.870	35.9	75.2	55.7	163,840	Try
M Meituan	LongCat Flash Chat	$0.200	$0.800	—	—	—	131,072	Try
MI Mistral AI	Mistral 7B Instruct v0.2	$0.200	$0.200	—	19.1	3.5	32,768	Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Saba is available from multiple providers with different pricing and availability.

Providers

$0.200

Cheapest Input/M

$0.600

Cheapest Output/M

Mistral

Best Price

Provider Pricing

1 models

Provider	Input $/M	Output $/M	Uptime
Mistral Best Price	$0.200	$0.600	-

Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Saba perform? Vote based on your experience.

Cost vs. Quality

Compare Saba's benchmark performance against all models.

X-axis:

Y-axis:

Loading chart...

Saba

Other models

Detailed Benchmark Scores

Intelligence

12.1 (14th pct)

Coding

Math

MMLU Pro

61.1 (19th pct)

GPQA

42.4 (19th pct)

LiveCodeBench

AIME

13.0 (26th pct)

Aider

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Saba

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Saba directly in your browser.

Open Playground

Compare Saba

Frequently Asked Questions

All Mistral AI Models

See pricing for all Mistral AI models.

View all Mistral AI models →