Skip to content
Vercel AI Gateway

Mistral/Mistral Saba 24b

Mistral/Mistral Saba 24b is available via Vercel AI Gateway with a 33K context window and up to 32,768 output tokens. Pricing: $0.7900/1M input tokens, $0.7900/1M output tokens.

Mistral/Mistral Saba 24b Pricing & Specifications

Input Price$0.79 per 1M tokens
Output Price$0.79 per 1M tokens
Context Window32,768 tokens (33K)
Max Output32,768 tokens
ProviderVercel AI Gateway

What is Mistral/Mistral Saba 24b?

Mistral/Mistral Saba 24b is a large language model by Vercel AI Gateway with a 33K context window and up to 32,768 output tokens. It costs $0.79 per 1M input tokens and $0.79 per 1M output tokens. Mistral/Mistral Saba 24b is available via Vercel AI Gateway with a 33K context window and up to 32,768 output tokens. Pricing: $0.7900/1M input tokens, $0.7900/1M output tokens.

Capabilities

text

Mistral/Mistral Saba 24b Cost Examples

Short prompt (500 tokens)

$0.000395

Medium prompt (2K tokens)

$0.00158

Long output (4K tokens)

$0.00316

Count tokens for Mistral/Mistral Saba 24b

Paste your prompt to see exact token counts and API cost estimates.

Open Token Counter

Similar Models to Mistral/Mistral Saba 24b

Vercel AI Gateway

Amazon/Nova Pro

$0.80/1M in 300K ctx

Vercel AI Gateway

Anthropic/Claude 3.5 Haiku

$0.80/1M in 200K ctx

Vercel AI Gateway

Morph/Morph V3 Fast

$0.80/1M in 33K ctx

Vercel AI Gateway

Deepseek/Deepseek R1 Distill Llama 70b

$0.75/1M in 131K ctx

Frequently Asked Questions

How much does Mistral/Mistral Saba 24b cost per token? +
Mistral/Mistral Saba 24b costs $0.79 per 1M input tokens and $0.79 per 1M output tokens. For a typical 1,000-token request with a 500-token response, that works out to roughly $0.001185.
What is the context window for Mistral/Mistral Saba 24b? +
Mistral/Mistral Saba 24b supports a context window of 32,768 tokens (33K). This determines the maximum combined length of your prompt and conversation history in a single API call.
What is the maximum output length for Mistral/Mistral Saba 24b? +
Mistral/Mistral Saba 24b can generate up to 32,768 tokens in a single response. If you need longer outputs, you can make multiple API calls and concatenate the results.
Is Mistral/Mistral Saba 24b good for coding tasks? +
Mistral/Mistral Saba 24b can handle basic coding tasks, but there are models specifically optimized for code generation that may perform better on complex programming problems.
Token Counter | Pricing Calculator | Model Comparison | All Vercel AI Gateway Models