impulse

Mistral Saba 24B

API id mistral-saba-24b
Input / 1M
$0.79
at Vercel AI Gateway
Output / 1M
$0.79
at Vercel AI Gateway
Context window
33K
tokens
Max output
33K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Vercel AI Gateway, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.79$0.79

What it costs a month

At Vercel AI Gateway list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$296
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$408
  • Coding agent1,000 requests a day, 40K in / 2K out$995
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,086
Use your own numbers

Where to run it

1 host serve Mistral Saba 24B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
mistral-saba-24b
$0.79 / $0.79

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Vercel AI Gateway.

Smaller Mistral AI models

  • Mistral Large
    Mistral AI · on Mistral AI
    $0.50 / $1.50
    Has every key capability
    5% less
  • Codestral 2508
    Mistral AI · on Mistral AI
    $0.30 / $0.90
    Has every key capability
    43% less
  • Codestral
    Mistral AI · on Mistral AI
    $0.30 / $0.90
    Has every key capability
    43% less

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    41% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    75% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    75% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    67% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    13% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    19% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    34% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    39% less

Call it

Using Vercel AI Gateway's API.

Python
from litellm import completion

response = completion(
    model="vercel_ai_gateway/mistral-saba-24b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Mistral Saba 24B cost?

On Vercel AI Gateway, Mistral Saba 24B costs $0.79 per million input tokens and $0.79 per million output tokens.

Which APIs offer Mistral Saba 24B?

Mistral Saba 24B runs on 1 API: Vercel AI Gateway.

What is Mistral Saba 24B's context window?

33K tokens, with up to 33K tokens in one reply.

Is Mistral Saba 24B being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Mistral Saba 24B?

Models that cost less and keep most of what it can do: Mistral Large on Mistral AI (5% less), GPT-5.4 Nano on OpenAI (41% less), Claude Haiku 5.5 on Anthropic (75% less) and Kimi K2.7 Code on CLF AI Gateway (13% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Mistral Saba 24B's API model id?

Use mistral-saba-24b with Vercel AI Gateway.

Sources

Raw catalog entry for mistral-saba-24b on Vercel AI Gateway
{
  "input_cost_per_token": 7.9e-7,
  "litellm_provider": "vercel_ai_gateway",
  "max_input_tokens": 32768,
  "max_output_tokens": 32768,
  "mode": "chat",
  "output_cost_per_token": 7.9e-7
}