impulse

Codestral Embed 2505

Embedding
API id codestral-embed-2505
Input / 1M
$0.15
at Mistral AI
Output / 1M
-
at Mistral AI
Context window
8K
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.15
Cached input
90% off input
$0.015

What it costs a month

At Mistral AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$32.85
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$39.60
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$66.60
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$360
Use your own numbers

Where to run it

1 host serve Codestral Embed 2505. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Mistral AILab API
codestral-embed-2505
$0.15 / -

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
Embeddings

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 Mistral AI.

Smaller Mistral AI models

  • Mistral Embed
    Mistral AI · on Mistral AI
    $0.10 / -
    Has every key capability
    33% less
  • Mistral Embed 2312
    Mistral AI · on Mistral AI
    $0.10 / -
    Has every key capability
    33% less

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

Call it

Using Mistral AI's API.

Python
from litellm import completion

response = completion(
    model="mistral/codestral-embed-2505",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Codestral Embed 2505 cost?

On Mistral AI, Codestral Embed 2505 costs $0.15 per million input tokens. Cached input costs $0.015 per million tokens.

Which APIs offer Codestral Embed 2505?

Codestral Embed 2505 runs on 1 API: Mistral AI.

What is Codestral Embed 2505's context window?

8K tokens.

Is Codestral Embed 2505 being retired?

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

What are cheaper alternatives to Codestral Embed 2505?

Models that cost less and keep most of what it can do: Mistral Embed on Mistral AI (33% less) and Snowflake Arctic Embed L V2.0 on Snowflake (53% less).

What is Codestral Embed 2505's API model id?

Use codestral-embed-2505 with Mistral AI.

Sources

Raw catalog entry for codestral-embed-2505 on Mistral AI
{
  "cache_read_input_token_cost": 1.5e-8,
  "input_cost_per_token": 1.5e-7,
  "litellm_provider": "mistral",
  "max_input_tokens": 8192,
  "mode": "embedding"
}