impulse

Codestral 2501

API id codestral-2501
A newer model in this line is out: Codestral 2508, released 1 Aug 2025.
Azure AI Foundry retires it on 15 Feb 2027 (in 89 days). 1 host keeps serving it.
Input / 1M
$0.20
at Vertex AI
Output / 1M
$0.60
at Vertex AI
Context window
128K
tokens
Max output
128K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.20$0.60

What it costs a month

At Vertex AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$105
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$118
  • Coding agent1,000 requests a day, 40K in / 2K out$276
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$624
Use your own numbers

Where to run it

2 hosts serve Codestral 2501. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
codestral-2501
$0.20 / $0.60
Codestral-2501
$0.30 / $0.90
+50% vs headline
Retires 15 Feb 2027

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 Vertex AI.

Smaller Mistral AI models

  • Magistral Small
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    13% less
  • Mistral Vibe Cli Fast
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    13% less
  • Zai Glm 5.3 Flash
    Mistral AI · on Mistral AI
    $0.15 / $0.50
    Has every key capability
    21% less

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    33% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    33% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    13% less

Open-weight picks

  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    13% less
  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    16% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    40% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    47% less

Model line

Newer and older versions, at each lab's own price.

  1. Aug 2025Codestral 2508Latest$0.30 / $0.90
  2. UndatedCodestral 2501This page$0.20 / $0.60
  3. UndatedCodestral 2405Not listed
  4. UndatedCodestral 2$0.30 / $0.90

Call it

Using Vertex AI's API.

Python
from litellm import completion

response = completion(
    model="vertex_ai/codestral-2501",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Codestral 2501 cost?

On Vertex AI, Codestral 2501 costs $0.20 per million input tokens and $0.60 per million output tokens.

Which APIs offer Codestral 2501?

Codestral 2501 runs on 2 APIs: Vertex AI and Azure AI Foundry.

What is Codestral 2501's context window?

128K tokens, with up to 128K tokens in one reply.

Is Codestral 2501 being retired?

Azure AI Foundry retires it on 15 Feb 2027. 1 host keeps serving it.

Is there a newer version of Codestral 2501?

Yes. Codestral 2508 is the newest model in this line, released on 1 Aug 2025.

What are cheaper alternatives to Codestral 2501?

Models that cost less and keep most of what it can do: Magistral Small on Mistral AI (13% less), Claude Haiku 5.5 on Anthropic (33% less), GPT-6 Luna on OpenAI (33% less) and Mistral Small 2603 on Mistral AI (13% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Codestral 2501's API model id?

Use codestral-2501 with Vertex AI. Other hosts use their own ids: Codestral-2501 on Azure AI Foundry.

Sources

Raw catalog entry for codestral-2501 on Vertex AI
{
  "input_cost_per_token": 2e-7,
  "litellm_provider": "vertex_ai-mistral_models",
  "max_input_tokens": 128000,
  "max_output_tokens": 128000,
  "mode": "chat",
  "output_cost_per_token": 6e-7,
  "supports_function_calling": true,
  "supports_tool_choice": true
}