Codestral 2
codestral-2Pricing
List prices at Vertex AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.30 | $0.90 |
What it costs a month
At Vertex AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$158
- RAG over documents2,000 requests a day, 8K in / 0.6K out$176
- Coding agent1,000 requests a day, 40K in / 2K out$414
- Overnight batch20,000 requests a day, 4K in / 0.4K out$936
Where to run it
1 host serve Codestral 2. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Vertex AICloud codestral-2 | $0.30 / $0.90 | codestral-2 |
Show 3 more listings: regions, snapshots and variantsHide regional listings
| Vertex AI | |||||||
| Alias codestral-2 | $0.30 / $0.90 | codestral-2 | |||||
| Alias codestral-2@001 | $0.30 / $0.90 | codestral-2@001 | |||||
| Alias codestral-2@001 | $0.30 / $0.90 | codestral-2@001 | |||||
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
- 42% less
- 42% less
- 47% less
Other frontier labs
- 56% less
- 56% less
- 42% less
Open-weight picks
- 3% less
- 3% less
- 12% less
- 18% less
Model line
Newer and older versions, at each lab's own price.
- Aug 2025Codestral 2508Latest$0.30 / $0.90
- UndatedCodestral 2501$0.20 / $0.60
- UndatedCodestral 2405Not listed
- UndatedCodestral 2This page$0.30 / $0.90
Call it
Using Vertex AI's API.
from litellm import completion
response = completion(
model="vertex_ai/codestral-2",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Codestral 2 cost?
On Vertex AI, Codestral 2 costs $0.30 per million input tokens and $0.90 per million output tokens.
Which APIs offer Codestral 2?
Codestral 2 runs on 1 API: Vertex AI.
What is Codestral 2's context window?
128K tokens, with up to 128K tokens in one reply.
Is Codestral 2 being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Codestral 2?
Yes. Codestral 2508 is the newest model in this line, released on 1 Aug 2025.
What are cheaper alternatives to Codestral 2?
Models that cost less and keep most of what it can do: Magistral Small on Mistral AI (42% less), Claude Haiku 5.5 on Anthropic (56% less), GPT-6 Luna on OpenAI (56% less) and Step 3.7 Flash on DeepInfra (3% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Codestral 2's API model id?
Use codestral-2 with Vertex AI.
Sources
Raw catalog entry for codestral-2 on Vertex AI
{
"input_cost_per_token": 3e-7,
"litellm_provider": "vertex_ai-mistral_models",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 9e-7,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supports_function_calling": true,
"supports_tool_choice": true
}