Pixtral 12B 2409
pixtral-12b-2409Pricing
List prices at Scaleway, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.20 | $0.20 |
What it costs a month
At Scaleway list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$75.00
- RAG over documents2,000 requests a day, 8K in / 0.6K out$103
- Coding agent1,000 requests a day, 40K in / 2K out$252
- Overnight batch20,000 requests a day, 4K in / 0.4K out$528
Where to run it
2 hosts serve Pixtral 12B 2409. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
ScalewayCloud pixtral-12b-2409 | $0.20 / $0.20 | pixtral-12b-2409 | |
IBM watsonx.aiCloud pixtral-12b-2409 | $0.35 / $0.35 +75% vs headline | pixtral-12b-2409 |
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
- TextImages
- 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 Scaleway.
Smaller Mistral AI models
- 25% less
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 10% less
- 11% less
- 20% less
- 25% less
Call it
Using Scaleway's API.
from litellm import completion
response = completion(
model="scaleway/pixtral-12b-2409",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Pixtral 12B 2409 cost?
On Scaleway, Pixtral 12B 2409 costs $0.20 per million input tokens and $0.20 per million output tokens.
Which APIs offer Pixtral 12B 2409?
Pixtral 12B 2409 runs on 2 APIs: Scaleway and IBM watsonx.ai.
What is Pixtral 12B 2409's context window?
128K tokens, with up to 4K tokens in one reply.
Is Pixtral 12B 2409 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Pixtral 12B 2409?
Models that cost less and keep most of what it can do: Devstral Small on Mistral AI (25% less) and Qwen3.8 Flash on AIHubMix (10% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Pixtral 12B 2409's API model id?
Use pixtral-12b-2409 with Scaleway.
Sources
Raw catalog entry for pixtral-12b-2409 on Scaleway
{
"input_cost_per_token": 2e-7,
"litellm_provider": "scaleway",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 2e-7,
"supports_vision": true,
"supports_function_calling": true,
"deprecation_date": "2026-10-01"
}