Magistral Small 2509
mistral.magistral-small-2509Pricing
List prices at Amazon Bedrock, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.50 | $1.50 | |
| Batch 50% off | $0.25 | $0.75 | 50% off |
| Flex 50% off | $0.25 | $0.75 | 50% off |
| Priority 76% more | $0.88 | $2.63 | 76% more |
What it costs a month
At Amazon Bedrock list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$263
- RAG over documents2,000 requests a day, 8K in / 0.6K out$294
- Coding agent1,000 requests a day, 40K in / 2K out$690
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$780
Where to run it
1 host serve Magistral Small 2509. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Amazon BedrockCloud mistral.magistral-small-2509 | $0.50 / $1.50 | mistral.magistral-small-2509 |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| Mantle mistral.magistral-small-2509 | $0.50 / $1.50 | mistral.magistral-small-2509 | |||||
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 Amazon Bedrock.
Smaller Mistral AI models
- 65% less
- 65% less
- 68% less
Other frontier labs
- 38% less
- 73% less
- 73% less
- 65% less
Open-weight picks
- 9% less
- 15% less
- 30% less
- 36% less
Call it
Using Amazon Bedrock's API.
from litellm import completion
response = completion(
model="bedrock/mistral.magistral-small-2509",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Magistral Small 2509 cost?
On Amazon Bedrock, Magistral Small 2509 costs $0.50 per million input tokens and $1.50 per million output tokens.
Which APIs offer Magistral Small 2509?
Magistral Small 2509 runs on 1 API: Amazon Bedrock.
What is Magistral Small 2509's context window?
128K tokens, with up to 40K tokens in one reply.
Is Magistral Small 2509 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Magistral Small 2509?
Models that cost less and keep most of what it can do: Magistral Small on Mistral AI (65% less), GPT-5.4 Nano on OpenAI (38% less), Claude Haiku 5.5 on Anthropic (73% less) and Kimi K2.7 Code on CLF AI Gateway (9% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Magistral Small 2509's API model id?
Use mistral.magistral-small-2509 with Amazon Bedrock.
Sources
Raw catalog entry for mistral.magistral-small-2509 on Amazon Bedrock
{
"input_cost_per_token": 5e-7,
"input_cost_per_token_batches": 2.5e-7,
"input_cost_per_token_flex": 2.5e-7,
"input_cost_per_token_priority": 8.8e-7,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 128000,
"max_output_tokens": 40000,
"mode": "chat",
"output_cost_per_token": 0.0000015,
"output_cost_per_token_batches": 7.5e-7,
"output_cost_per_token_flex": 7.5e-7,
"output_cost_per_token_priority": 0.00000263,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
"supports_audio_input": false,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true
}