Devstral 2 123B
mistral.devstral-2-123bPricing
List prices at Amazon Bedrock, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.40 | $2.00 | |
| Batch 50% off | $0.20 | $1.00 | 50% off |
| Flex 50% off | $0.20 | $1.00 | 50% off |
| Priority 75% more | $0.70 | $3.50 | 75% more |
What it costs a month
At Amazon Bedrock list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$270
- RAG over documents2,000 requests a day, 8K in / 0.6K out$264
- Coding agent1,000 requests a day, 40K in / 2K out$600
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$720
Where to run it
1 host serve Devstral 2 123B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Amazon BedrockCloud mistral.devstral-2-123b | $0.40 / $2.00 Retires 30 Mar 2027 | mistral.devstral-2-123b | Retires 30 Mar 2027 |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| Mantle mistral.devstral-2-123b | $0.40 / $2.00 Retires 30 Mar 2027 | mistral.devstral-2-123b | Retires 30 Mar 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 Amazon Bedrock.
Smaller Mistral AI models
- 6% less
- 44% less
- 44% less
Other frontier labs
- 42% less
- 75% less
- 75% less
- 67% less
Open-weight picks
- 1% less
- 14% less
- 20% less
- 40% less
Call it
Using Amazon Bedrock's API.
from litellm import completion
response = completion(
model="bedrock/mistral.devstral-2-123b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Devstral 2 123B cost?
On Amazon Bedrock, Devstral 2 123B costs $0.40 per million input tokens and $2.00 per million output tokens.
Which APIs offer Devstral 2 123B?
Devstral 2 123B runs on 1 API: Amazon Bedrock.
What is Devstral 2 123B's context window?
256K tokens, with up to 32K tokens in one reply.
Is Devstral 2 123B being retired?
Amazon Bedrock retires it on 30 Mar 2027. No API serves it after that.
What are cheaper alternatives to Devstral 2 123B?
Models that cost less and keep most of what it can do: Mistral Large on Mistral AI (6% less), GPT-5.4 Nano on OpenAI (42% less), Claude Haiku 5.5 on Anthropic (75% less) and DeepSeek V4 Pro on CLF AI Gateway (1% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Devstral 2 123B's API model id?
Use mistral.devstral-2-123b with Amazon Bedrock.
Sources
Raw catalog entry for mistral.devstral-2-123b on Amazon Bedrock
{
"deprecation_date": "2027-03-30",
"deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html",
"input_cost_per_token": 4e-7,
"input_cost_per_token_batches": 2e-7,
"input_cost_per_token_flex": 2e-7,
"input_cost_per_token_priority": 7e-7,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 256000,
"max_output_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 0.000002,
"output_cost_per_token_batches": 0.000001,
"output_cost_per_token_flex": 0.000001,
"output_cost_per_token_priority": 0.0000035,
"supports_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
"supports_audio_input": false,
"supports_response_schema": true,
"supports_vision": false
}