Devstral 2 123B pricing, context window and limits
Devstral 2 123B costs $0.4 per million input tokens and $2 per million output tokens at Amazon Bedrock list price. It accepts up to 262,144 tokens of context and returns up to 8,192 tokens.
- Model id
bedrock/mistral.devstral-2-123b - Snapshot
What does Devstral 2 123B cost?
| Input | $0.4 |
|---|---|
| Output | $2 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Devstral 2 123B read and write?
| Context window | 262,144 |
|---|---|
| Max output | 8,192 |
What can Devstral 2 123B do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | No |
| Input | text |
| Output | text |
What does a request to Devstral 2 123B cost?
| A typical request: 1,000 tokens in, 500 out | $0.0014 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.006 |
| 1,000 typical requests | $1.4 |
| 1 million tokens in and 1 million out | $2.4 |
Among 199 Amazon Bedrock models with a published price, Devstral 2 123B is the 65th cheapest by input price. Its context window is the 117th largest of 199. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Devstral 2 123B through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/mistral.devstral-2-123b. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Amazon Bedrock models are there?
- MiniMax-M2.5$0.3 in · $1.2 out · 197K context
- Magistral Small 1.2$0.5 in · $1.5 out · 128K context
- MiniMax-M2.1$0.3 in · $1.2 out · 197K context
- Ministral 14B 3.0$0.2 in · $0.2 out · 128K context
- MiniMax-M2$0.3 in · $1.2 out · 205K context
- Ministral 3 3B$0.1 in · $0.1 out · 256K context
- Llama 4 Scout 17B Instruct$0.17 in · $0.66 out · 10M context
- Ministral 3 8B$0.15 in · $0.15 out · 128K context
- Llama 4 Maverick 17B Instruct$0.24 in · $0.97 out · 1M context
- Mistral Large 3$0.5 in · $1.5 out · 262K context
- Llama 3.3 70B Instruct$0.72 in · $0.72 out · 128K context
- Pixtral Large (25.02)$2 in · $6 out · 128K context
Which models from other providers are similar to Devstral 2 123B?
These are the closest in context window and input price, one per provider.
- Devstral 2Mistral AI · $0.4 in · $2 out · 262K context
- Qwen3 MaxAlibaba Qwen · $0.359 in · $1.434 out · 262K context
- GLM-4.6Zhipu GLM · $0.6 in · $2.2 out · 205K context
- Kimi K2.6Moonshot AI · $0.95 in · $4 out · 262K context
- GPT-5 MiniOpenAI · $0.25 in · $2 out · 400K context