devstral-2-123b

Mistral AIbedrock/mistral.devstral-2-123b
Modality

Chat

Family

devstral-2-123b

Context window

—

Max output

—

Served On

Amazon Bedrock

devstral-2-123b is a chat model made by Mistral AI, served on nRouter.

Model pricing

Exact provider list price · 0% platform fee · x-nr-request-cost header

Rates are read live

Pricing for devstral-2-123b is fetched from the live catalogue on load, so it is never served from a cache that could outlive a repricing.

Start building with devstral-2-123b

One API key, three steps. Choose your tool to begin.

  1. Set your API key

    export NROUTER_API_KEY="<YOUR_API_KEY>"
  2. Configure Claude Code

    Choose a tool, then copy its setup from the panel.

npm install -g @anthropic-ai/claude-code
Claude Code · bedrock/mistral.devstral-2-123b
# Point Claude Code to nRouter gateway
export ANTHROPIC_BASE_URL="https://api.nrouter.ai"
export ANTHROPIC_API_KEY="$NROUTER_API_KEY"

# Launch with bedrock/mistral.devstral-2-123b
claude --model bedrock/mistral.devstral-2-123b

Specifications & capabilities

VisionFunction callingSystem prompt
Compare context window against peer models (—)

Context window, ranked against other chat models

Proportional scale: 0 to 128K tokens. Not ranked, no published context window: nemotron-nano-12b-v2, qwen-flash-character, qwen3.5-omni-flash, gemini-live-2.5-flash-native-audio, qwen3.7-max-2026-05-20.

Provider-Reported Capabilities

What the hosting provider reports for this model, shown as it was returned. nRouter adds nothing to this report and infers nothing that is missing from it.

Model ID modelId

mistral.devstral-2-123b

Converse converse
Max Tokens Default maxTokensDefault

null

Max Tokens Maximum maxTokensMaximum

262144

Reasoning Supported reasoningSupported

null

System Role Supported systemRoleSupported
Stop Sequences Default stopSequencesDefault
User Image Types Supported userImageTypesSupported
User Video Types Supported userVideoTypesSupported
User Document Types Supported userDocumentTypesSupported
Model Name modelName

Devstral 2 123B

Description description

null

Model Family modelFamily

Devstral 2

Provider Name providerName

Mistral AI

Batch Supported batchSupported
Base Model Supported baseModelSupported
Cross Region Supported crossRegionSupported
Custom Model Supported customModelSupported
Model Lifecycle modelLifecycle
Status status

ACTIVE

Legacy Time legacyTime

null

End Of Life Time endOfLifeTime

null

Public Extended Access Time publicExtendedAccessTime

null

Input Modalities inputModalities
TEXT
Output Modalities outputModalities
TEXT
Features Supported featuresSupported
Count Tokens countTokens
Prompt Caching promptCaching
Batch Inference batchInference
In Region inRegion
Cross Region crossRegion
Prompt Optimization promptOptimization
Provisioned Throughput provisionedThroughput
Intelligent Prompt Routing intelligentPromptRouting
Console IDEMetadata consoleIDEMetadata

null

Guardrails Supported guardrailsSupported
Explicit Prompt Caching explicitPromptCaching
Is Supported isSupported
Inference APIs Supported inferenceAPIsSupported
Converse converse
Sync sync
Streaming streaming
Async Invoke asyncInvoke
Invoke Model invokeModel
Sync sync
Response Streaming responseStreaming
Bidirectional Streaming bidirectionalStreaming
Open AI Responses openAiResponses
Open AI Chat Completions openAiChatCompletions
Customizations Supported customizationsSupported
Inference Types Supported inferenceTypesSupported
ON_DEMAND
Intelligent Prompt Routing intelligentPromptRouting
Is Supported isSupported
Response Streaming Supported responseStreamingSupported
Latency Optimization Supported latencyOptimizationSupported

Availability

Collecting probe samples

Not enough health probe samples collected yet to publish an uptime or latency figure.

More from Mistral AI

FAQs

What is devstral-2-123b?

devstral-2-123b is a chat model made by Mistral AI, served on nRouter.

How much does devstral-2-123b cost?

devstral-2-123b is billed at the provider's list price on nRouter with no per-token markup — tokens settle at the exact upstream rate. Input and output rates are read live, so see the pricing section above for the current figures.

Does devstral-2-123b support tool calling and structured outputs?

Yes. devstral-2-123b supports tool calling (function calling), so it can invoke external tools and APIs during a conversation.

What inputs and outputs does devstral-2-123b support?

devstral-2-123b takes text and images as input and returns text as output.

How do I use devstral-2-123b via nRouter?

Use any OpenAI-compatible client: point it at https://api.nrouter.ai/v1 with your nRouter API key and set the model to "bedrock/mistral.devstral-2-123b". The quick-start panel above has a copy-paste curl command for this model.

Where is the devstral-2-123b documentation?

Start at nrouter.ai/docs. The quick-start guide (nrouter.ai/docs/getting-started/quick-start) covers API keys and your first request, and the API reference (nrouter.ai/docs/api-reference) lists every parameter.

What other text models does Mistral AI have?

Other Mistral AI text models on nRouter include Ministral 3 14B Instruct (nrouter.ai/models/ministral-3-14b-instruct), Mistral Small 2503 (nrouter.ai/models/mistral-small-2503), Pixtral Large 2502 (nrouter.ai/models/pixtral-large-2502), Ministral 3 3B Instruct (nrouter.ai/models/ministral-3-3b-instruct).