mistral logo 99% off

Devstral 2 123B API

Mistral AI·Text· 100.0% success (7d)

Devstral 2 123B

256K Context 32.0K out $53.12 capacity 227 req/24h $0.01 24h volume
Input
Text
Output
Text

Pricing

Cheapest live price, per 1 million tokens.

Input / 1M tokens

$0.00699% off

$0.400 OpenRouter

Output / 1M tokens

$0.03099% off

$2.00 OpenRouter

Cache read / 1M

$0.000831

Repeated prompt prefixes

Cache read is the discounted rate for repeated prompt prefixes (system prompts, agent context).

Capabilities · 5

Tool calling JSON mode JSON schema Streaming Seed

Specifications

Context window
256K
Max output
32K
Type
Text
Creator
Mistral AI
Live sellers
24
Requests / 24h
227

Price history · 60 days

Sep 18 — Nov 17▲ 91.88% vs last week
Compare all top models

Estimated monthly cost

30 days at the cheapest live price.

AI Chatbot
1,000 req/day · 2K in · 0.5K out
$0.81/mo
$54.00 OpenRouter
Coding Copilot
500 req/day · 8K in · 2K out
$1.62/mo
$108.00 OpenRouter
AI Agent
100 req/day · 50K in · 5K out
$1.35/mo
$90.00 OpenRouter

Quick start

OpenAI-compatible — change the base URL and key. Get a key from the dashboard.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.qubax.ai/v1",
    api_key="YOUR_QUBAX_API_KEY",
)

response = client.chat.completions.create(
    model="devstral-2-123b",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

About Devstral 2 123B

Devstral 2 123B is a language model developed by Mistral AI. It's particularly well-suited for orchestrating tool-using agents that call APIs and external services, producing structured outputs for reliable data extraction and handling large contexts of up to 256K tokens. Its 256K-token context window means you can pass in entire documents, codebases, or conversation histories without losing context. It can write up to 32K tokens in a single response.

As of Nov 17, 2026, Devstral 2 123B costs $0.0060 per 1M input tokens and $0.030 per 1M output tokens on Qubax, versus $0.400 / $2.00 on OpenRouter (99% less on input). A typical 1,000 chat requests (2K tokens in, 500 out) come to about $0.03. Measured availability over the last 7 days: 100.0%. 24 independent compute providers currently serve it, so requests fail over automatically. It handled 227 requests on Qubax in the last 24 hours. Pay with USDC, USDT, BTC, ETH or 350+ other coins — no credit card required.

Function Calling
Build agents and tool-using applications
Long Documents
Process entire codebases, books, or lengthy conversations
Chat & Conversation
Build AI chatbots and conversational assistants
Content Generation
Write articles, code, emails, and more

Similar-priced alternatives

Frequently asked questions

How much does the Devstral 2 123B API cost?

On Qubax, Devstral 2 123B costs $0.0060 per 1M input tokens and $0.030 per 1M output tokens. This is 99% cheaper than OpenRouter's price of $0.400 per 1M input tokens.

Is the Devstral 2 123B API compatible with OpenAI?

Yes. Qubax provides an OpenAI-compatible API. You can use Devstral 2 123B as a drop-in replacement by changing your base URL to https://api.qubax.ai/v1 and using your Qubax API key. It works with Cline, Cursor, OpenCode, Hermes Agent, and any tool that supports OpenAI APIs.

Why is Devstral 2 123B cheaper on Qubax than OpenRouter?

Qubax sources AI inference from an open compute marketplace on the Base blockchain where GPU providers compete on price. We pass the savings to you — 99% cheaper than OpenRouter's price for Devstral 2 123B.

How do I pay for Devstral 2 123B API usage?

Qubax uses prepaid crypto credits. Top up with USDC, USDT, BTC, ETH, SOL or 350+ other coins and your balance is deducted as you use the API. No credit card or KYC required.

What is the context window of Devstral 2 123B?

Devstral 2 123B supports a context window of 256K tokens, allowing you to process large documents, codebases, or long conversations in a single request.

What can I build with Devstral 2 123B?

You can use Devstral 2 123B to build autonomous agents that call external tools and APIs, generate structured JSON output for data pipelines and process long documents and entire codebases. Because it's served through Qubax's OpenAI-compatible API, integration into existing apps, agents, or workflows takes just a few lines of code.

How fast and reliable is Devstral 2 123B on Qubax?

Its 7-day success rate is 100.0%. Responses stream token by token. 24 sellers serve it, so if one is slow or down the request moves to the next.

Devstral 2 123B vs GLM 4.5: which should I choose?

Devstral 2 123B by Mistral AI and GLM 4.5 by Zhipu AI are both strong models in a similar price tier. Devstral 2 123B is well-suited for general-purpose language tasks. GLM 4.5 comes from a different lab and may have different strengths depending on your workload. On Qubax, Devstral 2 123B starts at $0.0060/1M input tokens versus GLM 4.5's $0.0088/1M — making Devstral 2 123B the more cost-effective option for high-volume workloads. Both are available on Qubax with crypto payments and OpenAI-compatible APIs, so you can try each and switch freely.

Can I use Devstral 2 123B for commercial projects?

Yes. Devstral 2 123B on Qubax can be used for commercial purposes. You own the outputs you generate. Qubax provides the API infrastructure — you bring your use case.

Why use Devstral 2 123B on Qubax?

99% cheaper

Providers compete on price — you get the cheapest healthy seller.

Pay with crypto

350+ coins (BTC, ETH, SOL, USDT, USDC). No card, no KYC.

OpenAI & Anthropic compatible

Drop-in base URL. Works with Cline, Cursor, Claude Code, OpenAI and Anthropic SDKs.

Get started free →

More from Mistral AI

Browse 380+ other AI models

GPT, Claude, Gemini, Llama, DeepSeek & more.

See all models →

Devstral 2 123B

$0.006 in · $0.030 out

Get API key