Devstral 2 123B

Amazon Bedrock chat Deprecates in 146d (Mar 30, 2027)
Heads-up: Amazon Bedrock has scheduled Devstral 2 123B for deprecation on Mar 30, 2027. Plan a migration. Use Agent Command Center's model fallback routing to swap models without code changes.

Devstral 2 123B is an Amazon Bedrock chat model.It supports a 256,000-token context windowwith up to 32,000 output tokens.Input is priced at $0.400/M tokens and output at $2.00/M tokens. Capabilities include function calling. Route Devstral 2 123B via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.

Pricing source: litellm Last verified: Oct 22, 2026 View source ↗
Cost calculator

Estimate Devstral 2 123B spend

Pick a workload, fine-tune the sliders, and see the monthly bill.

~3K in / ~400 out · 5K req/day
3,000
0256,000
400
032,000
5,000
01,000,000
Per request
$0.002000
in $0.001200 · out $0.000800
Per day
$10.00
5,000 requests
Per month
$304
152,188 requests

Estimate uses $0.4000/M input · $2.00/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.

Pricing

Per-token rates, expressed in USD per 1M tokens. Verified Oct 22, 2026.

Input $0.400/M
Output $2.00/M
Blended (3:1 in:out) $0.800/M
Cross-model comparable price
Batch input $0.200/M
Batch output $1.00/M

Context & limits

Context window
256,000 tokens
Max input
256,000 tokens
Max output
32,000 tokens
Modalities
text

Capabilities

  • Function calling ✓ supported
  • Parallel tool calls — not advertised
  • Vision input — not advertised
  • Audio input — not advertised
  • Audio output — not advertised
  • PDF input — not advertised
  • Streaming ✓ supported
  • Structured output ✓ supported
  • Prompt caching — not advertised
  • Reasoning — not advertised

Strengths & caveats — when to pick Devstral 2 123B

Data-driven from Devstral 2 123B's percentile within chat peers.

Where it's strong

  • +agentic workflows that depend on reliable tool calls

Watch out for

  • !scheduled deprecation on Mar 30, 2027 (146 days)

Benchmarks pending

We haven't logged public benchmark scores for Devstral 2 123B yet. Have one to contribute? Submit a source — citations help us prioritise.

Try it

Call Devstral 2 123B via Agent Command Center

One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.

SDK
Native Future AGI client (agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.
# Devstral 2 123B via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC

client = AgentCC(
    api_key=os.environ["AGENTCC_API_KEY"],   # from app.futureagi.com → Settings → API Keys
    base_url="https://gateway.futureagi.com/v1",
)

resp = client.chat.completions.create(
    model="bedrock/mistral-devstral-2-123b",
    messages=[{"role": "user", "content": "Hello, Devstral 2 123B!"}],
)

print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")

# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
    model="bedrock/mistral-devstral-2-123b",
    messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost:   ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache:  ", raw.headers.get("x-agentcc-cache"))
Set AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗

Explore similar models

Devstral 2 123B doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark. Side-by-side links appear where a comparison page exists; otherwise, open the model profile.

FAQ

How much does Devstral 2 123B cost?

Input is priced at $0.400 per 1M tokens and output at $2.00 per 1M tokens (Amazon Bedrock, last verified Oct 22, 2026).

What is the context window of Devstral 2 123B?

Devstral 2 123B supports a 256,000-token context window with up to 32,000 output tokens.

Does Devstral 2 123B support function calling?

Yes — Devstral 2 123B supports function (tool) calling.

Is Devstral 2 123B good for production?

Devstral 2 123B is well-suited for agentic workflows that depend on reliable tool calls. Consider alternatives if you need scheduled deprecation on Mar 30, 2027 (146 days).

How can I route to Devstral 2 123B with fallback?

Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.

Useful links for Devstral 2 123B

Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.