This model was retired on 2025-11-30. The pricing below is the last-known rate, kept for migration reference.

Devstral Small 2505Deprecated

MistralReleasedMay 7, 2025KnowledgeMay 2025
Tool useStructured output
Context
131K
Max output
131K
Serving providers
2
Cheapest input
$0.10 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
Intelligence Index
11.8
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
EvalComputeProxy5.8default
GPQA Diamond43%default
Humanity's Last Exam4%default
IFBench32%default
LiveCodeBench26%default
Long-Context Reasoning30%default
MMLU-Pro63%default
Omniscience-56.8default
Omniscience Accuracy0.2default
Omniscience Non Hallucination0.1default
SciCode25%default
TerminalBench Hard6%default
τ²-bench38%default

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Mistral$0.10$0.301
Fireworks AI$0.90$0.901

Price history

input + output $/1M since we started tracking
Input Output
Input down 70% since first tracked
$0.000$0.100$0.200$0.300May 23Jul 30Aug 22Dec 9Jun 22$0.030$0.030

Cost calculator

estimate your monthly spend on this model
$44
estimated / month

Model IDs

copy the exact identifier for your platform
mistral/devstral-small-2505fireworks_ai/accounts/fireworks/models/devstral-small-2505

Frequently asked questions

Devstral Small 2505 pricing, context and availability

Is Devstral Small 2505 still available?

Devstral Small 2505 was retired on 2025-11-30. The pricing on this page is the last-known rate, kept for migration reference.

How much did Devstral Small 2505 cost?

Devstral Small 2505's last-known pricing, before it was retired on 2025-11-30, was $0.10 per 1M input tokens and $0.30 per 1M output tokens.

What was the context window of Devstral Small 2505?

Devstral Small 2505 had a 131K token context window and could return up to 131K output tokens.

What could Devstral Small 2505 do?

Devstral Small 2505 supported tool use and structured output.

Other Mistral models

compare pricing across the Mistral lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI