impulse

Devstral Small

API id devstral-small-latest
Input / 1M
$0.10
at Mistral AI
Output / 1M
$0.30
at Mistral AI
Context window
256K
tokens
Max output
256K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

List prices at Mistral AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.10$0.30
Cached input
90% off input
$0.01

What it costs a month

At Mistral AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$44.40
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$37.20
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$62.40
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$312
Use your own numbers

Where to run it

2 hosts serve Devstral Small. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Mistral AILab API
devstral-small-latest
$0.10 / $0.30
devstral-small
$0.07 / $0.28
−18% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Effort settings the source lists
nonehigh
Features
Assistant prefill

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

  • Vercel AI Gateway
    devstral-small
    $0.07 / $0.28
    18% less

Smaller Mistral AI models

No cheaper Mistral AI model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

Call it

Using Mistral AI's API.

Python
from litellm import completion

response = completion(
    model="mistral/devstral-small-latest",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Devstral Small cost?

On Mistral AI, Devstral Small costs $0.10 per million input tokens and $0.30 per million output tokens. Cached input costs $0.01 per million tokens. The cheapest host is Vercel AI Gateway, at $0.07 per million input tokens and $0.28 per million output tokens.

Which APIs offer Devstral Small?

Devstral Small runs on 2 APIs: Mistral AI and Vercel AI Gateway.

What is Devstral Small's context window?

256K tokens, with up to 256K tokens in one reply.

Is Devstral Small being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Devstral Small?

Models that cost less and keep most of what it can do: DeepSeek V4.1 Flash on Sail (5% less). Devstral Small itself costs 18% less on Vercel AI Gateway. Savings are on a mix of 3 input tokens to 1 output token.

What is Devstral Small's API model id?

Use devstral-small-latest with Mistral AI. Other hosts use their own ids: devstral-small on Vercel AI Gateway.

Sources

Raw catalog entry for devstral-small-latest on Mistral AI
{
  "cache_read_input_token_cost": 1e-8,
  "input_cost_per_token": 1e-7,
  "litellm_provider": "mistral",
  "max_input_tokens": 256000,
  "max_output_tokens": 256000,
  "mode": "chat",
  "output_cost_per_token": 3e-7,
  "reasoning_effort_levels": [
    "none",
    "high"
  ],
  "source": "https://docs.mistral.ai/models/devstral-small-2-25-12",
  "supports_assistant_prefill": true,
  "supports_function_calling": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true
}