Back to Text & reasoning

Model comparison

Claude Haiku 4.5 vs Mistral Medium 3.5

Provider-published facts for Claude Haiku 4.5 and Mistral Medium 3.5, side by side: price, limits, inputs, access and data policy. No mystery scores and no invented benchmark rankings.

Estimate your cost

Set your usage. Your estimate updates as you type.

Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.

One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.

Advanced options
How this estimate works

Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.

Estimate your cost
ModelEstimated total (USD)
Claude Haiku 4.5Anthropic$0.0085
Mistral Medium 3.5Mistral AINo reviewed rate

Quick take

Claude Haiku 4.5

A compact Claude model for quick replies, classification and narrowly scoped assistants.

Best for

  • Data extraction
  • Request routing

Watch out for

Haiku 4.5 uses manual extended thinking, not the adaptive thinking settings of the newer Claude models.

Mistral Medium 3.5

Mistral's open-weight frontier model for demanding multimodal, coding, reasoning, and agent workflows, with a 256K context window.

Best for

  • Complex coding and agent workflows
  • Multimodal document and image reasoning
  • Organizations choosing between hosted and controlled deployment

Watch out for

The headline token price applies to Mistral's standard hosted endpoint. Regional inference costs more, and self-hosting shifts the bill to GPUs, operations, and support.

Compare the published facts

Claude Haiku 4.5 vs Mistral Medium 3.5

Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.

Text & reasoningClaude Haiku 4.5Mistral Medium 3.5
Context windowMaximum combined prompt and working context documented by the provider.200K tokens256K tokens combined
Maximum outputProvider-published response limit, where available.64K tokensNot separately published
Knowledge cutoffLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff.February 2025Not published
Input priceCurrent standard list price per million input tokens unless noted.$1 / 1M$1.50 / 1M
Output priceCurrent standard list price per million output tokens unless noted.$5 / 1M$7.50 / 1M
InputsMedia types accepted by the listed model endpoint.Text, imageText, image
Tools & agentsSelected native tools and agent-building capabilities, not an exhaustive list.Tool use, agents, vision, coding workflowsFunctions, agents, built-in tools, structured and predicted outputs

How to choose

Data policy and API access

Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.

Claude Haiku 4.5

Anthropic does not train on API data without express permission. Retention depends on the API feature, account agreement and cloud provider.

Mistral Medium 3.5

Mistral's commercial terms exclude model training by default except when a customer opts in or uses designated Labs or preview models. Standard API input and output retention is generally 30 rolling days for abuse monitoring unless zero data retention is enabled.

Frequently asked questions

Claude Haiku 4.5 vs Mistral Medium 3.5 FAQ

What is the main difference between Claude Haiku 4.5 and Mistral Medium 3.5?

Claude Haiku 4.5: A compact Claude model for quick replies, classification and narrowly scoped assistants. Mistral Medium 3.5: Mistral's open-weight frontier model for demanding multimodal, coding, reasoning, and agent workflows, with a 256K context window.

Should I choose Claude Haiku 4.5 or Mistral Medium 3.5?

Best fit for Claude Haiku 4.5: Data extraction. Best fit for Mistral Medium 3.5: Complex coding and agent workflows. Test both with your own data and provider route before committing.

Where do the facts in this Claude Haiku 4.5 vs Mistral Medium 3.5 comparison come from?

From each provider's own documentation, pricing and policy pages for the Text & reasoning category. Cody does not add its own benchmark scores or name a universal winner.