Claude Haiku 4.5 vs Mistral Medium 3.5
Anthropic against Mistral AI, costed on the same three workloads. Claude Haiku 4.5 is cheaper on all three workloads.
Run this comparison on your own numbers
Monthly bill, side by side
| Workload | Claude Haiku 4.5 | Mistral Medium 3.5 | Difference |
|---|---|---|---|
| Support chatbot 2,500 six-turn conversations a day |
$4,028 | $6,041 | $2,014 (1.5×) |
| Document summarizer 1,000 single-shot summaries a day |
$486 | $729 | $243 (+50%) |
| Coding agent 200 twelve-turn sessions a day |
$2,808 | $4,212 | $1,404 (+50%) |
No prompt caching and no batch discount on either side, so the comparison is like for like. Both figures assume 30 days a month.
The rate cards
| Claude Haiku 4.5 | Mistral Medium 3.5 | |
|---|---|---|
| Input, per 1M tokens | $1 | $1.5 |
| Output, per 1M tokens | $5 | $7.5 |
| Cached input | $0.1 | $0.15 |
| Context window | 200K | 262K |
| Maximum output | 64K | 262K |
| Reasoning model | yes | no |
| Vision | yes | yes |
Beyond the price
- Mistral Medium 3.5 reads up to 262K tokens of context in one request; Claude Haiku 4.5 stops at 200K.
- Mistral Medium 3.5 can write up to 262K tokens in one response, against 64K for Claude Haiku 4.5.
- Only Claude Haiku 4.5 is a reasoning model, so its output bill also pays for the thinking it does before it answers.
- Only Claude Haiku 4.5 offers a batch discount — 50% off both rates for work that can wait.
Run this comparison on your own numbers
Full detail: Claude Haiku 4.5 pricing · Mistral Medium 3.5 pricing
More comparisons
Other head-to-heads that include Claude Haiku 4.5 or Mistral Medium 3.5.
- Claude Haiku 4.5 vs Nova 2 Lite
- Claude Haiku 4.5 vs Nova 2 Pro
- Claude Haiku 4.5 vs Command A
- Mistral Medium 3.5 vs Nova 2 Pro
- Mistral Medium 3.5 vs Command A
- Mistral Medium 3.5 vs o4-mini
Common questions
Which is cheaper, Claude Haiku 4.5 or Mistral Medium 3.5?
Claude Haiku 4.5 is cheaper on all three workloads.
How much would Claude Haiku 4.5 and Mistral Medium 3.5 cost each month?
On PromptSpend's standard workloads, per month: support chatbot: Claude Haiku 4.5 $4,028, Mistral Medium 3.5 $6,041 (Claude Haiku 4.5 is cheaper by $2,014); document summarizer: Claude Haiku 4.5 $486, Mistral Medium 3.5 $729 (Claude Haiku 4.5 is cheaper by $243); coding agent: Claude Haiku 4.5 $2,808, Mistral Medium 3.5 $4,212 (Claude Haiku 4.5 is cheaper by $1,404). No prompt caching and no batch discount is assumed.
How do Claude Haiku 4.5 and Mistral Medium 3.5 differ apart from price?
Mistral Medium 3.5 reads up to 262K tokens of context in one request; Claude Haiku 4.5 stops at 200K. Mistral Medium 3.5 can write up to 262K tokens in one response, against 64K for Claude Haiku 4.5. Only Claude Haiku 4.5 is a reasoning model, so its output bill also pays for the thinking it does before it answers. Only Claude Haiku 4.5 offers a batch discount — 50% off both rates for work that can wait.