Verified November 2026

Home › Compare › Claude Haiku 5.5 vs Mistral Small 4

Claude Haiku 5.5 vs Mistral Small 4

A straight cost comparison of Claude Haiku 5.5 (Anthropic) and Mistral Small 4 (Mistral AI), per 1,000,000 tokens, verified November 2026.

$0.10Claude Haiku 5.5 input / 1M
$0.15Mistral Small 4 input / 1M
25%Blended price gap
Claude Haiku 5.5Cheaper blended

Rate-by-rate comparison

USD per 1M tokens · November 2026
MetricClaude Haiku 5.5Mistral Small 4Winner
Input / 1M$0.10$0.15Claude Haiku 5.5
Cached input / 1M$0.01$0.015Claude Haiku 5.5
Cache write / 1M$0.125—Mistral Small 4
Output / 1M$0.50$0.60Claude Haiku 5.5
Context window200,000256,000Mistral Small 4
Batch APIYesYesTie
Long-context tier> 100,000None—

For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.

Blended cost: 1M input + 250K output

ModelBlended costDifference
Claude Haiku 5.5$0.225Cheaper
Mistral Small 4$0.30+$0.075

Ten workloads, two bills

The same two models, priced across ten workloads that differ only in their input:output ratio. Nothing else changes — no retries, no system prompt, no middleware.

WorkloadClaude Haiku 5.5Mistral Small 4Winner
Classification
100K reqs · 500 in / 10 out
$5.50$8.10Claude Haiku 5.5
Data extraction
10K reqs · 2K in / 200 out
$3$4.20Claude Haiku 5.5
Support chat
1K reqs · 4K in / 600 out
$0.70$0.96Claude Haiku 5.5
Code review
2K reqs · 8K in / 1.5K out
$3.10$4.20Claude Haiku 5.5
Summarisation
1K reqs · 20K in / 1K out
$2.50$3.60Claude Haiku 5.5
Agent loop
5K reqs · 12K in / 2K out
$11$15Claude Haiku 5.5
Translation
500 reqs · 15K in / 15K out
$4.50$5.63Claude Haiku 5.5
Long-document QA
200 reqs · 120K in / 800 out
$12.08$3.70Mistral Small 4
Cached RAG
1K reqs · 50K in (45K cached) / 1K out
$1.46$2.03Claude Haiku 5.5
Nightly batch
10K reqs · 10K in / 2K out
$10$13.50Claude Haiku 5.5

Claude Haiku 5.5 wins 9 of 10, Mistral Small 4 wins 1 of 10. The winner is set by the token mix, not by the headline rate.

Where the two bills cross over

Claude Haiku 5.5 is cheaper on both sides of the mix: $0.10 vs $0.15 per million input tokens, and $0.50 vs $0.60 per million output. No input:output ratio reverses that, so on price alone the other model never becomes the better choice — it has to win on context, latency or output quality.

Cost at four scales

The same support-chat workload (4K input, 600 output per request) at four monthly volumes.

Requests / monthClaude Haiku 5.5Mistral Small 4Difference
100$0.07$0.096Claude Haiku 5.5 cheaper by $0.026
1,000$0.70$0.96Claude Haiku 5.5 cheaper by $0.26
10,000$7$9.60Claude Haiku 5.5 cheaper by $2.60
100,000$70$96Claude Haiku 5.5 cheaper by $26

What caching does to each bill

Caching only helps the part of the prompt that repeats. This is the support-chat workload (1,000 requests, 4,000 input tokens each) with an increasing share of that prompt served from a warm cache, written once on the first request.

Cached share of the promptClaude Haiku 5.5Mistral Small 4Winner
0%$0.70$0.96Claude Haiku 5.5
50%$0.52$0.69Claude Haiku 5.5
80%$0.412$0.528Claude Haiku 5.5
95%$0.358$0.448Claude Haiku 5.5

Both models publish a cached-read rate, so the discount is comparable: Claude Haiku 5.5 reads cache at $0.01 per million, Mistral Small 4 at $0.015.

Which one should you pick?

Claude Haiku 5.5 wins on classification, data extraction, support chat, code review, summarisation, agent loop, translation, cached rag, nightly batch, while Mistral Small 4 wins on long-document qa.

Beyond price, the two differ on input rate ($0.10 vs $0.15); output rate ($0.50 vs $0.60); cached-input rate ($0.01 vs $0.015); cache-write rate ($0.125 vs —); context window (200,000 vs 256,000); long-context tier (yes, above 100,000 vs none).

Batch mode is available on Claude Haiku 5.5 and Mistral Small 4, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.

FAQ

Is Claude Haiku 5.5 cheaper than Mistral Small 4?

On a blended 1M-input-plus-250K-output workload, Claude Haiku 5.5 is cheaper by 25% ($0.225 vs $0.30). The gap changes for cache-heavy prompts and for batch jobs, as the workload table shows.

Which handles longer prompts, Claude Haiku 5.5 or Mistral Small 4?

Mistral Small 4 has the larger context window (256,000 vs 200,000 tokens). Watch the long-context threshold on Claude Haiku 5.5: rates rise once input passes it.

Do both models support prompt caching?

Claude Haiku 5.5 bills cached reads at $0.01 per 1M; Mistral Small 4 at $0.015.

Related comparisons

Run your own token volumes