budget

Claude Haiku 4 5 vs Mistral Small Latest

Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.

Specifications

Feature Claude Haiku 4 5 Mistral Small Latest
Provider anthropic mistral
Model ID claude-haiku-4-5 mistral/mistral-small-latest
Input / 1M tokens $1.00 $0.06 (94% cheaper)
Output / 1M tokens $5.00 $0.18 (96% cheaper)
Cached input / 1M $0.10
Context window 200kk tokens 131kk tokens
Max output 64kk tokens 131kk tokens
Vision
Function calling
Prompt caching
Web search
JSON schema

Monthly cost comparison

No cache discount applied — pure token costs at three usage scales.

Scale Claude Haiku 4 5 Mistral Small Latest Winner
Small
1M in / 0.2M out
$2.00 $0.10 Mistral Small Latest saves 95%
Medium
10M in / 2M out
$20.00 $0.96 Mistral Small Latest saves 95%
Large
100M in / 20M out
$200 $9.60 Mistral Small Latest saves 95%

Category winners

Cheapest input
Mistral Small Latest
$0.06/M · 94% less than the other
Cheapest output
Mistral Small Latest
$0.18/M · 96% less than the other
Larger context
Claude Haiku 4 5
200kk tokens · 53% larger window
More features
Claude Haiku 4 5
4 / 5 capabilities

Better for…

High-volume RAG & repeated context
$0.10/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Claude Haiku 4 5
Short interactions & high-throughput APIs
$0.18/M output — 96% cheaper on output at scale
Mistral Small Latest
Long-document processing & large codebases
200k context window vs 131k — 53% larger context
Claude Haiku 4 5
Agentic workflows & tool use
Supports 4 of 5 tracked capabilities (vision, function calling, caching, web search, JSON schema)
Claude Haiku 4 5

Deep-dive on each model

Pricing data sourced from LiteLLM and refreshed regularly. Always verify with each provider's official pricing page before making business decisions.