workhorse

Mistral Medium Latest vs Gemini 2.5 Flash

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

Specifications

Feature Mistral Medium Latest Gemini 2.5 Flash
Provider mistral vertex ai-language-models
Model ID mistral/mistral-medium-latest gemini-2.5-flash
Input / 1M tokens $0.40 $0.30 (25% cheaper)
Output / 1M tokens $2.00 (20% cheaper) $2.50
Cached input / 1M $0.03
Context window 131kk tokens 1049kk tokens
Max output 131kk tokens 66kk 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 Mistral Medium Latest Gemini 2.5 Flash Winner
Small
1M in / 0.2M out
$0.80 $0.80 Mistral Medium Latest
Medium
10M in / 2M out
$8.00 $8.00 Mistral Medium Latest
Large
100M in / 20M out
$80.00 $80.00 Mistral Medium Latest

Category winners

Cheapest input
Gemini 2.5 Flash
$0.30/M · 25% less than the other
Cheapest output
Mistral Medium Latest
$2.00/M · 20% less than the other
Larger context
Gemini 2.5 Flash
1049kk tokens · 700% larger window
More features
Gemini 2.5 Flash
5 / 5 capabilities

Better for…

High-volume RAG & repeated context
$0.03/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Gemini 2.5 Flash
Short interactions & high-throughput APIs
$2.00/M output — 20% cheaper on output at scale
Mistral Medium Latest
Long-document processing & large codebases
1049k context window vs 131k — 700% larger context
Gemini 2.5 Flash
Agentic workflows & tool use
Supports 5 of 5 tracked capabilities (vision, function calling, caching, web search, JSON schema)
Gemini 2.5 Flash

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.