Home › Compare › Gemini 4 Hydrogen vs Mistral Small 4
Gemini 4 Hydrogen vs Mistral Small 4
A straight cost comparison of Gemini 4 Hydrogen (Google Gemini) and Mistral Small 4 (Mistral AI), per 1,000,000 tokens, verified November 2026.
Rate-by-rate comparison
| Metric | Gemini 4 Hydrogen | Mistral Small 4 | Winner |
|---|---|---|---|
| Input / 1M | $1.50 | $0.15 | Mistral Small 4 |
| Cached input / 1M | $0.075 | $0.015 | Mistral Small 4 |
| Cache write / 1M | — | — | Tie |
| Output / 1M | $7.50 | $0.60 | Mistral Small 4 |
| Context window | 1,000,000 | 256,000 | Gemini 4 Hydrogen |
| Batch API | Yes | Yes | Tie |
| Long-context tier | None | None | — |
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
| Model | Blended cost | Difference |
|---|---|---|
| Gemini 4 Hydrogen | $3.38 | +$3.08 |
| Mistral Small 4 | $0.30 | Cheaper |
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.
| Workload | Gemini 4 Hydrogen | Mistral Small 4 | Winner |
|---|---|---|---|
| Classification 100K reqs · 500 in / 10 out | $82.50 | $8.10 | Mistral Small 4 |
| Data extraction 10K reqs · 2K in / 200 out | $45 | $4.20 | Mistral Small 4 |
| Support chat 1K reqs · 4K in / 600 out | $10.50 | $0.96 | Mistral Small 4 |
| Code review 2K reqs · 8K in / 1.5K out | $46.50 | $4.20 | Mistral Small 4 |
| Summarisation 1K reqs · 20K in / 1K out | $37.50 | $3.60 | Mistral Small 4 |
| Agent loop 5K reqs · 12K in / 2K out | $165 | $15 | Mistral Small 4 |
| Translation 500 reqs · 15K in / 15K out | $67.50 | $5.63 | Mistral Small 4 |
| Long-document QA 200 reqs · 120K in / 800 out | $37.20 | $3.70 | Mistral Small 4 |
| Cached RAG 1K reqs · 50K in (45K cached) / 1K out | $18.44 | $2.03 | Mistral Small 4 |
| Nightly batch 10K reqs · 10K in / 2K out | $150 | $13.50 | Mistral Small 4 |
Gemini 4 Hydrogen wins 0 of 10, Mistral Small 4 wins 10 of 10. The winner is set by the token mix, not by the headline rate.
Where the two bills cross over
Mistral Small 4 is cheaper on both sides of the mix: $0.15 vs $1.50 per million input tokens, and $0.60 vs $7.50 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 / month | Gemini 4 Hydrogen | Mistral Small 4 | Difference |
|---|---|---|---|
| 100 | $1.05 | $0.096 | Mistral Small 4 cheaper by $0.954 |
| 1,000 | $10.50 | $0.96 | Mistral Small 4 cheaper by $9.54 |
| 10,000 | $105 | $9.60 | Mistral Small 4 cheaper by $95.40 |
| 100,000 | $1,050 | $96 | Mistral Small 4 cheaper by $954 |
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 prompt | Gemini 4 Hydrogen | Mistral Small 4 | Winner |
|---|---|---|---|
| 0% | $10.50 | $0.96 | Mistral Small 4 |
| 50% | $7.65 | $0.69 | Mistral Small 4 |
| 80% | $5.94 | $0.528 | Mistral Small 4 |
| 95% | $5.09 | $0.448 | Mistral Small 4 |
Both models publish a cached-read rate, so the discount is comparable: Gemini 4 Hydrogen reads cache at $0.075 per million, Mistral Small 4 at $0.015.
Which one should you pick?
Gemini 4 Hydrogen wins on none of the ten workloads above, while Mistral Small 4 wins on classification, data extraction, support chat, code review, summarisation, agent loop, translation, long-document qa, cached rag, nightly batch.
Beyond price, the two differ on input rate ($1.50 vs $0.15); output rate ($7.50 vs $0.60); cached-input rate ($0.075 vs $0.015); context window (1,000,000 vs 256,000).
Batch mode is available on Gemini 4 Hydrogen 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 Gemini 4 Hydrogen cheaper than Mistral Small 4?
On a blended 1M-input-plus-250K-output workload, Mistral Small 4 is cheaper by 91% ($0.30 vs $3.38). The gap changes for cache-heavy prompts and for batch jobs, as the workload table shows.
Which handles longer prompts, Gemini 4 Hydrogen or Mistral Small 4?
Mistral Small 4 has the larger context window (1,000,000 vs 256,000 tokens). Neither model publishes a long-context surcharge.
Do both models support prompt caching?
Gemini 4 Hydrogen bills cached reads at $0.075 per 1M; Mistral Small 4 at $0.015.
Related comparisons
- Gemini 4 Hydrogen vs Gemini 3.6 Flash
- Gemini 4 Hydrogen vs Gemini 2.5 Pro
- Mistral Large 4 vs Mistral Small 4
- All Google Gemini pricing
- All Mistral AI pricing