Gemma 3 4B vs Mistral-Small-24B-2501 API pricing
Updated
Gemma 3 4B: USD 0.04 input, USD 0.08 output per 1M tokens (Amazon Bedrock). Mistral-Small-24B-2501: USD 0.05 input, USD 0.08 output per 1M tokens (DeepInfra). At 3 input tokens per output token, Mistral-Small-24B-2501 costs 15% more than Gemma 3 4B (USD 0.0575 vs USD 0.05 per 1M).
How do Gemma 3 4B and Mistral-Small-24B-2501 differ on price?
- Cheapest input price: Gemma 3 4B USD 0.04 against USD 0.05 per 1M tokens, so Mistral-Small-24B-2501 costs 1.25× as much (25% more).
- Cheapest output price: both USD 0.08 per 1M tokens.
- Among the 201 indexed models, Gemma 3 4B ranks 4th cheapest and Mistral-Small-24B-2501 7th on the 3:1 blend.
- No input:output mix changes the answer: Gemma 3 4B is cheaper at every mix before cache discounts.
- Only Mistral-Small-24B-2501 lists a cached-input discount: Mistral-Small-24B-2501 at 1 standard price of 2, from USD 0.04 (Featherless, 77% below that provider's input price). Gemma 3 4B's cached tokens bill at the input price.
- Gemma 3 4B states up to 131,072 tokens of context, 4× the 32,768 of Mistral-Small-24B-2501.
- Gemma 3 4B has 3 providers with a standard price, 1 more than Mistral-Small-24B-2501; 2 providers sell both (DeepInfra and Featherless).
- On one account, DeepInfra charges USD 0.0625 for Gemma 3 4B (1.25× its cheapest price) and USD 0.0575 for Mistral-Small-24B-2501 (its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Mistral-Small-24B-2501: its dearest standard price is 3.5× its cheapest, against 1.25× for Gemma 3 4B.
- Per character of input, the gap depends on the language: Gemma 3 4B costs 9% less than Mistral-Small-24B-2501 on Arabic MSA text but 63% less than Mistral-Small-24B-2501 on Hindi, because the two tokenizers split those languages differently.
Gemma 3 4B and Mistral-Small-24B-2501 prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | Gemma 3 4B | Mistral-Small-24B-2501 |
|---|---|---|
| Model page | Gemma 3 4B Google · 3 providers | Mistral-Small-24B-Instruct-2501 Mistral AI · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.05 lower USD 0.04 in / USD 0.08 out at Amazon Bedrock Amazon Bedrock page checked 2026-11-14 | USD 0.0575 USD 0.05 in / USD 0.08 out at DeepInfra DeepInfra page checked 2026-11-14 |
| Cheapest input | USD 0.04 lower Amazon Bedrock source | USD 0.05 DeepInfra source |
| Cheapest cached input | No standard price lists a cache price; cached tokens bill at the input price. | USD 0.04 Featherless source |
| Cheapest output | USD 0.08 tie Amazon Bedrock source | USD 0.08 tie DeepInfra source |
| Maker's own API | Google publishes no paid standard price on its own API that we found. | Mistral AI publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.05 / USD 0.10 input / output, 3 prices | USD 0.1125 / USD 0.185 input / output, 2 prices |
| Context window | 131,072 tokens, largest stated; from 32,768 at some providers | 32,768 tokens, largest stated |
| Providers with a standard price | 3 | 2 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do Gemma 3 4B and Mistral-Small-24B-2501 cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | Gemma 3 4B | Mistral-Small-24B-2501 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 5.04 Amazon Bedrock | USD 5.94 DeepInfra | USD 0.9 Gemma 3 4B lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 10.80 Amazon Bedrock | USD 13.20 DeepInfra | USD 2.40 Gemma 3 4B lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 79.20 Amazon Bedrock | exceeds context | — |
Gemma 3 4B is cheaper on 2 workloads. The widest gap is on RAG over documents: the dearer model costs 22% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
Gemma 3 4B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Mistral-Small-24B-2501's, so the input:output ratio never changes the answer. On output price alone they tie.
| Input : output tokens | Gemma 3 4B | Mistral-Small-24B-2501 |
|---|---|---|
| 1 : 3 (long answers) | USD 0.07 lower Amazon Bedrock | USD 0.0725 DeepInfra |
| 1 : 1 | USD 0.06 lower Amazon Bedrock | USD 0.065 DeepInfra |
| 3 : 1 (the site’s blend) | USD 0.05 lower Amazon Bedrock | USD 0.0575 DeepInfra |
| 10 : 1 (retrieval, long prompts) | USD 0.04364 lower Amazon Bedrock | USD 0.05273 DeepInfra |
| 30 : 1 (agents, big contexts) | USD 0.04129 lower Amazon Bedrock | USD 0.05097 DeepInfra |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Gemma 3 4B and Mistral-Small-24B-2501 cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Gemma 3 27B tokenizer for Gemma 3 4B and the Mistral Small 3.1 tokenizer for Mistral-Small-24B-2501:
| Content | Gemma 3 4B | Mistral-Small-24B-2501 |
|---|---|---|
| English | USD 0.0087 lower Amazon Bedrock | USD 0.011 DeepInfra |
| Arabic MSA | USD 0.014 lower Amazon Bedrock | USD 0.015 DeepInfra |
| Egyptian Arabic | USD 0.014 lower Amazon Bedrock | USD 0.016 DeepInfra |
| Hindi | USD 0.011 lower Amazon Bedrock | USD 0.029 DeepInfra |
| Chinese | USD 0.027 lower Amazon Bedrock | USD 0.045 DeepInfra |
| Spanish | USD 0.0090 lower Amazon Bedrock | USD 0.012 DeepInfra |
| Code | USD 0.012 lower Amazon Bedrock | USD 0.014 DeepInfra |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Check it on your own traffic
- Gemma 3 4B API pricing: all 3 providers and other tiers.
- Mistral-Small-24B-Instruct-2501 API pricing: all 2 providers and other tiers.
- Cost calculator with Gemma 3 4B and Mistral-Small-24B-2501 preloaded
- Gemma 3 token counter
- Mistral Small token counter
- Prompt caching calculator
More comparisons: Gemma 3 12B vs Gemma 3 4B · Mistral Small 3.1 24B vs Mistral-Small-24B-2501 · every Gemma 3 4B comparison · every Mistral-Small-24B-2501 comparison · all 662 price comparisons
Questions
Is Gemma 3 4B cheaper than Mistral-Small-24B-2501?
Yes. On a blend of 3 input tokens to 1 output token, Gemma 3 4B costs USD 0.05 per 1M tokens and Mistral-Small-24B-2501 USD 0.0575, at each model's cheapest standard price. For input alone, Gemma 3 4B is cheaper (USD 0.04 against USD 0.05 per 1M); for output alone, both start at USD 0.08. This compares price only, not quality.
What do Gemma 3 4B and Mistral-Small-24B-2501 cost per 1M tokens?
Gemma 3 4B: from USD 0.04 input and USD 0.08 output at Amazon Bedrock; median of 3 standard prices USD 0.05 / USD 0.10. Mistral-Small-24B-2501: from USD 0.05 input and USD 0.08 output at DeepInfra; median of 2 standard prices USD 0.1125 / USD 0.185. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Gemma 3 4B and Mistral-Small-24B-2501?
2 providers have a standard price for both: DeepInfra (USD 0.0625 and USD 0.0575 at 3:1), Featherless (USD 0.0625 and USD 0.2037 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.05 and USD 0.0575.
At what input:output ratio does the cheaper of Gemma 3 4B and Mistral-Small-24B-2501 change?
Gemma 3 4B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Mistral-Small-24B-2501's, so the input:output ratio never changes the answer. On output price alone they tie.
Do Gemma 3 4B and Mistral-Small-24B-2501 have cached input pricing?
Gemma 3 4B: no standard price lists a cached-input discount. Mistral-Small-24B-2501 from USD 0.04 per 1M cached input tokens (Featherless; 1 of 2 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, Gemma 3 4B or Mistral-Small-24B-2501?
Gemma 3 4B: up to 131,072 tokens, against 32,768 for Mistral-Small-24B-2501, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.