gemma-4-31B-it-turbo vs Step-3.5-Flash API pricing
Updated
gemma-4-31B-it-turbo's lowest standard price we found is USD 0.09 per 1M input tokens and USD 0.34 per 1M output tokens (DeepInfra). Step-3.5-Flash's lowest standard price we found is USD 0.10 per 1M input tokens and USD 0.30 per 1M output tokens (Featherless and 1 other). At 3 input tokens per output token, gemma-4-31B-it-turbo costs 1.7% more than Step-3.5-Flash (USD 0.1525 vs USD 0.15 per 1M).
How do gemma-4-31B-it-turbo and Step-3.5-Flash differ on price?
- Cheapest input price: gemma-4-31B-it-turbo USD 0.09 against USD 0.10 per 1M tokens, so Step-3.5-Flash costs 1.11× as much (11% more).
- Cheapest output price: Step-3.5-Flash USD 0.30 against USD 0.34 per 1M tokens, so gemma-4-31B-it-turbo costs 1.13× as much (13% more).
- Among the 201 indexed models, gemma-4-31B-it-turbo ranks 45th cheapest and Step-3.5-Flash 40th on the 3:1 blend.
- The cheaper model changes at 4 input tokens per output token.
- Only gemma-4-31B-it-turbo lists a cached-input discount: gemma-4-31B-it-turbo at 2 standard prices of 2, from USD 0.012 (Chutes, 90% below that provider's input price). Step-3.5-Flash's cached tokens bill at the input price.
- Both state a context window of up to 262,144 tokens.
- Both have 2 providers with a standard price; no provider sells both, so using both means two accounts.
- Shopping around matters more for gemma-4-31B-it-turbo: its dearest standard price is 1.2× its cheapest, against 1× for Step-3.5-Flash.
- For the one-developer coding agent preset, the gap is USD 1,475 a year in gemma-4-31B-it-turbo's favour (gemma-4-31B-it-turbo USD 84.06 a month, Step-3.5-Flash USD 207.00).
gemma-4-31B-it-turbo and Step-3.5-Flash 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-4-31B-it-turbo | Step-3.5-Flash |
|---|---|---|
| Model page | gemma-4-31B-it-turbo Google · 2 providers | Step-3.5-Flash StepFun · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.1525 USD 0.09 in / USD 0.34 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 0.15 lower USD 0.10 in / USD 0.30 out at Featherless and 1 other Featherless page checked 2026-11-15 |
| Cheapest input | USD 0.09 lower DeepInfra source | USD 0.10 Featherless source |
| Cheapest cached input | USD 0.012 Chutes source | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 0.34 DeepInfra source | USD 0.30 lower Featherless source |
| Maker's own API | Google publishes no paid standard price on its own API that we found. | StepFun publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.105 / USD 0.355 input / output, 2 prices | USD 0.10 / USD 0.30 input / output, 2 prices |
| Context window | 262,144 tokens, largest stated; from 131,072 at some providers | 262,144 tokens, largest stated |
| Providers with a standard price | 2 | 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-4-31B-it-turbo and Step-3.5-Flash 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-4-31B-it-turbo | Step-3.5-Flash | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 11.63 Chutes | USD 14.40 Featherless | USD 2.77 gemma-4-31B-it-turbo lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 23.82 DeepInfra | USD 28.50 Featherless | USD 4.68 gemma-4-31B-it-turbo lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 84.06 Chutes | USD 207.00 Featherless | USD 122.94 gemma-4-31B-it-turbo lower |
gemma-4-31B-it-turbo is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 2.46× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 4 input tokens per output token, Step-3.5-Flash is cheaper; above 4, gemma-4-31B-it-turbo is cheaper. At the site's 3:1 blend, Step-3.5-Flash is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
| Input : output tokens | gemma-4-31B-it-turbo | Step-3.5-Flash |
|---|---|---|
| 1 : 3 (long answers) | USD 0.2775 DeepInfra | USD 0.25 lower Featherless |
| 1 : 1 | USD 0.215 DeepInfra | USD 0.20 lower Featherless |
| 3 : 1 (the site’s blend) | USD 0.1525 DeepInfra | USD 0.15 lower Featherless |
| 10 : 1 (retrieval, long prompts) | USD 0.1127 lower DeepInfra | USD 0.1182 Featherless |
| 30 : 1 (agents, big contexts) | USD 0.09806 lower DeepInfra | USD 0.1065 Featherless |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do gemma-4-31B-it-turbo and Step-3.5-Flash cost per character in other languages?
Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and gemma-4-31B-it-turbo and Step-3.5-Flash are not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- gemma-4-31B-it-turbo API pricing: all 2 providers and other tiers.
- Step-3.5-Flash API pricing: all 2 providers and other tiers.
- Cost calculator with gemma-4-31B-it-turbo and Step-3.5-Flash preloaded
- Gemma token counter
- Token counter
- Prompt caching calculator
More comparisons: Step 3.7 Flash vs Step-3.5-Flash · every gemma-4-31B-it-turbo comparison · every Step-3.5-Flash comparison · all 662 price comparisons
Questions
Is gemma-4-31B-it-turbo cheaper than Step-3.5-Flash?
No. On a blend of 3 input tokens to 1 output token, Step-3.5-Flash costs USD 0.15 per 1M tokens and gemma-4-31B-it-turbo USD 0.1525, at each model's cheapest standard price. For input alone, gemma-4-31B-it-turbo is cheaper (USD 0.09 against USD 0.10 per 1M); for output alone, Step-3.5-Flash is (USD 0.30 against USD 0.34). This compares price only, not quality.
What do gemma-4-31B-it-turbo and Step-3.5-Flash cost per 1M tokens?
gemma-4-31B-it-turbo: from USD 0.09 input and USD 0.34 output at DeepInfra; median of 2 standard prices USD 0.105 / USD 0.355. Step-3.5-Flash: from USD 0.10 input and USD 0.30 output at Featherless and 1 other; median of 2 standard prices USD 0.10 / USD 0.30. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both gemma-4-31B-it-turbo and Step-3.5-Flash?
None of the providers we track sells both at a standard price. gemma-4-31B-it-turbo is cheapest at DeepInfra and Step-3.5-Flash at Featherless and 1 other, so running both means two accounts.
Which is cheaper for a coding agent or a chatbot, gemma-4-31B-it-turbo or Step-3.5-Flash?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 84.06 a month on gemma-4-31B-it-turbo (Chutes) against USD 207.00 on Step-3.5-Flash (Featherless), a difference of USD 122.94. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 11.63 a month on gemma-4-31B-it-turbo (Chutes) against USD 14.40 on Step-3.5-Flash (Featherless), a difference of USD 2.77. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of gemma-4-31B-it-turbo and Step-3.5-Flash change?
The cheaper model changes with the mix: below 4 input tokens per output token, Step-3.5-Flash is cheaper; above 4, gemma-4-31B-it-turbo is cheaper. At the site's 3:1 blend, Step-3.5-Flash is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
Do gemma-4-31B-it-turbo and Step-3.5-Flash have cached input pricing?
gemma-4-31B-it-turbo from USD 0.012 per 1M cached input tokens (Chutes; 2 of 2 standard prices list a discount). Step-3.5-Flash: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, gemma-4-31B-it-turbo or Step-3.5-Flash?
Both go up to 262,144 tokens on the providers that state it.