Llama 4 Scout vs Step-3.5-Flash API pricing
Updated
Llama 4 Scout's lowest standard price we found is USD 0.10 per 1M input tokens and USD 0.30 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 they cost the same, USD 0.15 per 1M tokens.
How do Llama 4 Scout and Step-3.5-Flash differ on price?
- Cheapest input price: Llama 4 Scout USD 0.08 against USD 0.10 per 1M tokens, so Step-3.5-Flash costs 1.25× as much (25% more).
- Cheapest output price: both USD 0.30 per 1M tokens.
- Among the 201 indexed models, Llama 4 Scout ranks 40th cheapest and Step-3.5-Flash 40th on the 3:1 blend (the same rank).
- The cheaper model changes at 10 input tokens per output token.
- Neither model has a standard price with a cached-input discount, so prompt caching does not lower either bill.
- Llama 4 Scout states up to 1,048,576 tokens of context, 4× the 262,144 of Step-3.5-Flash.
- Llama 4 Scout has 6 providers with a standard price, 4 more than Step-3.5-Flash; no provider sells both, so using both means two accounts.
- Shopping around matters more for Llama 4 Scout: its dearest standard price is 2.8× its cheapest, against 1× for Step-3.5-Flash.
- Llama 4 Scout has a batch price at 2 providers, from USD 0.1462 at 3:1 (Amazon Bedrock); Step-3.5-Flash has no batch price on file.
- For the one-developer coding agent preset, the gap is USD 216.00 a year in Llama 4 Scout's favour (Llama 4 Scout USD 189.00 a month, Step-3.5-Flash USD 207.00).
Llama 4 Scout 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 | Llama 4 Scout | Step-3.5-Flash |
|---|---|---|
| Model page | Llama 4 Scout 17B 16E Instruct Meta · 6 providers | Step-3.5-Flash StepFun · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.15 tie USD 0.10 in / USD 0.30 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 0.15 tie USD 0.10 in / USD 0.30 out at Featherless and 1 other Featherless page checked 2026-11-15 |
| Cheapest input | USD 0.08 lower GMI Cloud source | USD 0.10 Featherless source |
| Cheapest cached input | No standard price lists a cache price; cached tokens bill at the input price. | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 0.30 tie DeepInfra source | USD 0.30 tie Featherless source |
| Maker's own API | Meta 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 0.175 / USD 0.625 input / output, 6 prices | USD 0.10 / USD 0.30 input / output, 2 prices |
| Context window | 1,048,576 tokens, largest stated; from 131,072 at some providers | 262,144 tokens, largest stated |
| Providers with a standard price | 6 | 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 Llama 4 Scout 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 | Llama 4 Scout | Step-3.5-Flash | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 14.40 DeepInfra | USD 14.40 Featherless | same |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 26.70 GMI Cloud | USD 28.50 Featherless | USD 1.80 Llama 4 Scout lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 189.00 GMI Cloud | USD 207.00 Featherless | USD 18.00 Llama 4 Scout lower |
Llama 4 Scout is cheaper on 2 workloads. The widest gap is on Coding agent (one developer): the dearer model costs 9.5% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 10 input tokens per output token, they cost the same; above 10, Llama 4 Scout is cheaper. At the site's 3:1 blend, they cost the same. 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 | Llama 4 Scout | Step-3.5-Flash |
|---|---|---|
| 1 : 3 (long answers) | USD 0.25 tie DeepInfra | USD 0.25 tie Featherless |
| 1 : 1 | USD 0.20 tie DeepInfra | USD 0.20 tie Featherless |
| 3 : 1 (the site’s blend) | USD 0.15 tie DeepInfra | USD 0.15 tie Featherless |
| 10 : 1 (retrieval, long prompts) | USD 0.1182 tie DeepInfra | USD 0.1182 tie Featherless |
| 30 : 1 (agents, big contexts) | USD 0.09355 lower GMI Cloud | 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 Llama 4 Scout 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 Step-3.5-Flash is not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- Llama 4 Scout 17B 16E Instruct API pricing: all 6 providers and other tiers.
- Step-3.5-Flash API pricing: all 2 providers and other tiers.
- Cost calculator with Llama 4 Scout and Step-3.5-Flash preloaded
- Llama 4 token counter
- Token counter
- Prompt caching calculator
More comparisons: Llama 4 Scout vs Gemma 4 31B · Step 3.7 Flash vs Step-3.5-Flash · every Llama 4 Scout comparison · every Step-3.5-Flash comparison · all 662 price comparisons
Questions
Is Llama 4 Scout cheaper than Step-3.5-Flash?
Not on price: on a blend of 3 input tokens to 1 output token they tie at USD 0.15 per 1M tokens. For input alone, Llama 4 Scout is cheaper (USD 0.08 against USD 0.10 per 1M); for output alone, both start at USD 0.30. This compares price only, not quality.
What do Llama 4 Scout and Step-3.5-Flash cost per 1M tokens?
Llama 4 Scout: from USD 0.10 input and USD 0.30 output at DeepInfra; median of 6 standard prices USD 0.175 / USD 0.625. 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 Llama 4 Scout and Step-3.5-Flash?
None of the providers we track sells both at a standard price. Llama 4 Scout 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, Llama 4 Scout 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 189.00 a month on Llama 4 Scout (GMI Cloud) against USD 207.00 on Step-3.5-Flash (Featherless), a difference of USD 18.00. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 14.40 a month on Llama 4 Scout (DeepInfra) against USD 14.40 on Step-3.5-Flash (Featherless), the same. 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 Llama 4 Scout and Step-3.5-Flash change?
The cheaper model changes with the mix: below 10 input tokens per output token, they cost the same; above 10, Llama 4 Scout is cheaper. At the site's 3:1 blend, they cost the same. 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 Llama 4 Scout and Step-3.5-Flash have cached input pricing?
Llama 4 Scout: no standard price lists a cached-input 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, Llama 4 Scout or Step-3.5-Flash?
Llama 4 Scout: up to 1,048,576 tokens, against 262,144 for Step-3.5-Flash, 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.