LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Llama 4 Scout 17B Instruct

meta·meta/llama-4-scout-17b-instruct·GA·Open weights·llama series
Open Llama with long-context vision for efficient multimodal agents

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·HeliconeGateway
$0.08 / $0.30
Blended $0.14 · 9× spread
Context
192,000
Output limit
16,384
Knowledge cutoff
2024-08
Released / updated
2025-04-05 / 2025-04-05
Capabilities
Reasoning✓ Tool useStructured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage
Weights
Hugging Face

Llama 4 Scout 17B Instruct by meta is offered by 15 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Helicone at $0.08 / $0.30 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 9.0× across the providers that host it.

Median output speed is 126 tokens per second, with 0.75s to the first token.

The context window is 192,000 tokens at the reference host, but hosts report different limits, from 8,192 to 10,000,000, so the usable window depends on the provider you pick. It supports tool use. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-08.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed126 tok/s
TTFT0.75 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 15 providers15 with public prices

  • ProviderInput / Output
  • HeliconeGateway
    llama-4-scout
    $0.08 / $0.30
    Context 131,072 ⚠Output limit 8,192
  • OpenRouterGateway
    meta-llama/llama-4-scout
    $0.10 / $0.30
    Context 327,680 ⚠Output limit 16,384
  • Kilo GatewayGateway
    meta-llama/llama-4-scout
    $0.10 / $0.30
    Context 327,680 ⚠Output limit 16,384
  • Deep InfraCloud
    meta-llama/Llama-4-Scout-17B-16E-Instruct
    $0.10 / $0.30
    Context 327,680 ⚠Output limit 16,384
  • NanoGPTGateway
    meta-llama/llama-4-scout
    $0.085 / $0.46
    Cache read $0.043Context 328,000 ⚠Output limit 65,536
  • LLM GatewayGateway
    $0.18 / $0.59
    Context 131,072 ⚠Output limit 131,072
  • DevPass (LLM Gateway)Gateway
    $0.18 / $0.59
    Context 131,072 ⚠Output limit 2,048
  • Novita AIGateway
    meta-llama/llama-4-scout-17b-16e-instruct
    $0.18 / $0.59
    Context 131,072 ⚠Output limit 131,072
  • LLM GatewayGateway
    $0.17 / $0.66
    Context 8,192 ⚠Output limit 2,048deprecated
  • Amazon BedrockCloud
    meta.llama4-scout-17b-instruct-v1:0
    $0.17 / $0.66
    Context 10,000,000 ⚠Output limit 8,192deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Helicone
llama-4-scout
Gateway$0.08$0.30——131,072 ⚠8,192
OpenRouter
meta-llama/llama-4-scout
Gateway$0.10$0.30——327,680 ⚠16,384
Kilo Gateway
meta-llama/llama-4-scout
Gateway$0.10$0.30——327,680 ⚠16,384
Deep Infra
meta-llama/Llama-4-Scout-17B-16E-Instruct
Cloud$0.10$0.30——327,680 ⚠16,384
NanoGPT
meta-llama/llama-4-scout
Gateway$0.085$0.46$0.043—328,000 ⚠65,536
LLM GatewayGateway$0.18$0.59——131,072 ⚠131,072
DevPass (LLM Gateway)Gateway$0.18$0.59——131,072 ⚠2,048
Novita AI
meta-llama/llama-4-scout-17b-16e-instruct
Gateway$0.18$0.59——131,072 ⚠131,072
LLM GatewayGateway$0.17$0.66——8,192 ⚠2,048deprecated
Amazon Bedrock
meta.llama4-scout-17b-instruct-v1:0
Cloud$0.17$0.66——10,000,000 ⚠8,192deprecated

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1Helicone$31.00
2NanoGPT$34.90
3OpenRouter$35.00
4Kilo Gateway$35.00
5Deep Infra$35.00
6LLM Gateway$65.50
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.28$02026-08-052026-11-18
2026-11-18Input list —Output list —Min blended $0.14

Artificial Analysis evaluations18 items

GPQA Diamond58.7%
Humanity's Last Exam3.8%
MMMU-Pro52.9%
CritPt0.0%
SciCode21.3%
LiveCodeBench29.9%
Terminal-Bench Hard1.5%
Terminal-Bench 2.13.8%
Terminal-Bench 4.00.0%
AIME 202514.0%
τ²-Bench Telecom15.5%
τ³-Bench Banking3.3%
AutomationBench-AA0.2%
AA-Briefcase0
GDPval-AA-156
GDP.pdf0.0%
AA-LCR27.7%
IFBench39.5%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Omega Directive 24B Unslop v2.0same series—EVA-LLaMA-3.33-70B-v0.1same series—Llama 3.3 70B Instruct abliteratedsame series—Llama 4 Maverick 17B Instructsame lab—Llama-Guard-3-8Bsame lab—
Data partly from models.dev (MIT)