Llama 4 Scout 17B-16E Instruct
- Family
- Llama 4
- Released
- 2025-04-05
- Context
- 10M
- Parameters
- 109B (17B active)
- Architecture
- Mixture of Experts
- Knowledge cutoff
- 2024-08
- Specialization
- general
- Openness
- Open weights
- License
- Llama 4 CommunityRestricted
- Weights
- Unknown
- Code
- Unknown
- Training
- Pretrained
Large-scale open-source AI for social technologies.
Cheapest of 12 routes · AWS Bedrock
About
Meta's Llama 4 Scout is a 17-billion parameter mixture-of-experts model with 16 expert routing. Optimized for efficient inference on edge and cloud environments with strong multi-turn conversation capabilities. Available on Cloudflare Workers AI.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ BAgents
Q/$ AProviders(12)
Compare all 12Compare API pricing across 12 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| AWS Bedrock | $0.170 | $0.220 | Serverless Scheduled retirement: March 30, 2027 |
| DeepInfra | $0.080 | $0.300 | Serverless |
| GroqCloud | $0.110 | $0.340 | Serverless |
| Novita AI | $0.180 | $0.590 | Serverless |
| OpenRouter | $0.180 | $0.590 | Serverless |
| GCP Vertex AI | $0.200 | $0.650 | Serverless |
| Vercel AI Gateway | $0.170 | $0.660 | Serverless |
| Microsoft Foundry | $0.200 | $0.780 | Serverless |
| Cloudflare Workers AI | $0.270 | $0.850 | Serverless |
| Fireworks AI | - | - | ServerlessPartial |
| NVIDIA NIM | - | - | ServerlessPartial |
| Together AI | - | - | ServerlessPartial |
Available via routers & gateways(16)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 500+ models from 80+ providers via a single OpenAI-compatible API, with an optional Auto Router that selects a model per prompt from market spend data.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, caching, and guardrails; MIT-licensed open-source core is self-hostable. Now part of Palo Alto Networks as Prisma AIRS AI Gateway.
AIRouter
RouterCommercial LLM router (branded "AI Router" on its site) that picks the best model per request via a Decision API or an OpenAI-compatible Chat Completions endpoint, with a private selection mode that routes on anonymized patterns; sold as BYOK subscription plans priced by routed tokens.
Amazon Bedrock Intelligent Prompt Routing
RouterAWS Bedrock's native prompt router that predicts each model's performance per request and routes between two models of the same family (Anthropic Claude, Meta Llama or Amazon Nova).
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(8)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 1295.0 | —Observed 2026-04-15 | — | Source Source: LMArena (lmarena.ai), CC BY 4.0 | |
| 62.3 | τ-benchObserved 2026-04-24 | — | ||
| 69.4 | —Observed 2025-04-05 | — | ||
| 74.3 | —Observed 2025-04-05 | — | ||
| 32.8 | —Observed 2025-04-05 | — | ||
| 28.1 | v4Observed 2026-10-26 | Configuration: Llama-4-Scout-17B-16E-Instruct (FC) Harness: BFCL V4 official evaluation (gorilla berkeley-function-call-leaderboard), FC mode Evaluator: Gorilla LLM team (UC Berkeley) Confidence: confirmed Notes: BFCL V4 leaderboard (Last Updated 2026-04-12), entry 'Llama-4-Scout-17B-16E-Instruct (FC)': rank 72, Overall Acc 28.13%; Multi Turn 9.00%, Web Search 14.50%, Memory 8.17%, Non-Live AST 89.38%, Live 74.69%, Irrelevance 44.92%. Retrieved 2026-10-26. | ||
| 1128.0 | vision_style_control overall 2026-10-19 (style control, default view)Observed 2026-10-26 | Configuration: Llama 4 Scout 17B 16E Instruct Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena vision style control leaderboard, overall category, published 2026-10-19 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split; live page https://lmarena.ai/leaderboard/vision showed the same 2026-10-19 snapshot). Board entry 'Llama 4 Scout 17B 16E Instruct': rank 127, Arena Score 1127.5 (95% CI 1118.0-1137.0), 6446 votes. Versioned arena label mapped to catalog slug llama-4-scout-17b-16e-instruct (label date equals the model's release checkpoint). Retrieved 2026-10-26. | Source Source: LMArena (lmarena.ai), CC BY 4.0 | |
| 1249.0 | text creative_writing 2026-10-22Observed 2026-10-22 | Configuration: Llama 4 Scout 17B 16E Instruct Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 4 Scout 17B 16E Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 270 of 416, rating 1248.7 (95% CI 1238.7-1258.7), 3759 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27. | Source Source: LMArena (lmarena.ai), CC BY 4.0 |
Migration checks
No linked migration route is available for this model yet.
Compare Llama 4 Scout 17B-16E Instruct with other models
- Llama 4 Scout 17B-16E Instruct vs Llama 4 Maverick 17B Instruct FP8124
- Llama 4 Scout 17B-16E Instruct vs Grok 4.370
- Llama 4 Scout 17B-16E Instruct vs GPT-4o Mini (07-18)22
- Llama 4 Scout 17B-16E Instruct vs Mistral Small 3.1 24B Instruct21
- Llama 4 Scout 17B-16E Instruct vs Grok 419
- Llama 4 Scout 17B-16E Instruct vs Mistral Small 414
- Llama 4 Scout 17B-16E Instruct vs Gemini 2.5 Flash10
- Llama 4 Scout 17B-16E Instruct vs Claude 3.5 Haiku7
Comparison and alternatives
Browse all comparisons →Large-scale open-source AI for social technologies.
Cheapest of 12 routes · AWS Bedrock