Llama 4 Maverick 17B Instruct FP8 vs Llama 4 Scout 17B-16E Instruct
Llama 4 Maverick 17B Instruct FP8 (2025) and Llama 4 Scout 17B-16E Instruct (2025) are general-purpose language models from AI at Meta. Llama 4 Maverick 17B Instruct FP8 ships a 1m-token context window, while Llama 4 Scout 17B-16E Instruct ships a 10m-token context window. On MMLU PRO, Llama 4 Maverick 17B Instruct FP8 leads by 6.2 pts. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
Llama 4 Scout 17B-16E Instruct is ~87% cheaper at $0.08/1M; pay for Llama 4 Maverick 17B Instruct FP8 only for vision-heavy evaluation.
Decision scorecard
Local evidence first| Signal | Llama 4 Maverick 17B Instruct FP8 | Llama 4 Scout 17B-16E Instruct |
|---|---|---|
| Best for | multimodal apps, long-context analysis, and provider-routed production | multimodal apps, long-context analysis, and provider-routed production |
| Decision fit | Coding, RAG, and Agents | Coding, RAG, and Agents |
| Context window | 1m | 10m |
| Cheapest output | $0.60/1M tokens | $0.30/1M tokens |
| Provider routes | 10 tracked | 12 tracked |
| Shared benchmarks | MMLU PRO leader | 5 shared |
Decision tradeoffs
- Llama 4 Maverick 17B Instruct FP8 holds a shared-benchmark lead on MMLU PRO, ahead by 6.2 points.
- Local decision data tags Llama 4 Maverick 17B Instruct FP8 for Coding, RAG, and Agents.
- Llama 4 Scout 17B-16E Instruct has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Llama 4 Scout 17B-16E Instruct has the lower cheapest tracked output price at $0.30/1M tokens.
- Llama 4 Scout 17B-16E Instruct has broader tracked provider coverage for fallback and procurement flexibility.
- Local decision data tags Llama 4 Scout 17B-16E Instruct for Coding, RAG, and Agents.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Llama 4 Maverick 17B Instruct FP8
$270
Cheapest tracked route/tier: OpenRouter
Llama 4 Scout 17B-16E Instruct
$139
Cheapest tracked route/tier: OpenRouter
Estimated monthly gap: $131. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on OpenRouter, Together AI, and Fireworks AI; start route-level A/B tests there.
- Llama 4 Scout 17B-16E Instruct is $0.30/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Provider overlap exists on Microsoft Foundry, Together AI, and OpenRouter; start route-level A/B tests there.
- Llama 4 Maverick 17B Instruct FP8 is $0.30/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
Specs
| Specification | ||
|---|---|---|
| Released | 2025-04-05 | 2025-04-05 |
| Context window | 1m | 10m |
| Parameters | 400B (17B active) | 109B (17B active) |
| Architecture | Mixture of Experts | Mixture of Experts |
| License | Llama 4 Community | Llama 4 Community |
| Openness | Open weights | Open weights |
| Commercial use | Commercial use with conditions | Commercial use with conditions |
| Knowledge cutoff | 2024-08 | 2024-08 |
Pricing and availability
| Pricing attribute | Llama 4 Maverick 17B Instruct FP8 | Llama 4 Scout 17B-16E Instruct |
|---|---|---|
| Input price | $0.15/1M tokens | $0.08/1M tokens |
| Output price | $0.60/1M tokens | $0.30/1M tokens |
| Providers |
Capabilities
| Capability | Llama 4 Maverick 17B Instruct FP8 | Llama 4 Scout 17B-16E Instruct |
|---|---|---|
| Vision | Yes | Yes |
| Multimodal | Yes | Yes |
| Reasoning | No | No |
| Function calling | No | No |
| Tool use | No | No |
| Structured outputs | Yes | Yes |
| Code execution | No | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
| Benchmark | Llama 4 Maverick 17B Instruct FP8 | Llama 4 Scout 17B-16E Instruct |
|---|---|---|
| MMLU PRO | 80.5 | 74.3 |
| LiveCodeBench | 43.4 | 32.8 |
| Massive Multi-discipline Multimodal Understanding | 73.4 | 69.4 |
| Chatbot Arena | 1365.0 | 1295.0 |
| τ-bench | 68.5 | 62.3 |
Deep dive
On shared benchmark coverage, MMLU PRO has Llama 4 Maverick 17B Instruct FP8 at 80.5 and Llama 4 Scout 17B-16E Instruct at 74.3, with Llama 4 Maverick 17B Instruct FP8 ahead by 6.2 points; LiveCodeBench has Llama 4 Maverick 17B Instruct FP8 at 43.4 and Llama 4 Scout 17B-16E Instruct at 32.8, with Llama 4 Maverick 17B Instruct FP8 ahead by 10.6 points; Massive Multi-discipline Multimodal Understanding has Llama 4 Maverick 17B Instruct FP8 at 73.4 and Llama 4 Scout 17B-16E Instruct at 69.4, with Llama 4 Maverick 17B Instruct FP8 ahead by 4 points. The largest visible gap is 10.6 points on LiveCodeBench, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.
The capability footprint is close: both models cover vision, multimodal input, and structured outputs. That makes context budget, benchmark fit, and provider maturity more important than a simple checklist. If your application depends on one integration detail, verify it against the provider route you plan to use, not just the base model listing.
For cost, Llama 4 Maverick 17B Instruct FP8 lists $0.15/1M input and $0.60/1M output tokens on the cheapest tracked provider, while Llama 4 Scout 17B-16E Instruct lists $0.08/1M input and $0.30/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Llama 4 Scout 17B-16E Instruct lower by about $0.14 per million blended tokens. Availability is 10 providers versus 12, so concentration risk also matters.
Choose Llama 4 Maverick 17B Instruct FP8 when vision-heavy evaluation are central to the workload. Choose Llama 4 Scout 17B-16E Instruct when long-context analysis, larger context windows, and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.
FAQ
Which has a larger context window, Llama 4 Maverick 17B Instruct FP8 or Llama 4 Scout 17B-16E Instruct?
Llama 4 Scout 17B-16E Instruct supports 10m tokens, while Llama 4 Maverick 17B Instruct FP8 supports 1m tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.
Which is cheaper, Llama 4 Maverick 17B Instruct FP8 or Llama 4 Scout 17B-16E Instruct?
Llama 4 Scout 17B-16E Instruct is cheaper on tracked token pricing. Llama 4 Maverick 17B Instruct FP8 costs $0.15/1M input and $0.60/1M output tokens. Llama 4 Scout 17B-16E Instruct costs $0.08/1M input and $0.30/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is Llama 4 Maverick 17B Instruct FP8 or Llama 4 Scout 17B-16E Instruct open source?
Llama 4 Maverick 17B Instruct FP8 is listed under Llama 4 Community. Llama 4 Scout 17B-16E Instruct is listed under Llama 4 Community. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for vision, Llama 4 Maverick 17B Instruct FP8 or Llama 4 Scout 17B-16E Instruct?
Both Llama 4 Maverick 17B Instruct FP8 and Llama 4 Scout 17B-16E Instruct expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.
Which is better for multimodal input, Llama 4 Maverick 17B Instruct FP8 or Llama 4 Scout 17B-16E Instruct?
Both Llama 4 Maverick 17B Instruct FP8 and Llama 4 Scout 17B-16E Instruct expose multimodal input. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.
Where can I run Llama 4 Maverick 17B Instruct FP8 and Llama 4 Scout 17B-16E Instruct?
Llama 4 Maverick 17B Instruct FP8 is available on Microsoft Foundry, Together AI, OpenRouter, Fireworks AI, and DeepInfra. Llama 4 Scout 17B-16E Instruct is available on Cloudflare Workers AI, OpenRouter, Together AI, Fireworks AI, and DeepInfra. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-06-15. Data sourced from public model cards and provider documentation.