Llama 4 Scout on Groq
Current Groq-hosted Llama 4 family for better open-model reasoning and tool use.
- Input
- $0.11 / 1M tokens
- Output
- $0.34 / 1M tokens
- Cached read
- — / 1M tokens
- Cached write
- — / 1M tokens
- Batch discount
- —%
- Source
- Llama 4 Scout on Groq pricing
- Verified
- Apr 2, 2026 (High)
Capabilities
- Modalities
- textimage→text
- Capabilities
- reasoningimageInputbatchSupportpromptCachingfunctionCallingstructuredOutputs
- Strengths
- Modern open-model tier, Still relatively cheap
- Tradeoffs
- Open-model ceiling below hosted frontier APIs
Official Links
Benchmark Coverage
| Benchmark | Version | Score | Date | Source | Notes |
|---|
Release History
| Release | Alias | Lifecycle | Release Date | Deprecation | Shutdown | Summary |
|---|---|---|---|---|---|---|
| Llama 4 Scout on Groq | groq-llama-4-scout | Active | Jun 1, 2025 | — | — | Current published model family snapshot. |
Host Coverage
| Host | Type | Context | Pricing Note | Differences |
|---|---|---|---|---|
| Groq API | first-party | 131.1K | Reference production Groq pricing. | Image input |
Migration Guidance
Open-model upgrade from Llama 3.x tiers for better reasoning and multimodal input.
Replacement models: groq-llama-3-3-70b-versatile
Change Events
| Date | Type | Title | Description | Source |
|---|---|---|---|---|
| Jun 1, 2025 | family_added | Llama 4 Scout on Groq published | Initial public model family launch. | Llama 4 Scout on Groq release notes |
Other models from Groq
GPT-OSS 120B on Groq, GPT-OSS 20B on Groq, Groq Compound, Llama 3.1 8B Instant on Groq, Llama 3.3 70B Versatile on Groq, Qwen3 32B on Groq