Llama 4 Scout costs $0.170/1M input tokens and $0.660/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 128K tokens context window. o10 lists Llama 4 Scout on AWS Bedrock, Together AI, and Fireworks AI at routing band C3. API slug llama-4-scout. Verify list prices against the venue you call.
Last updated: 2026-06-27. Full catalog. Reference prices are dated snapshots. Compare total cost and measured task quality before choosing a route.
Llama 4 Scout is a chat model from openrouter (slug: llama-4-scout). Pick Llama 4 Scout when you want Meta Llama on a fulfillment host (or your own GPUs) instead of a closed lab SKU. Published input pricing starts at $0.170/1M tokens. Context window: 128K tokens.
Catalog snapshot 2026-06-27.
Pick Llama 4 Scout when you want Meta Llama on a fulfillment host (or your own GPUs) instead of a closed lab SKU. Llama 4 Scout is a Llama instruct checkpoint. Smaller Llama SKUs cut cost; larger ones raise quality. Prove the swap in shadow.
Llama 4 Scout is a Llama instruct checkpoint. Smaller Llama SKUs cut cost; larger ones raise quality. Prove the swap in shadow.
Llama 4 Scout costs $0.170/1M input tokens and $0.660/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Llama 4 Scout is configured on AWS Bedrock, Together AI, and Fireworks AI. Known host IDs: meta: bedrock/us.meta.llama4-scout-17b-instruct-v1:0; meta: together_ai/llama-4-scout; meta: fireworks_ai/llama-4-scout. This model is routable through o10 eval-gated routing.
Llama 4 Scout supports a 128K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
Llama 4 Scout is classified at o10 routing band C3. Bands group models by cost tier and eval profile: C0 (economy), C1 (standard), C2 (capable), C3/C4 (frontier). Production routing is enabled for this slug.
Llama 4 Scout is attributed to source provider openrouter in the o10 catalog. Fulfillment hosts (AWS Bedrock, Together AI, and Fireworks AI) supply API access; list pricing may differ by venue.
Llama 4 Scout in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `llama-4-scout` |
| Type | text |
| Band | C3 |
| Routable | Yes |
| Source provider | openrouter |
| Primary host | AWS Bedrock |
| Gateway ID | `meta/llama-4-scout` |
| Context window | 128,000 tokens |
| Released | 2025-04-05 |
Gateway snapshot pricing for Llama 4 Scout.
| Unit | Price |
|---|---|
| Input | $0.17/1M tokens |
| Output | $0.66/1M tokens |
Upstream venues configured for Llama 4 Scout.
| Host | Upstream model ID |
|---|---|
| meta | bedrock/us.meta.llama4-scout-17b-instruct-v1:0 |
| meta | together_ai/llama-4-scout |
| meta | fireworks_ai/llama-4-scout |
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| bedrock | $0.17 | 231.5ms | 10000.0% |
| deepinfra | $0.1 | 204ms | 10000.0% |
| groq | $0.11 | 168.5ms | 10000.0% |
Eval-gated model selection for this slug.
o10 slug: llama-4-scout. Band: C3. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/frontier, o10/squad) and [/kyi](/kyi) for governance.
Fulfillment catalog 2026-06-27. Gateway pricing joined where slug match exists.
Llama 4 Scout costs $0.170/1M input tokens and $0.660/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
Llama 4 Scout supports 128K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Llama 4 Scout (llama-4-scout) is configured on: AWS Bedrock, Together AI, and Fireworks AI. Upstream model IDs are listed in the fulfillment routes section.
Yes. Llama 4 Scout is routable at band C3. Send model: "llama-4-scout" or use an o10 smart routing alias.
Use o10 slug "llama-4-scout" or gateway ID "meta/llama-4-scout" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes Llama 4 Scout only when per-use-case evals clear at your quality floor. Band C3 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.