What is Llama 3.2 11b?
Llama 3.2 11b is a language model in the o10 fulfillment catalog (slug: llama-3.2-11b). Published input pricing starts at $0.160/1M tokens. Context window: 128K tokens.
Catalog snapshot 2026-06-27.
Llama 3.2 11b costs $0.160/1M input tokens and $0.160/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 128K tokens context window. o10 lists Llama 3.2 11b on AWS Bedrock, Together AI, and Fireworks AI at routing band C2.
Last updated: 2026-06-27. Full catalog
Llama 3.2 11b — specs, hosts, and routing
AnswersSelf-contained
How much does Llama 3.2 11b cost per million tokens?
Llama 3.2 11b costs $0.160/1M input tokens and $0.160/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Where can you run Llama 3.2 11b?
Llama 3.2 11b is configured on AWS Bedrock, Together AI, and Fireworks AI. Each host maps to an upstream model ID listed in the fulfillment routes table. This model is routable through o10 eval-gated routing.
What is Llama 3.2 11b's context window?
Llama 3.2 11b supports a 128K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
What o10 routing band is Llama 3.2 11b?
Llama 3.2 11b is classified at o10 routing band C2. 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.
Who makes Llama 3.2 11b?
Llama 3.2 11b 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.
01Deep dive
Specifications
Llama 3.2 11b in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `llama-3.2-11b` |
| Type | text |
| Band | C2 |
| Routable | Yes |
| Source provider | openrouter |
| Primary host | AWS Bedrock |
| Gateway ID | `meta/llama-3.2-11b` |
| Context window | 128,000 tokens |
| Released | 2024-09-25 |
02Deep dive
Token pricing
Gateway snapshot pricing for Llama 3.2 11b.
| Unit | Price |
|---|---|
| Input | $0.16/1M tokens |
| Output | $0.16/1M tokens |
03Deep dive
Fulfillment hosts
Upstream venues configured for Llama 3.2 11b.
| Host | Upstream model ID |
|---|---|
| meta | bedrock/us.meta.llama3-2-11b-instruct-v1:0 |
| meta | together_ai/llama-3.2-11b |
| meta | fireworks_ai/llama-3.2-11b |
04Deep dive
Gateway provider endpoints
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| bedrock | $0.16 | 217ms | 10000.0% |
05Deep dive
Routing with o10
Eval-gated model selection for this slug.
o10 slug: llama-3.2-11b. Band: C2. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/economy) and [/kyi](/kyi) for governance.
SourceMethodology
Fulfillment catalog 2026-06-27. Gateway pricing joined where slug match exists.
FAQFrequently asked questions
Common questions
How much does Llama 3.2 11b cost?
Llama 3.2 11b costs $0.160/1M input tokens and $0.160/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
What is Llama 3.2 11b's context window?
Llama 3.2 11b supports 128K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Which hosts serve Llama 3.2 11b?
Llama 3.2 11b (llama-3.2-11b) is configured on: AWS Bedrock, Together AI, and Fireworks AI. Upstream model IDs are listed in the fulfillment routes section.
Is Llama 3.2 11b routable through o10?
Yes. Llama 3.2 11b is routable at band C2. Send model: "llama-3.2-11b" or use an o10 smart routing alias.
How do I call Llama 3.2 11b via o10?
Use o10 slug "llama-3.2-11b" or gateway ID "meta/llama-3.2-11b" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
How does o10 route this model?
o10 routes Llama 3.2 11b only when per-use-case evals clear at your quality floor. Band C2 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.