What is Llama2 70b?
Llama2 70b is a chat model from meta (slug: meta-llama2-70b). Pick Llama2 70b when you want Meta Llama on a fulfillment host (or your own GPUs) instead of a closed lab SKU.
Catalog snapshot 2026-06-27.
Llama2 70b is listed in the o10 fulfillment catalog as of 2026-06-27. Meta publishes this model without a published context window in this snapshot. o10 lists Llama2 70b on NVIDIA NIM at routing band C2. API slug meta-llama2-70b. 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.
Llama2 70b. Specs, hosts, and routing
Snapshot
No list price in snapshot
Spec
meta · context varies by host · band C2
On this page
AnswersSelf-contained
When should you pick Llama2 70b?
Pick Llama2 70b when you want Meta Llama on a fulfillment host (or your own GPUs) instead of a closed lab SKU. Llama2 70b is a Llama instruct checkpoint. Smaller Llama SKUs cut cost; larger ones raise quality. Prove the swap in shadow.
How does Llama2 70b differ from sibling models?
Llama2 70b is a Llama instruct checkpoint. Smaller Llama SKUs cut cost; larger ones raise quality. Prove the swap in shadow.
How much does Llama2 70b cost per million tokens?
Llama2 70b does not have published per-token pricing in the current gateway snapshot. See fulfillment hosts below for routing options.
Pricing unavailable in current snapshot.
Where can you run Llama2 70b?
Llama2 70b is configured on NVIDIA NIM. Known host IDs: nvidia_nim: nvidia_nim/meta/llama2-70b. This model is routable through o10 eval-gated routing.
What is Llama2 70b's context window?
Llama2 70b context limits depend on the fulfillment host. Check the specifications table for endpoint-specific limits.
What o10 routing band is Llama2 70b?
Llama2 70b 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 Llama2 70b?
Llama2 70b is attributed to source provider meta in the o10 catalog. Fulfillment hosts (NVIDIA NIM) supply API access; list pricing may differ by venue.
01Deep dive
Specifications
Llama2 70b in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `meta-llama2-70b` |
| Type | text |
| Band | C2 |
| Routable | Yes |
| Source provider | meta |
| Primary host | NVIDIA NIM |
02Deep dive
Fulfillment hosts
Upstream venues configured for Llama2 70b.
| Host | Upstream model ID |
|---|---|
| nvidia_nim | nvidia_nim/meta/llama2-70b |
03Deep dive
Routing with o10
Eval-gated model selection for this slug.
o10 slug: meta-llama2-70b. Band: C2. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/frontier, o10/squad) 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 Llama2 70b cost?
Llama2 70b has no published per-token price in the current gateway snapshot. Use the fulfillment hosts table to identify available venues.
What is Llama2 70b's context window?
Context limits for Llama2 70b vary by fulfillment host. See the specifications table on this page.
Which hosts serve Llama2 70b?
Llama2 70b (meta-llama2-70b) is configured on: NVIDIA NIM. Upstream model IDs are listed in the fulfillment routes section.
Is Llama2 70b routable through o10?
Yes. Llama2 70b is routable at band C2. Send model: "meta-llama2-70b" or use an o10 smart routing alias.
How do I call Llama2 70b via o10?
Use o10 slug "meta-llama2-70b" in the model field. See /models/routing for smart aliases (o10/auto, o10/frontier, o10/squad).
How does o10 route this model?
o10 routes Llama2 70b 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.