Llama 3.1 8b costs $0.220/1M input tokens and $0.220/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 128K tokens context window. o10 lists Llama 3.1 8b on AWS Bedrock, Together AI, and Fireworks AI at routing band C2. API slug llama-3.1-8b. 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 3.1 8b is a chat model from openrouter (slug: llama-3.1-8b). Pick Llama 3.1 8b when you want Meta Llama on a fulfillment host (or your own GPUs) instead of a closed lab SKU. Published input pricing starts at $0.220/1M tokens. Context window: 128K tokens.
Catalog snapshot 2026-06-27.
Pick Llama 3.1 8b when you want Meta Llama on a fulfillment host (or your own GPUs) instead of a closed lab SKU. Llama 3.1 8b is a Llama instruct checkpoint. Smaller Llama SKUs cut cost; larger ones raise quality. Prove the swap in shadow.
Llama 3.1 8b is a Llama instruct checkpoint. Smaller Llama SKUs cut cost; larger ones raise quality. Prove the swap in shadow.
Llama 3.1 8b costs $0.220/1M input tokens and $0.220/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Llama 3.1 8b is configured on AWS Bedrock, Together AI, and Fireworks AI. Known host IDs: meta: bedrock/us.meta.llama3-1-8b-instruct-v1:0; meta: together_ai/meta-llama/Llama-3.1-8B-Instruct-Turbo; meta: fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct. This model is routable through o10 eval-gated routing.
Llama 3.1 8b supports a 128K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
Llama 3.1 8b 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.
Llama 3.1 8b 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 3.1 8b in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `llama-3.1-8b` |
| Type | text |
| Band | C2 |
| Routable | Yes |
| Source provider | openrouter |
| Primary host | AWS Bedrock |
| Gateway ID | `meta/llama-3.1-8b` |
| Context window | 128,000 tokens |
| Released | 2024-07-23 |
Gateway snapshot pricing for Llama 3.1 8b.
| Unit | Price |
|---|---|
| Input | $0.22/1M tokens |
| Output | $0.22/1M tokens |
Upstream venues configured for Llama 3.1 8b.
| Host | Upstream model ID |
|---|---|
| meta | bedrock/us.meta.llama3-1-8b-instruct-v1:0 |
| meta | together_ai/meta-llama/Llama-3.1-8B-Instruct-Turbo |
| meta | fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct |
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| bedrock | $0.22 | 191ms | 10000.0% |
| deepinfra | $0.03 | 265ms | 10000.0% |
| groq | $0.05 | 105ms | 10000.0% |
| novita | $0.02 | 599ms | 10000.0% |
Eval-gated model selection for this slug.
o10 slug: llama-3.1-8b. Band: C2. 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 3.1 8b costs $0.220/1M input tokens and $0.220/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
Llama 3.1 8b supports 128K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Llama 3.1 8b (llama-3.1-8b) is configured on: AWS Bedrock, Together AI, and Fireworks AI. Upstream model IDs are listed in the fulfillment routes section.
Yes. Llama 3.1 8b is routable at band C2. Send model: "llama-3.1-8b" or use an o10 smart routing alias.
Use o10 slug "llama-3.1-8b" or gateway ID "meta/llama-3.1-8b" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes Llama 3.1 8b 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.