Meta API pricing by model
Updated
BroadRouter tracks API prices for 25 Meta models, 12 of them listed by 2 or more providers. In our snapshot of 2026-11-14, the lowest listed input price is USD 0.02 per 1M tokens, for Llama 3.1 8B Instruct at DeepInfra. Meta sells no API of its own for them. BroadRouter is BroadNet's site.
- Models priced
- 25
- Listed by 2+ providers
- 12
- Providers
- 17
- Lowest listed input / output
- USD 0.02 / USD 0.03
Meta models and their lowest listed prices
The first 12 models have a standard price from 2 or more providers; the other 13 have one provider so far. USD per 1M tokens, standard tier. The input and output columns can come from different providers.
| Model | Providers | Lowest listed input | Lowest listed output | Maker's own API in / out | Checked |
|---|---|---|---|---|---|
| Llama 3.3 70B | 14 | USD 0.10 DeepInfra | USD 0.32 DeepInfra | — | 2026-11-15 |
| Llama 4 Maverick 17B 128E Instruct FP8 | 7 | USD 0.24 Amazon Bedrock | USD 0.80 GMI Cloud | — | 2026-11-15 |
| Llama 3.1 8B Instruct | 6 | USD 0.02 DeepInfra | USD 0.04 DeepInfra | — | 2026-11-15 |
| Llama 4 Scout 17B 16E Instruct | 6 | USD 0.08 GMI Cloud | USD 0.30 DeepInfra | — | 2026-11-15 |
| Llama 3.2 3B Instruct | 4 | USD 0.0509 Featherless | USD 0.15 Amazon Bedrock | — | 2026-11-15 |
| Muse Spark Open | 4 | USD 1.25 Baseten | USD 4.25 Baseten | — | 2026-11-15 |
| Llama 3 8B Instruct | 3 | USD 0.0925 Featherless | USD 0.095 Featherless | — | 2026-11-15 |
| Llama 3.1 Instruct (70B) | 3 | USD 0.293 Cloudflare Workers AI | USD 0.72 Amazon Bedrock | — | 2026-11-15 |
| Llama 3.2 11B Vision Instruct | 3 | USD 0.049 Cloudflare Workers AI | USD 0.16 Amazon Bedrock | — | 2026-11-15 |
| Llama 3.2 1B Instruct | 3 | USD 0.027 Cloudflare Workers AI | USD 0.10 Amazon Bedrock | — | 2026-11-15 |
| Muse Glimmer 30B | 3 | USD 0.30 Featherless | USD 1.10 Featherless | — | 2026-11-15 |
| Llama 3 Instruct (70B) | 2 | USD 2.65 Amazon Bedrock | USD 3.50 Amazon Bedrock | — | 2026-11-15 |
| Llama 2 7B Chat (fp16) | 1 (single) | USD 0.556 Cloudflare Workers AI | USD 6.667 Cloudflare Workers AI | — | 2026-11-14 |
| Llama 2 Chat (13B) | 1 (single) | USD 0.75 Amazon Bedrock | USD 1 Amazon Bedrock | — | 2026-11-14 |
| Llama 2 Chat (70B) | 1 (single) | USD 1.95 Amazon Bedrock | USD 2.56 Amazon Bedrock | — | 2026-11-14 |
| Llama 3 8B Instruct (AWQ) | 1 (single) | USD 0.123 Cloudflare Workers AI | USD 0.266 Cloudflare Workers AI | — | 2026-11-14 |
| Llama 3.1 8B Instruct (AWQ) | 1 (single) | USD 0.123 Cloudflare Workers AI | USD 0.266 Cloudflare Workers AI | — | 2026-11-14 |
| Llama 3.1 8B Instruct (fp8-fast) | 1 (single) | USD 0.045 Cloudflare Workers AI | USD 0.384 Cloudflare Workers AI | — | 2026-11-14 |
| Llama 3.1 8B Instruct (fp8) | 1 (single) | USD 0.152 Cloudflare Workers AI | USD 0.287 Cloudflare Workers AI | — | 2026-11-14 |
| Llama 3.2 Instruct (90B) | 1 (single) | USD 0.72 Amazon Bedrock | USD 0.72 Amazon Bedrock | — | 2026-11-14 |
| Llama Guard 3 8B | 1 (single) | USD 0.484 Cloudflare Workers AI | USD 0.03 Cloudflare Workers AI | — | 2026-11-14 |
| Llama-Guard-4-12B | 1 (single) | USD 0.18 DeepInfra | USD 0.18 DeepInfra | — | 2026-11-14 |
| Muse Ember 1.0 | 1 (single) | USD 0.10 Google Vertex AI | USD 0.50 Google Vertex AI | — | 2026-11-14 |
| Muse Spark 1.3 | 1 (single) | USD 1.25 Google Vertex AI | USD 4.25 Google Vertex AI | — | 2026-11-14 |
| Muse Wonder 1.0 | 1 (single) | USD 4 Google Vertex AI | USD 20 Google Vertex AI | — | 2026-11-14 |
"Lowest listed": the lowest standard, non-free price for the model in our snapshot, with the provider that lists it. Free rows and batch, flex, priority and fast tiers are on each model page but not in these columns. "Single": one provider so far; those pages are kept out of search results until a second provider lists the model. "Checked": the newest check date of the model's prices.
Where can you buy the Meta API?
Meta does not sell Llama models through an API of its own: llama.com now redirects to Meta's developer site, whose Model API lists only Meta's Muse models. Llama is available only from third-party hosts. 17 providers in our data list at least one Meta model: Cloudflare Workers AI (14), Amazon Bedrock (13), Featherless (8), Google Vertex AI (6), DeepInfra (5), Novita AI (4), GMI Cloud (3), IBM watsonx.ai (3), Venice (3), CoreWeave Forge (2), and 7 more.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
All model makers · All models: API prices compared · Prices by provider · LLM API cost calculator
Questions
How many Meta models does BroadRouter track?
25 Meta models have a standard per-token price from at least one provider in our data, read from 17 providers' own pricing pages (newest check 2026-11-15). 12 of them are listed by 2 or more providers; the other 13 have one provider so far, and their pages are kept out of search results.
Which Meta model has the lowest listed input price on 2026-11-14?
In our snapshot of 2026-11-14, Llama 3.1 8B Instruct at DeepInfra: USD 0.02 input and USD 0.04 output per 1M tokens, standard tier. The lowest listed output price is USD 0.03 per 1M tokens, for Llama Guard 3 8B at Cloudflare Workers AI (checked 2026-11-14). Free rows, and batch, flex and priority tiers, are left out. Price says nothing about quality, so compare models on your own task.
Does BroadNet serve any Meta models?
No. BroadRouter is BroadNet's own site, and BroadNet Inference serves 4 chat models, none of them from Meta (rate card synced 2026-11-14). The prices on this page are other providers' own prices. BroadNet Inference models.
Does Meta sell its own API?
Meta does not sell Llama models through an API of its own: llama.com now redirects to Meta's developer site, whose Model API lists only Meta's Muse models. Llama is available only from third-party hosts. Checked 2026-11-14: source.
Which providers list Meta models?
17 providers publish a standard price for at least one Meta model. By number of Meta models priced: Cloudflare Workers AI 14, Amazon Bedrock 13, Featherless 8, Google Vertex AI 6, DeepInfra 5, and 12 more. Each model page ranks its providers on a blend of 3 input tokens to 1 output token.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- Meta: developer docs (checked 2026-11-14)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- Amazon Bedrock: pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- Google Cloud Vertex AI: pricing (checked 2026-11-14)
- DeepInfra: pricing (checked 2026-11-14)
- Novita AI: pricing (checked 2026-11-14)