Meta API pricing
All 112 Meta models with a listed API price, cheapest input from $0.015 per 1M tokens. Sort by price, context window or benchmark, filter by capability, and copy the exact model ID for any serving provider. Listed prices from LiteLLM, OpenRouter and Vercel.
Models
112
with a listed price
Cheapest input
$0.015
per 1M tokens
Cheapest output
$0.02
per 1M tokens
Max context
10.5M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
Capability
| Llama 3.3 70B Instruct | First listed Dec 2024 | 131K | from $0.12 via Hyperbolic | from $0.20 via Crusoe | 7.7 | 5% | 50% | 18 providers | |
| Llama 3.1 8B Instruct | First listed Jul 2024 | 200K | from $0.02 via Nebius | from $0.03 via Nscale | 6.9 | 1% | 26% | 17 providers | |
| Llama 3.1 70B Instruct | First listed Jul 2024 | 131K | from $0.12 via Hyperbolic | from $0.30 via Hyperbolic | 6.6 | n/a | 41% | 12 providers | |
| Llama 3.2 3B Instruct | First listed Sep 2024 | 131K | from $0.015 via Lambda AI | from $0.02 via DeepInfra | 5.7 | n/a | 25% | 11 providers | |
| Llama 4 Scout 17B 16e Instruct | Released Apr 5, 2025 | 10.5M | from $0.05 via Lambda AI | from $0.10 via Lambda AI | n/a | n/a | n/a | 11 providers | |
| Llama 3.1 405B Instruct | First listed Jul 2024 | 131K | from $0.12 via Hyperbolic | from $0.30 via Hyperbolic | 7.3 | n/a | 52% | 9 providers | |
| Llama 3 70B Instruct | Released Apr 18, 2024 | 131K | from $0.12 via Hyperbolic | from $0.30 via Hyperbolic | 5.5 | n/a | 38% | 9 providers | |
| Llama 3.2 1B Instruct | First listed Sep 2024 | 131K | from $0.02 via Novita | from $0.02 via Novita | 4.8 | n/a | 20% | 8 providers | |
| Llama 3.2 11B Vision Instruct | First listed Sep 2024 | 131K | from $0.015 via Lambda AI | from $0.025 via Lambda AI | 5.4 | n/a | 22% | 7 providers | |
| Llama 3 8B Instruct | Released Apr 3, 2025 | 8K | from $0.03 via DeepInfra | from $0.04 via Novita | 4.8 | n/a | 30% | 7 providers | |
| Llama 4 Maverick 17B 128e Instruct FP8 | Released Apr 5, 2025 | 1M | from $0.05 via Lambda AI | from $0.10 via Lambda AI | n/a | n/a | n/a | 7 providers | |
| Llama Guard 3 8B | First listed May 2025 | 131K | from $0.02 via Nebius | from $0.03 via Cloudflare | n/a | n/a | n/a | 6 providers | |
| Llama 3.1 8B | First listed Aug 2024 | 131K | from $0.03 via Llamagate | from $0.05 via Llamagate | n/a | n/a | n/a | 5 providers | |
| Llama 2 70B Chat | First listed Sep 2023 | 4K | from $0.50 via Databricks | from $0.90 via Fireworks AI | 5.3 | n/a | 33% | 5 providers | |
| Llama 3 8B | First listed Apr 2024 | 8K | from $0.05 via Replicate | from $0.08 Routed quote | n/a | n/a | n/a | 4 providers | |
| Llama Guard 4 12B | First listed Jul 2025 | 164K | from $0.18 via DeepInfra | from $0.18 via DeepInfra | n/a | n/a | n/a | 4 providers | |
| Llama 4 Maverick | Released Apr 5, 2025 | 131K | from $0.188 Routed quote | from $0.652 Routed quote | 10.0 | 8% | 67% | 4 providers | |
| Llama 3.2 90B Vision Instruct | First listed Sep 2024 | 131K | from $0.90 via Fireworks AI | from $0.90 via Fireworks AI | 6.4 | n/a | 43% | 4 providers | |
| Llama 3.2 3B | First listed Jul 2025 | 131K | from $0.04 via Llamagate | from $0.08 via Llamagate | n/a | n/a | n/a | 3 providers | |
| Llama 2 7B | First listed Apr 2024 | 4K | from $0.05 via Replicate | from $0.20 via Fireworks AI | n/a | n/a | n/a | 3 providers | |
| Llama 2 13B | First listed Oct 2023 | 4K | from $0.10 via Replicate | from $0.20 via Fireworks AI | n/a | n/a | n/a | 3 providers | |
| Llama 2 13B Chat | First listed Sep 2023 | 4K | from $0.10 via Replicate | from $0.20 via Fireworks AI | 5.3 | n/a | 32% | 3 providers | |
| Llama 2 70B | First listed Oct 2023 | 4K | from $0.10 via Fireworks AI | from $0.10 via Fireworks AI | n/a | n/a | n/a | 3 providers | |
| Llama 3 70B | First listed Apr 2024 | 8K | from $0.59 Routed quote | from $0.79 Routed quote | n/a | n/a | n/a | 3 providers | |
| Llama 3.1 70B | First listed Aug 2024 | 128K | from $0.60 via Cerebras | from $0.60 via Cerebras | n/a | n/a | n/a | 3 providers | |
| Llama 3.3 70B | First listed Feb 2025 | 128K | from $0.72 via Snowflake | from $0.72 via Snowflake | n/a | n/a | n/a | 3 providers | |
| Llama 3.1 8B Instruct Turbo | First listed Dec 2024 | 131K | from $0.02 via DeepInfra | from $0.04 via DeepInfra | n/a | n/a | n/a | 2 providers | |
| Llama 2 7B Chat | First listed Apr 2024 | 4K | from $0.05 via Replicate | from $0.20 via Fireworks AI | 5.7 | n/a | 23% | 2 providers | |
| Codellama 7B | First listed Dec 2025 | 16K | from $0.06 via Llamagate | from $0.12 via Llamagate | n/a | n/a | n/a | 2 providers | |
| Llama 3.2 1B | First listed Jul 2025 | 131K | from $0.10 via Fireworks AI | from $0.10 via Fireworks AI | n/a | n/a | n/a | 2 providers | |
| Llama 3.3 70B Instruct Turbo | First listed Jan 2025 | 131K | from $0.10 via DeepInfra | from $0.32 via DeepInfra | n/a | n/a | n/a | 2 providers | |
| Llama 4 Scout | Released Jan 1, 2025 | 131K | from $0.17 Routed quote | from $0.59 Routed quote | 8.1 | 4% | 59% | 2 providers | |
| Llama 4 Maverick 17B 128e Instruct | First listed May 2025 | 131K | from $0.20 via Groq | from $0.60 via Groq | n/a | n/a | n/a | 2 providers | |
| Codellama 34B Instruct | First listed Sep 2023 | 16K | from $0.35 via Perplexity | from $0.90 via Fireworks AI | n/a | n/a | n/a | 2 providers | |
| Llama 3.1 70B Instruct Turbo | First listed Dec 2024 | 131K | from $0.40 via DeepInfra | from $0.40 via DeepInfra | n/a | n/a | n/a | 2 providers | |
| Codellama 70B Instruct | First listed Feb 2024 | 16K | from $0.70 via Perplexity | from $0.90 via Fireworks AI | n/a | n/a | n/a | 2 providers | |
| Llama Prompt Guard 2 22m | Released Oct 1, 2024 | 512 | $0.03 via Groq | $0.03 via Groq | n/a | n/a | n/a | Groq cheapest groq/meta-llama/llama-prompt-guard-2-22m | |
| Llama Prompt Guard 2 86m | Released Oct 1, 2024 | 512 | $0.04 via Groq | $0.04 via Groq | n/a | n/a | n/a | Groq cheapest groq/meta-llama/llama-prompt-guard-2-86m | |
| Llama 3.1 8B Instant | First listed Jul 2024 | 131K | $0.05 via Groq | $0.08 via Groq | n/a | n/a | n/a | groq/llama-3.1-8b-instant | |
| Cogito V1 Preview Llama 3B | First listed Dec 2025 | 131K | $0.10 via Fireworks AI | $0.10 via Fireworks AI | n/a | n/a | n/a | Fireworks AI cheapest fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b | |
| Llama 3.1 405B Instruct Long | First listed Dec 2025 | 4K | $0.10 via Fireworks AI | $0.10 via Fireworks AI | n/a | n/a | n/a | Fireworks AI cheapest fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long | |
| Llama 3.1 70B Instruct 1B | First listed Dec 2025 | 4K | $0.10 via Fireworks AI | $0.10 via Fireworks AI | n/a | n/a | n/a | Fireworks AI cheapest fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b | |
| Llama Guard 3 1B | First listed Dec 2025 | 131K | $0.10 via Fireworks AI | $0.10 via Fireworks AI | n/a | n/a | n/a | Fireworks AI cheapest fireworks_ai/accounts/fireworks/models/llama-guard-3-1b | |
| Llama 3.1 70B Instruct FP8 | First listed Jul 2025 | 131K | $0.12 via Lambda AI | $0.30 via Lambda AI | n/a | n/a | n/a | Lambda AI cheapest lambda_ai/llama3.1-70b-instruct-fp8 | |
| Llama 3.3 70B Instruct FP8 | First listed Jul 2025 | 131K | $0.12 via Lambda AI | $0.30 via Lambda AI | n/a | n/a | n/a | Lambda AI cheapest lambda_ai/llama3.3-70b-instruct-fp8 | |
| Llama 2 7B Chat HF | First listed Oct 2023 | 4K | $0.15 via Anyscale | $0.15 via Anyscale | n/a | n/a | n/a | Anyscale cheapest anyscale/meta-llama/Llama-2-7b-chat-hf | |
| Llama 4 Scout Instruct Basic | First listed Apr 2025 | 131K | $0.15 via Fireworks AI | $0.60 via Fireworks AI | n/a | n/a | n/a | Fireworks AI cheapest fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic | |
| Llama 3.1 8B Instruct FP8 | First listed Jun 2026 | 32K | $0.152 via Cloudflare | $0.287 via Cloudflare | n/a | n/a | n/a | Cloudflare cheapest cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8 | |
| Llama 3.2 11B | First listed Jul 2025 | 128K | $0.16 Routed quote | $0.16 Routed quote | n/a | n/a | n/a | Vercel cheapest vercel_ai_gateway/meta/llama-3.2-11b | |
| Llama 3.2 11B Instruct | First listed Oct 2024 | 128K | $0.16 via Amazon Bedrock | $0.16 via Amazon Bedrock | n/a | n/a | n/a | Amazon Bedrock cheapest meta.llama3-2-11b-instruct-v1:0 |
Input $/1M
from$0.12
via HyperbolicOutput $/1M
from$0.20
via CrusoeIntelligence7.718 providers
Input $/1M
from$0.02
via NebiusOutput $/1M
from$0.03
via NscaleIntelligence6.917 providers
Input $/1M
from$0.12
via HyperbolicOutput $/1M
from$0.30
via HyperbolicIntelligence6.612 providers
Input $/1M
from$0.015
via Lambda AIOutput $/1M
from$0.02
via DeepInfraIntelligence5.711 providers
Input $/1M
from$0.05
via Lambda AIOutput $/1M
from$0.10
via Lambda AIIntelligencen/a11 providers
Input $/1M
from$0.12
via HyperbolicOutput $/1M
from$0.30
via HyperbolicIntelligence7.39 providers
Input $/1M
from$0.12
via HyperbolicOutput $/1M
from$0.30
via HyperbolicIntelligence5.59 providers
Input $/1M
from$0.02
via NovitaOutput $/1M
from$0.02
via NovitaIntelligence4.88 providers
Input $/1M
from$0.015
via Lambda AIOutput $/1M
from$0.025
via Lambda AIIntelligence5.47 providers
Input $/1M
from$0.03
via DeepInfraOutput $/1M
from$0.04
via NovitaIntelligence4.87 providers
Input $/1M
from$0.05
via Lambda AIOutput $/1M
from$0.10
via Lambda AIIntelligencen/a7 providers
Input $/1M
from$0.02
via NebiusOutput $/1M
from$0.03
via CloudflareIntelligencen/a6 providers
Input $/1M
from$0.03
via LlamagateOutput $/1M
from$0.05
via LlamagateIntelligencen/a5 providers
Input $/1M
from$0.50
via DatabricksOutput $/1M
from$0.90
via Fireworks AIIntelligence5.35 providers
Input $/1M
from$0.05
via ReplicateOutput $/1M
from$0.08
Routed quoteIntelligencen/a4 providers
Input $/1M
from$0.18
via DeepInfraOutput $/1M
from$0.18
via DeepInfraIntelligencen/a4 providers
Input $/1M
from$0.188
Routed quoteOutput $/1M
from$0.652
Routed quoteIntelligence10.04 providers
Input $/1M
from$0.90
via Fireworks AIOutput $/1M
from$0.90
via Fireworks AIIntelligence6.44 providers
Input $/1M
from$0.04
via LlamagateOutput $/1M
from$0.08
via LlamagateIntelligencen/a3 providers
Input $/1M
from$0.05
via ReplicateOutput $/1M
from$0.20
via Fireworks AIIntelligencen/a3 providers
Input $/1M
from$0.10
via ReplicateOutput $/1M
from$0.20
via Fireworks AIIntelligencen/a3 providers
Input $/1M
from$0.10
via ReplicateOutput $/1M
from$0.20
via Fireworks AIIntelligence5.33 providers
Input $/1M
from$0.10
via Fireworks AIOutput $/1M
from$0.10
via Fireworks AIIntelligencen/a3 providers
Input $/1M
from$0.59
Routed quoteOutput $/1M
from$0.79
Routed quoteIntelligencen/a3 providers
Input $/1M
from$0.60
via CerebrasOutput $/1M
from$0.60
via CerebrasIntelligencen/a3 providers
Input $/1M
from$0.72
via SnowflakeOutput $/1M
from$0.72
via SnowflakeIntelligencen/a3 providers
Input $/1M
from$0.02
via DeepInfraOutput $/1M
from$0.04
via DeepInfraIntelligencen/a2 providers
Input $/1M
from$0.05
via ReplicateOutput $/1M
from$0.20
via Fireworks AIIntelligence5.72 providers
Input $/1M
from$0.06
via LlamagateOutput $/1M
from$0.12
via LlamagateIntelligencen/a2 providers
Input $/1M
from$0.10
via Fireworks AIOutput $/1M
from$0.10
via Fireworks AIIntelligencen/a2 providers
Input $/1M
from$0.10
via DeepInfraOutput $/1M
from$0.32
via DeepInfraIntelligencen/a2 providers
Input $/1M
from$0.17
Routed quoteOutput $/1M
from$0.59
Routed quoteIntelligence8.12 providers
Input $/1M
from$0.20
via GroqOutput $/1M
from$0.60
via GroqIntelligencen/a2 providers
Input $/1M
from$0.35
via PerplexityOutput $/1M
from$0.90
via Fireworks AIIntelligencen/a2 providers
Input $/1M
from$0.40
via DeepInfraOutput $/1M
from$0.40
via DeepInfraIntelligencen/a2 providers
Input $/1M
from$0.70
via PerplexityOutput $/1M
from$0.90
via Fireworks AIIntelligencen/a2 providers
Input $/1M
$0.03
via GroqOutput $/1M
$0.03
via GroqIntelligencen/aGroq
Input $/1M
$0.04
via GroqOutput $/1M
$0.04
via GroqIntelligencen/aGroq
Input $/1M
$0.05
via GroqOutput $/1M
$0.08
via GroqIntelligencen/aGroq
Input $/1M
$0.10
via Fireworks AIOutput $/1M
$0.10
via Fireworks AIIntelligencen/aFireworks AI
Input $/1M
$0.10
via Fireworks AIOutput $/1M
$0.10
via Fireworks AIIntelligencen/aFireworks AI
Input $/1M
$0.10
via Fireworks AIOutput $/1M
$0.10
via Fireworks AIIntelligencen/aFireworks AI
Input $/1M
$0.10
via Fireworks AIOutput $/1M
$0.10
via Fireworks AIIntelligencen/aFireworks AI
Input $/1M
$0.12
via Lambda AIOutput $/1M
$0.30
via Lambda AIIntelligencen/aLambda AI
Input $/1M
$0.12
via Lambda AIOutput $/1M
$0.30
via Lambda AIIntelligencen/aLambda AI
Input $/1M
$0.15
via AnyscaleOutput $/1M
$0.15
via AnyscaleIntelligencen/aAnyscale
Input $/1M
$0.15
via Fireworks AIOutput $/1M
$0.60
via Fireworks AIIntelligencen/aFireworks AI
Input $/1M
$0.152
via CloudflareOutput $/1M
$0.287
via CloudflareIntelligencen/aCloudflare
Input $/1M
$0.16
Routed quoteOutput $/1M
$0.16
Routed quoteIntelligencen/aVercel
Input $/1M
$0.16
via Amazon BedrockOutput $/1M
$0.16
via Amazon BedrockIntelligencen/aAmazon Bedrock
1–50 of 112 models
Page 1 of 3
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 28 prices older, back to Jul 19, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI