Llama 3 70B
Llama 3 70B is a text model from 
Vercel AI Gateway with a context window of 8K tokens and max output of 8K tokens. Pricing starts at 0.59 per million input tokens and 0.79 per million output tokens (cheapest at Vertex AI (Llama)).
Capabilities
✗ Vision✗ Function Calling✗ Reasoning✗ JSON Schema✗ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output
Specifications
| Model Key | vercel_ai_gateway/meta/llama-3-70b |
| Provider | Vercel AI Gateway |
| Provider ID | vercel_ai_gateway |
| Mode | Text |
| Canonical Name | llama-3-70b |
| Context Window | 8K tokens |
| Max Output | 8K tokens |
Pricing
| Type | Per 1K Tokens | Per 1M Tokens |
|---|---|---|
| Input Tokens | 0.000590 | 0.590 |
| Output Tokens | 0.000790 | 0.790 |
Price Comparison by Provider
Compare prices for Llama 3 70B across different providers. The same model may be available through multiple providers at different price points.
Provider | Model Key | Input Price, $ | Output Price, $ |
|---|---|---|---|
 Vertex AI (Llama) | vertex_ai/meta/llama3-70b-instruct-maas | N/A | N/A |
| Vercel AI Gateway | vercel_ai_gateway/meta/llama-3-70b | 0.590 | 0.790 |
 Snowflake | snowflake/llama3-70b | N/A | N/A |
 Replicate | replicate/meta/llama-3-70b-instruct | 0.650 | 2.75 |
 OpenRouter | openrouter/meta-llama/llama-3-70b-instruct | 0.590 | 0.790 |
 Ollama | ollama/llama3:70b | N/A | N/A |
 Novita AI | novita/meta-llama/llama-3-70b-instruct | 0.510 | 0.740 |
 AWS Bedrock | meta.llama3-70b-instruct-v1:0 | 2.65 | 3.50 |
 Hyperbolic | hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct | 0.120 | 0.300 |
 Fireworks AI | fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf | 0.900 | 0.900 |
 Databricks | databricks/databricks-meta-llama-3-70b-instruct | 1.00 | 3.00 |
 Azure AI | azure_ai/Meta-Llama-3-70B-Instruct | 1.10 | 0.370 |
 Anyscale | anyscale/meta-llama/Meta-Llama-3-70B-Instruct | 1.00 | 1.00 |
All Variants
All available versions, regions, and API endpoints for Llama 3 70B.