Llama 3 70B
ReplicateText
Llama 3 70B is a text model from Replicate with a context window of 8K tokens and max output of 8K tokens. Pricing starts at $0.65 per million input tokens and $2.75 per million output tokens (cheapest at Ollama).
Specifications
| Model Key | replicate/meta/llama-3-70b |
| Provider | Replicate |
| LiteLLM Provider | replicate |
| Mode | Text |
| Canonical Name | llama-3-70b |
| Context Window | 8K tokens |
| Max Output | 8K tokens |
Capabilities
✗ Vision✗ Function Calling✗ Reasoning✗ JSON Schema✗ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output
Pricing
| Type | Per 1K Tokens | Per 1M Tokens |
|---|---|---|
| Input Tokens | $0.000650 | $0.650 |
| Output Tokens | $0.0027 | $2.75 |
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 |
|---|---|---|---|
| Databricks | databricks/databricks-meta-llama-3-70b-instruct | $1.00 | $3.00 |
| Replicate | replicate/meta/llama-3-70b | $0.650 | $2.75 |
| Vercel Ai Gateway | vercel_ai_gateway/meta/llama-3-70b | $0.590 | $0.790 |
| Novita | novita/meta-llama/llama-3-70b-instruct | $0.510 | $0.740 |
| OpenRouter | openrouter/meta-llama/llama-3-70b-instruct | $0.590 | $0.790 |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct | $0.900 | $0.900 |
| Snowflake | snowflake/llama3-70b | N/A | N/A |
| Google Vertex AI | vertex_ai/meta/llama3-70b-instruct-maas | N/A | N/A |
| AWS Bedrock | bedrock/us-east-1/meta.llama3-70b-instruct-v1:0 | $2.65 | $3.50 |
| Ollama | ollama/llama3:70b | N/A | N/A |
| Anyscale | anyscale/meta-llama/Meta-Llama-3-70B-Instruct | $1.00 | $1.00 |
| Azure AI | azure_ai/Meta-Llama-3-70B-Instruct | $1.10 | $0.370 |
| Hyperbolic | hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct | $0.120 | $0.300 |
Similar Models
Models with similar capabilities and context window size.
Model | Provider | Mode | Input Price | Output Price | Context | Max Output | Vision | Functions |
|---|---|---|---|---|---|---|---|---|
| ALIA 40B Instruct Q8 0 | Publicai | Text | N/A | N/A | 8K | 4K | no | yes |
| Apertus 70B Instruct | Publicai | Text | N/A | N/A | 8K | 4K | no | yes |
| Apertus 8B Instruct | Publicai | Text | N/A | N/A | 8K | 4K | no | yes |
| Gemma SEA LION V4 27B IT | Publicai | Text | N/A | N/A | 8K | 4K | no | yes |
| Llama 3 8B Instruct:free | OpenRouter | Text | N/A | N/A | 8K | N/A | no | no |
| Llama3 | Ollama | Text | N/A | N/A | 8K | 8K | no | no |
| Llama3:70B | Ollama | Text | N/A | N/A | 8K | 8K | no | no |
| Llama3.1 | Ollama | Text | N/A | N/A | 8K | 8K | no | yes |
| Mistral 7B Instruct:free | OpenRouter | Text | N/A | N/A | 8K | N/A | no | no |
| Sarvam M | Sarvam | Text | N/A | N/A | 8K | 32K | no | no |