Llama V2 70B Chat
Llama V2 70B Chat is a text model from 
Fireworks AI with a context window of 2K tokens and max output of 2K tokens. Pricing starts at 0.90 per million input tokens and 0.90 per million output tokens (cheapest at Ollama).
Capabilities
✗ Vision✗ Function Calling✗ Reasoning✗ JSON Schema✗ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output
Specifications
| Model Key | fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat |
| Provider | Fireworks AI |
| Provider ID | fireworks_ai |
| Mode | Text |
| Canonical Name | llama-2-70b |
| Context Window | 2K tokens |
| Max Output | 2K tokens |
Pricing
| Type | Per 1K Tokens | Per 1M Tokens |
|---|---|---|
| Input Tokens | 0.000900 | 0.900 |
| Output Tokens | 0.000900 | 0.900 |
Price Comparison by Provider
Compare prices for Llama V2 70B Chat across different providers. The same model may be available through multiple providers at different price points.
Provider | Model Key | Input Price, $ | Output Price, $ |
|---|---|---|---|
 Snowflake | snowflake/llama2-70b-chat | N/A | N/A |
 AWS SageMaker | sagemaker/meta-textgeneration-llama-2-70b | N/A | N/A |
 Replicate | replicate/meta/llama-2-70b | 0.650 | 2.75 |
 Perplexity | perplexity/llama-2-70b-chat | 0.700 | 2.80 |
 Ollama | ollama/llama2:70b | N/A | N/A |
 AWS Bedrock | meta.llama2-70b-chat-v1 | 1.95 | 2.56 |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/llama-v2-70b | 0.100 | 0.100 |
 Databricks | databricks/databricks-llama-2-70b-chat | 0.500 | 1.50 |
 Anyscale | anyscale/meta-llama/Llama-2-70b-chat-hf | 1.00 | 1.00 |
All Variants
All available versions, regions, and API endpoints for Llama V2 70B Chat.
Model Key | Provider | Mode | Input Price, $ | Output Price, $ | Context | Max Output | Vision | Functions |
|---|---|---|---|---|---|---|---|---|
| anyscale/meta-llama/Llama-2-70b-chat-hf | Anyscale | Text | 1.00 | 1.00 | 4K | 4K | no | no |
| meta.llama2-70b-chat-v1 | AWS Bedrock | Text | 1.95 | 2.56 | 4K | 4K | no | no |
| sagemaker/meta-textgeneration-llama-2-70b | AWS SageMaker | Text | N/A | N/A | 4K | 4K | no | no |
| sagemaker/meta-textgeneration-llama-2-70b-b-f | AWS SageMaker | Text | N/A | N/A | 4K | 4K | no | no |
| databricks/databricks-llama-2-70b-chat | Databricks | Text | 0.500 | 1.50 | 4K | 4K | no | no |
| fireworks_ai/accounts/fireworks/models/llama-v2-70b | Fireworks AI | Text | 0.100 | 0.100 | 4K | 4K | no | no |
| fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat | Fireworks AI | Text | 0.900 | 0.900 | 2K | 2K | no | no |
| ollama/llama2:70b | Ollama | Text | N/A | N/A | 4K | 4K | no | no |
| perplexity/llama-2-70b-chat | Perplexity | Text | 0.700 | 2.80 | 4K | 4K | no | no |
| replicate/meta/llama-2-70b | Replicate | Text | 0.650 | 2.75 | 4K | 4K | no | no |
| replicate/meta/llama-2-70b-chat | Replicate | Text | 0.650 | 2.75 | 4K | 4K | no | no |
| snowflake/llama2-70b-chat | Snowflake | Text | N/A | N/A | 4K | 8K | no | no |