meta.llama-3.3-70b-instruct-fp8-dynamic
oci · chat model
Input
$0.7200 / 1M tokens
Output
$0.7200 / 1M tokens
Cached input
N/A
Context
4.0K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 7.2e-7 | $0.7200 / 1M tokens |
| Output | 7.2e-7 | $0.7200 / 1M tokens |
| Embedding | 7.2e-7 | $0.7200 / 1M tokens |
Token limits
Context window
4.0K
Max input tokens
128.0K
Max output tokens
4.0K
Max tokens
4.0K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | Yes |
| Parallel function calling | No |
| Tool choice | No |
| Prompt caching | No |
| Reasoning | No |
| Response schema | No |
| System messages | No |
| Audio input | No |
| Audio output | No |
| Web search | No |
| PDF input | No |
| Video input | No |
Similar models
Models with comparable pricing in the same mode (chat).
| Model | Provider | Input | Output | Context | Coding | Features |
|---|---|---|---|---|---|---|
| meta.llama3-3-70b-instruct-v1:0 | bedrock_converse | $0.7200 / 1M tokens | $0.7200 / 1M tokens | 4.1K | N/A | Tools |
| meta.llama-3.1-8b-instruct | oci | $0.7200 / 1M tokens | $0.7200 / 1M tokens | 4.0K | N/A | Tools |
| meta.llama-3.1-70b-instruct | oci | $0.7200 / 1M tokens | $0.7200 / 1M tokens | 4.0K | N/A | Tools |
| meta.llama-3.3-70b-instruct | oci | $0.7200 / 1M tokens | $0.7200 / 1M tokens | 4.0K | N/A | Tools |
| meta.llama-4-maverick-17b-128e-instruct-fp8 | oci | $0.7200 / 1M tokens | $0.7200 / 1M tokens | 8.2K | N/A | Vision Tools |
| meta.llama-4-scout-17b-16e-instruct | oci | $0.7200 / 1M tokens | $0.7200 / 1M tokens | 8.2K | N/A | Tools |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"input_cost_per_token": 7.2e-7,
"litellm_provider": "oci",
"max_input_tokens": 128000,
"max_output_tokens": 4000,
"max_tokens": 4000,
"mode": "chat",
"output_cost_per_token": 7.2e-7,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
"supports_function_calling": true,
"supports_response_schema": false
}