Code Llama 70B Instruct Hf
CodeLlama-70b-Instruct-hfPricing
List prices at Anyscale, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.00 | $1.00 |
What it costs a month
At Anyscale list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$375
- RAG over documents2,000 requests a day, 8K in / 0.6K out$516
- Coding agent1,000 requests a day, 40K in / 2K out$1,260
- Overnight batch20,000 requests a day, 4K in / 0.4K out$2,640
Where to run it
1 host serve Code Llama 70B Instruct Hf. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
AnyscaleCloud CodeLlama-70b-Instruct-hf | $1.00 / $1.00 | CodeLlama-70b-Instruct-hf |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: Llama Community LicenseRuntimes: Ollama, TGI, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Anyscale.
Smaller Meta models
- 88% less
- 80% less
Other frontier labs
- 15% less
- 54% less
- 80% less
- 80% less
Open-weight picks
- 13% less
- 14% less
- 19% less
- 21% less
Call it
Using Anyscale's API.
from litellm import completion
response = completion(
model="anyscale/CodeLlama-70b-Instruct-hf",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Code Llama 70B Instruct Hf cost?
On Anyscale, Code Llama 70B Instruct Hf costs $1.00 per million input tokens and $1.00 per million output tokens.
Which APIs offer Code Llama 70B Instruct Hf?
Code Llama 70B Instruct Hf runs on 1 API: Anyscale.
What is Code Llama 70B Instruct Hf's context window?
4K tokens, with up to 4K tokens in one reply.
Is Code Llama 70B Instruct Hf being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Code Llama 70B Instruct Hf?
Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (88% less), Gemini 3.5 Flash Lite on Google AI Studio (15% less), GPT-5.4 Nano on OpenAI (54% less) and Motif 3 on ai& (13% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Code Llama 70B Instruct Hf's API model id?
Use CodeLlama-70b-Instruct-hf with Anyscale.
Sources
Raw catalog entry for CodeLlama-70b-Instruct-hf on Anyscale
{
"input_cost_per_token": 0.000001,
"litellm_provider": "anyscale",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.000001,
"source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf"
}