Last refreshed 2026-04-19. Next refresh: weekly.
Why use CodeLlama 70B on Replicate API?
Replicate API offers CodeLlama 70B with pay-as-you-go pricing at $0.65/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare CodeLlama 70B across 6 providers to find the best fit for your use caseSetup recipe
Python + curlpip install replicateexport REPLICATE_API_TOKEN=...import replicate
output = replicate.run(
"codellama-70b",
input={"prompt": "Hello"}codellama-70bRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# codellama-70b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"codellama-70b",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
- The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.
Compare CodeLlama 70B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Together AI | $0.90 | $0.90 |
| NVIDIA NIM | — | — |
| DeepInfra | $0.45 | $0.65 |
| Fireworks AI | $0.90 | $0.90 |
| Microsoft Foundry | $3.78 | $11.34 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.65 |
| Output tokens | $2.75 |
Capabilities
About CodeLlama 70B
CodeLlama 70B is a state-of-the-art generative text model by Meta, specifically designed for code synthesis and understanding. It utilizes an auto-regressive transformer architecture and has been fine-tuned with up to 16,000 tokens, supporting inference with up to 100,000 tokens. The model excels in code completion, infilling, and instruction following, making it versatile for various programming languages and applications. With 70 billion parameters, it offers advanced capabilities for general code generation tasks, while also providing specialized variants for Python and instruction-following. Intended for both commercial and research use, CodeLlama 70B aims to assist developers in generating code, understanding programming concepts, and enhancing productivity in software development .
FAQ
What does CodeLlama 70B cost on Replicate API?
On Replicate API, CodeLlama 70B costs $0.65 per 1M input tokens and $2.75 per 1M output tokens.
What is the context window for CodeLlama 70B on Replicate API?
CodeLlama 70B supports a 16,000 token context window on Replicate API.
How does Replicate API compare to other CodeLlama 70B providers?
CodeLlama 70B is available from 6 providers. The cheapest input pricing is $0.45/1M tokens from DeepInfra.
Who created CodeLlama 70B?
CodeLlama 70B was created by AI at Meta as part of the Code Llama model family.
Is CodeLlama 70B open source?
CodeLlama 70B is open source according to the seed data.