Yi 34B 200K on Replicate API

Yi (2023/11) · 01.AI

ServerlessOpen Source

Last refreshed 2026-09-22. Next refresh: weekly.

Why use Yi 34B 200K on Replicate API?

Replicate API offers Yi 34B 200K with pay-as-you-go pricing at $0.20/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Compare Yi 34B 200K across 3 providers to find the best fit for your use case
Input / 1M
$0.20
Output / 1M
$1.00
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "01-ai/yi-34b-200k",
    input={"prompt": "Hello"}
Model ID
01-ai/yi-34b-200k

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# 01-ai/yi-34b-200k format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "01-ai/yi-34b-200k",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

  • Use provider model ID "01-ai/yi-34b-200k", not the LLMReference slug "yi-34b-200k".
  • 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 Yi 34B 200K Across Providers

ProviderInput (per 1M)Output (per 1M)
Alibaba Cloud PAI-EAS——
Fireworks AI$0.90$0.90
Replicate API$0.20$1.00

Pricing

TypePrice (per 1M)
Input tokens$0.20
Output tokens$1.00

Capabilities

No model capability flags are currently sourced.

About Yi 34B 200K

The Yi 34B 200K is a sophisticated large language model by 01.AI that excels in varied NLP tasks, featuring an impressive 34 billion parameters and a 200,000-token context window to handle extensive text inputs. Built on a Transformer architecture, it differentiates itself from models like Llama by employing unique training methods such as Grouped-Query Attention and RoPE with adjusted base frequency. It showcases strengths in language comprehension, commonsense reasoning, and bilingual support for English and Chinese. Despite its advanced capabilities, it shares common LLM limitations like hallucination and non-determinism.

Get Started

Model Specs

Released2023-11-02
Parameters34B
Context200k
ArchitectureDecoder Only
Knowledge cutoff2024-03

Related Models on Replicate API