Last refreshed 2026-06-01. Next refresh: weekly.
Why use Mistral 7B Instruct v0.2 on Replicate API?
Replicate API offers Mistral 7B Instruct v0.2 with pay-as-you-go pricing at $0.25/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare Mistral 7B Instruct v0.2 across 8 providers to find the best fit for your use caseInput / 1M
$0.25
Output / 1M
$0.25
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install replicateAuth
export REPLICATE_API_TOKEN=...Call
import replicate
output = replicate.run(
"mistral-7b-instruct-v0.2",
input={"prompt": "Hello"}Model ID
mistral-7b-instruct-v0.2Request example
import replicate
# reads REPLICATE_API_TOKEN from env
# mistral-7b-instruct-v0.2 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"mistral-7b-instruct-v0.2",
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 Mistral 7B Instruct v0.2 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | — | — |
| OctoML (Deprecated) | $0.15 | $0.20 |
| DeepInfra | $0.05 | $0.15 |
| Fireworks AI | $0.20 | $0.20 |
| NVIDIA NIM | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.25 |
| Output tokens | $0.25 |
Capabilities
No model capability flags are currently sourced.
About Mistral 7B Instruct v0.2
Instruction-tuned 7B Mistral variant optimized for conversational AI and task completion with efficient inference.
Get Started
Model Specs
Released2023-12-11
Parameters7B
Context32k
ArchitectureDecoder Only
Knowledge cutoff2023-12