impulse

Mixtral 8x22b Instruct V0.1

Open weights
API id mixtral-8x22b-instruct-v0.1
Input / 1M
$0.60
at Nscale
Output / 1M
$0.60
at Nscale
Context window
66K
tokens
Max output
66K
tokens per reply
Hosts
2
3 listings
Released
-
date not published

Pricing

List prices at Nscale, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.60$0.60

What it costs a month

At Nscale list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$225
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$310
  • Coding agent1,000 requests a day, 40K in / 2K out$756
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,584
Use your own numbers

Where to run it

2 hosts serve Mixtral 8x22b Instruct V0.1. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
NscaleInference
mixtral-8x22b-instruct-v0.1
$0.60 / $0.60
Mixtral-8x22B-Instruct-v0.1
$0.90 / $0.90
+50% vs headline
OllamaLocal
mixtral-8x22B-Instruct-v0.1
-

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: Apache-2.0
Runtimes: Ollama, 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 Nscale.

Smaller Mistral AI models

  • Codestral 2508
    Mistral AI · on Mistral AI
    $0.30 / $0.90
    Has every key capability
    25% less
  • Codestral
    Mistral AI · on Mistral AI
    $0.30 / $0.90
    Has every key capability
    25% less
  • Magistral Small
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    56% less

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    23% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    67% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    67% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    56% less

Open-weight picks

  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    13% less
  • Longcat 2.0
    Independent · on OpenCode Go
    $0.30 / $1.20
    Has every key capability
    13% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    20% less
  • GLM 4 6v
    Zhipu AI · on Novita AI
    $0.30 / $0.90
    Has every key capability
    25% less

Call it

Using Nscale's API.

Python
from litellm import completion

response = completion(
    model="nscale/mixtral-8x22b-instruct-v0.1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Mixtral 8x22b Instruct V0.1 cost?

On Nscale, Mixtral 8x22b Instruct V0.1 costs $0.60 per million input tokens and $0.60 per million output tokens.

Which APIs offer Mixtral 8x22b Instruct V0.1?

Mixtral 8x22b Instruct V0.1 runs on 2 APIs: Nscale and Anyscale.

What is Mixtral 8x22b Instruct V0.1's context window?

66K tokens, with up to 66K tokens in one reply.

Is Mixtral 8x22b Instruct V0.1 being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Mixtral 8x22b Instruct V0.1?

Models that cost less and keep most of what it can do: Codestral 2508 on Mistral AI (25% less), GPT-5.4 Nano on OpenAI (23% less), Claude Haiku 5.5 on Anthropic (67% less) and DeepSeek Flash on DeepSeek (13% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Mixtral 8x22b Instruct V0.1's API model id?

Use mixtral-8x22b-instruct-v0.1 with Nscale. Other hosts use their own ids: Mixtral-8x22B-Instruct-v0.1 on Anyscale.

Sources

Raw catalog entry for mixtral-8x22b-instruct-v0.1 on Nscale
{
  "input_cost_per_token": 6e-7,
  "litellm_provider": "nscale",
  "metadata": {
    "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output."
  },
  "mode": "chat",
  "output_cost_per_token": 6e-7,
  "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
}