impulse

Wizardlm 2 8x22b

API id WizardLM-2-8x22B
Input / 1M
$0.48
at DeepInfra
Output / 1M
$0.48
at DeepInfra
Context window
66K
tokens
Max output
66K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.48$0.48

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$180
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$248
  • Coding agent1,000 requests a day, 40K in / 2K out$605
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,267
Use your own numbers

Where to run it

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

HostIn / out per 1M
DeepInfraInference
WizardLM-2-8x22B
$0.48 / $0.48
Novita AIInference
wizardlm-2-8x22b
$0.62 / $0.62
+29% vs headline

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

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 DeepInfra.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    4% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    58% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    58% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    45% less

Open-weight picks

  • Inkling 2 Small
    Independent · on Cloudflare Workers AI
    $0.30 / $1.00
    Has every key capability
    1% less
  • GLM 4 6v
    Zhipu AI · on Novita AI
    $0.30 / $0.90
    Has every key capability
    6% less
  • MiMo V2.6 Pro
    Xiaomi · on GMI Cloud
    $0.348 / $0.696
    Has every key capability
    9% less
  • MiniMax M3
    MiniMax · on EmpirioLabs AI
    $0.225 / $0.90
    Has every key capability
    18% less

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/WizardLM-2-8x22B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Wizardlm 2 8x22b cost?

On DeepInfra, Wizardlm 2 8x22b costs $0.48 per million input tokens and $0.48 per million output tokens.

Which APIs offer Wizardlm 2 8x22b?

Wizardlm 2 8x22b runs on 2 APIs: DeepInfra and Novita AI.

What is Wizardlm 2 8x22b's context window?

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

Is Wizardlm 2 8x22b being retired?

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

What are cheaper alternatives to Wizardlm 2 8x22b?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (4% less), Claude Haiku 5.5 on Anthropic (58% less) and Inkling 2 Small on Cloudflare Workers AI (1% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Wizardlm 2 8x22b's API model id?

Use WizardLM-2-8x22B with DeepInfra. Other hosts use their own ids: wizardlm-2-8x22b on Novita AI.

Sources

Raw catalog entry for WizardLM-2-8x22B on DeepInfra
{
  "max_input_tokens": 65536,
  "max_output_tokens": 65536,
  "input_cost_per_token": 4.8e-7,
  "output_cost_per_token": 4.8e-7,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_tool_choice": false
}