impulse

Mixtral 8x22b Instruct

Open weights

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size.

API id mixtral-8x22b-instructReleased 17 Apr 2024 (Apr 2024)
Input / 1M
$1.20
at Fireworks AI
Output / 1M
$1.20
at Fireworks AI
Context window
66K
tokens
Max output
66K
tokens per reply
Hosts
2
2 listings
Released
Apr 2024
17 Apr 2024

Pricing

List prices at Fireworks AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.20$1.20

What it costs a month

At Fireworks AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$450
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$619
  • Coding agent1,000 requests a day, 40K in / 2K out$1,512
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$3,168
Use your own numbers

Where to run it

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

HostIn / out per 1M
Fireworks AIInference
mixtral-8x22b-instruct
$1.20 / $1.20
mixtral-8x22b-instruct
$1.20 / $1.20

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
Runs in about 337.5 GB of GPU memory
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 Fireworks AI.

Smaller Mistral AI models

  • Mistral Large
    Mistral AI · on Mistral AI
    $0.50 / $1.50
    Has every key capability
    38% less
  • Codestral 2508
    Mistral AI · on Mistral AI
    $0.30 / $0.90
    Has every key capability
    63% less
  • Codestral
    Mistral AI · on Mistral AI
    $0.30 / $0.90
    Has every key capability
    63% less

Other frontier labs

  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    29% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    61% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    83% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    83% less

Open-weight picks

  • Motif 3
    Independent · on ai&
    $0.50 / $2.00
    Has every key capability
    27% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    28% less
  • Nemotron 3 Ultra 550B A55B
    NVIDIA · on Perplexity
    $0.25 / $2.50
    Has every key capability
    32% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    34% less

Benchmarks

Scores published on the model card.

  • BBH44.1%
  • GPQA16.4%
  • IFEval71.8%
  • MATH Lvl 518.7%
  • MMLU-Pro38.7%
  • MUSR13.5%
  • Open LLM Average33.9%

Call it

Using Fireworks AI's API.

Python
from litellm import completion

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

Quick answers

How much does Mixtral 8x22b Instruct cost?

On Fireworks AI, Mixtral 8x22b Instruct costs $1.20 per million input tokens and $1.20 per million output tokens.

Which APIs offer Mixtral 8x22b Instruct?

Mixtral 8x22b Instruct runs on 2 APIs: Fireworks AI and Vercel AI Gateway.

What is Mixtral 8x22b Instruct's context window?

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

Is Mixtral 8x22b Instruct being retired?

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

What are cheaper alternatives to Mixtral 8x22b Instruct?

Models that cost less and keep most of what it can do: Mistral Large on Mistral AI (38% less), Gemini 3.5 Flash Lite on Google AI Studio (29% less), GPT-5.4 Nano on OpenAI (61% less) and Motif 3 on ai& (27% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Mixtral 8x22b Instruct released?

Mistral AI released it on 17 Apr 2024.

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

Use mixtral-8x22b-instruct with Fireworks AI.

Sources

Raw catalog entry for mixtral-8x22b-instruct on Fireworks AI
{
  "max_input_tokens": 65536,
  "max_output_tokens": 65536,
  "input_cost_per_token": 0.0000012,
  "output_cost_per_token": 0.0000012,
  "litellm_provider": "fireworks_ai",
  "mode": "chat"
}