Mixtral 8x22b Instruct
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.
mixtral-8x22b-instructReleased 17 Apr 2024 (Apr 2024)Pricing
List prices at Fireworks AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 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
Where to run it
2 hosts serve Mixtral 8x22b Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Fireworks AIInference mixtral-8x22b-instruct | $1.20 / $1.20 | mixtral-8x22b-instruct | |
Vercel AI GatewayGateway mixtral-8x22b-instruct | $1.20 / $1.20 | mixtral-8x22b-instruct |
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-2.0Runs in about 337.5 GB of GPU memoryRuntimes: 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
- 38% less
- 63% less
- 63% less
Other frontier labs
- 29% less
- 61% less
- 83% less
- 83% less
Open-weight picks
- 27% less
- 28% less
- 32% less
- 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.
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"
}