Start free trial

Mistral: Mixtral 8x22B Instruct

mistralai/mixtral-8x22b-instruct
CompareAPITry this model

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.

Modalities
In / out per 1M$2.00 / $6.00
Context64K
ReleasedApr 17, 2024

Providers

3 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Mistral$2.00$6.00$0.200.43s101 tps100%
Mistral$2.00$6.00$0.200.45s110 tps100%
Mistraleu$2.20$6.60$0.22——100%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Mixtral 8x22B Instruct in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Mixtral 8x22B Instruct costs pay-as-you-go elsewhere, not what you pay here.

Input
$2.00
per 1M tokens
Output
$6.00
per 1M tokens
Cache read
$0.20
per 1M cached tokens
Included in every pass
Mixtral 8x22B Instruct is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s1.0s2.0s3.0s4.0s
Oct 29, 12 AMOct 29, 1 AMOct 29, 2 AMOct 29, 4 PMOct 29, 5 PMOct 30, 4 AMOct 30, 5 PMOct 31, 12 AMOct 31, 1 PMOct 31, 2 PMNov 1, 1 AMNov 1, 7 AMNov 1, 3 PM
Mistral Mistral
0 tok/s50 tok/s100 tok/s150 tok/s200 tok/s
Oct 29, 12 AMOct 29, 1 AMOct 29, 2 AMOct 29, 4 PMOct 29, 5 PMOct 30, 4 AMOct 30, 5 PMOct 31, 12 AMOct 31, 1 PMOct 31, 2 PMNov 1, 1 AMNov 1, 7 AMNov 1, 3 PM
Mistral Mistral

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.96%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.94%
100% 97% 93% 90%
Oct 31, 6:10 PMNow

Apps

Tools that most often run Mixtral 8x22B Instruct, by tokens this week.

G0DM0D3-pliny84.4% of tokens73.4MSillyTavernRoleplay · 6.7% of tokens5.9MOpen WebUIGeneral Chat · 4.1% of tokens3.6MChatbox AIGeneral Chat · 2.5% of tokens2.2MHello HavenPersonal Agent · 2.2% of tokens1.9M

Activity

200.1M tokens processed market-wide in the last month.

010.0M20.0M30.0M40.0M
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens

FAQ

Which model id do I use for Mixtral 8x22B Instruct?
mistralai/mixtral-8x22b-instruct. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Mixtral 8x22B Instruct hold?
65,536 tokens per request, of which up to 52,428 can be the response.
What can it accept and return?
Input: text, file. Output: text.
What does Mixtral 8x22B Instruct cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $2.00 per 1M input tokens and $6.00 per 1M output tokens.
How current is its knowledge?
Training data runs to Jan 2024. Anything later has to come from your prompt or a tool call.
Who built Mixtral 8x22B Instruct?
Mistral, in the Mixtral family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion