Mistral: Mistral Nemo
mistralai/mistral-nemoA 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.
Modalities
In / out per 1M$0.03 / $0.03
Context128K
ReleasedJul 19, 2024
Providers
5 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.02 | $0.03 | Variable | 0.44s | 34 tps | 100% | |
 DeepInfraus · fp8 | $0.03 | $0.03 | Variable | 0.71s | 23 tps | 100% |
| $0.03 | $0.03 | Variable | 0.58s | 109 tps | 100% | |
 Mistraleu | $0.15 | $0.15 | $0.01 | 0.36s | 82 tps | 100% |
| $0.02 | $0.02 | $0.01 | 0.41s | 44 tps | 99.76% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Mistral Nemo in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Mistral Nemo costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.03
per 1M tokens
Output
$0.03
per 1M tokens
Cache read
—
not published
Included in every pass
Mistral Nemo 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.
0.0s10.0s20.0s30.0s40.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
DeepInfra (us) Parasail io.net DekaLLM Mistral (eu)
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
DeepInfra (us) Parasail io.net DekaLLM Mistral (eu)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.97%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.96%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run Mistral Nemo, by tokens this week.
Activity
1156.1B tokens processed market-wide in the last month.
020.0B40.0B60.0B80.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for Mistral Nemo?
mistralai/mistral-nemo. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Mistral Nemo hold?
131,072 tokens per request, of which up to 16,384 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Mistral Nemo cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.03 per 1M input tokens and $0.03 per 1M output tokens.
How current is its knowledge?
Training data runs to Apr 2024. Anything later has to come from your prompt or a tool call.
Who built Mistral Nemo?
Mistral, in the Mistral family.
Explore
Other models your pass can call.
