Skip to main content

Mistral Medium

Mistral AI's medium-sized model, soon to be deprecated, is a closed-source model known for its impressive abilities in reasoning, code comprehension, JSON handling, and chat applications. Powered by a proprietary closed-source prototype, it has demonstrated competitive performance in benchmark evaluations, often rivaling leading models from other companies. However, please note that this model is approaching deprecation and may soon be replaced by newer versions with further advancements and improvements. Stay tuned for the latest updates from Mistral AI.

Input / output price
$1.50 / $7.50 per 1M
Context
262K tokens
Released
Feb 26, 2024
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "mistral/mistral-medium".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Mistralmistral/mistral-medium
$1.50/M$7.50/M

Is a provider down? Mistral AI status

Pricing

USD per 1M tokens on Mistral, after gateway discounts.

Input
$1.50 per 1M
Output
$7.50 per 1M
Cache read
$0.15 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$1.50/MMistral

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

3.0tokens/sacross providers

Faster than 3% of the other 599 models on the gateway

Response latency

Lower is better

0.4sacross providers

Faster than 90% of the other 780 models on the gateway

Benchmarks

2 published scores from 2 sources, each linked to where it was published.

Published scores

BenchmarkScore
LMArena EloLMArena1223 Elo · #185 of 191

Apps

Use Mistral Medium in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Mistral Medium FAQ

Short answers, built from the data on this page.

Mistral Medium is a model from Mistral, released on Feb 26, 2024. Mistral AI's medium-sized model, soon to be deprecated, is a closed-source model known for its impressive abilities in reasoning, code comprehension, JSON handling, and chat applications. Powered by a proprietary closed-source prototype, it has demonstrated competitive performance in benchmark evaluations, often rivaling leading models from other companies. However, please note that this model is approaching deprecation and may soon be replaced by newer versions with further advancements and improvements. Stay tuned for the latest updates from Mistral AI.

On the Respan gateway, Mistral Medium costs $1.50 per 1M input tokens and $7.50 per 1M output tokens on Mistral, after gateway discounts.

Mistral Medium is served by Mistral.

Mistral Medium accepts up to 262K tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "mistral/mistral-medium". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Mistral Medium has 2 published benchmark scores, including LMArena Elo 1223 and MT-Bench 8.6. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.