Skip to main content

Mistral Medium 3.5

Mistral Medium 3 5 is a Mistral AI model for coding, reasoning, instruction following, or multimodal language tasks.

Model card on Hugging Face
Input / output price
$1.50 / $7.50 per 1M
Context
262K tokens
Released
Apr 28, 2026
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-3-5".

Read docs

Providers

2 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Mistralmistral/mistral-medium-3-5
$1.50/M$7.50/M
OpenRouteropenrouter/mistral-medium-3-5
$1.50/M$7.50/M

Is a provider down? Mistral AI status, OpenRouter status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input
$1.50 per 1M
Average output
$7.50 per 1M
Average cache read
$0.15 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$1.50/MMistral and OpenRouter

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

6.5tokens/sacross providers

Faster than 25% of the other 596 models on the gateway

Response latency

Lower is better

0.3sacross providers

Faster than 89% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 9 published scores from 4 sources, each linked to where it was published.

26.3/ 100

Respan Index#106 of 176

176 ranked models. The shaded band is this model's 95% interval, 20.4 to 44.5. Step 3.5 Flash and Qwen3.6 35B-A3B fall inside it, so the gap is within the margin of error.
Mistral Medium 3.5 by category: Coding 6.7, Agents 42.9, Reasoning 20.4, Knowledge & language 17.1 (estimated), Human preference 47.5
  1. 106Mistral Medium 3.526.3
  2. 105Step 3.5 Flash26.5
  3. 107Qwen3.6 35B-A3B26.0

Published scores

BenchmarkScore
SWE-bench VerifiedMistral77.6%
WeirdMLHåvard Tveit Ihle43.7%

Compare Mistral Medium 3.5: Mistral Medium 3.5 vs Mistral Large 4

Apps

Use Mistral Medium 3.5 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 3.5 FAQ

Short answers, built from the data on this page.

Mistral Medium 3.5 is a model from Mistral, released on Apr 28, 2026. Mistral Medium 3 5 is a Mistral AI model for coding, reasoning, instruction following, or multimodal language tasks.

On the Respan gateway, Mistral Medium 3.5 costs $1.50 per 1M input tokens and $7.50 per 1M output tokens on every provider, after gateway discounts.

Mistral Medium 3.5 is available through 2 providers: Mistral and OpenRouter.

Mistral Medium 3.5 accepts up to 262K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "mistral/mistral-medium-3-5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Mistral Medium 3.5 scores 26.3 out of 100 on the Respan Index v1.1, ranking #106 of 176 models. By category: Coding 6.7, Agents 42.9, Reasoning 20.4, Knowledge & language 17.1 (estimated), and Human preference 47.5. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Mistral Medium 3.5 has 9 published benchmark scores, including SWE-bench Verified 77.6%, Tau3 Telecom 91.4, and LMArena Elo 1426. 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.