Mistral Medium 3.5
Mistral AI chatMistral Medium 3.5 is a Mistral AI chat model.It supports a 262,144-token context windowwith up to 262,144 output tokens.Input is priced at $1.50/M tokens and output at $7.50/M tokens. Capabilities include function calling, vision, reasoning. Route Mistral Medium 3.5 via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
Estimate Mistral Medium 3.5 spend
Pick a workload, fine-tune the sliders, and see the monthly bill.
Estimate uses $1.50/M input · $7.50/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.
Pricing
Per-token rates, expressed in USD per 1M tokens. Verified Oct 22, 2026.
| Input | $1.50/M | |
| Output | $7.50/M | |
| Blended (3:1 in:out) | $3.00/M Cross-model comparable price | |
| Cached input | $0.150/M |
Context & limits
- Context window
- 262,144 tokens
- Max input
- 262,144 tokens
- Max output
- 262,144 tokens
- Modalities
- vision, text
Capabilities
- Function calling ✓ supported
- Parallel tool calls — not advertised
- Vision input ✓ supported
- Audio input — not advertised
- Audio output — not advertised
- PDF input — not advertised
- Streaming ✓ supported
- Structured output ✓ supported
- Prompt caching — not advertised
- Reasoning ✓ supported
Strengths & caveats — when to pick Mistral Medium 3.5
Data-driven from Mistral Medium 3.5's percentile within chat peers.
Where it's strong
- +long-form generation — 262,144-token max output, top-5% of peers
Watch out for
- No major caveats flagged from public spec.
Benchmark scores
Reported public benchmark numbers. Each row links to the source. Faded bar shows 6-peer average for context.
Call Mistral Medium 3.5 via Agent Command Center
One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.
agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.# Mistral Medium 3.5 via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC
client = AgentCC(
api_key=os.environ["AGENTCC_API_KEY"], # from app.futureagi.com → Settings → API Keys
base_url="https://gateway.futureagi.com/v1",
)
resp = client.chat.completions.create(
model="mistral/mistral-medium-3-5",
messages=[{"role": "user", "content": "Hello, Mistral Medium 3.5!"}],
)
print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")
# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
model="mistral/mistral-medium-3-5",
messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost: ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache: ", raw.headers.get("x-agentcc-cache"))AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗Advanced: fallback + cache config (YAML) ▸
strategy: cost-optimized
targets:
- model: mistral-medium-3-5
provider: mistral
weight: 80
fallbacks:
- model: mistral-large-4
provider: mistral
- model: gpt-5-6-sol
provider: azure-openai
guardrails: [pii, prompt-injection, secrets]
cache: { exact: true, semantic: true } Same model on other providers
mistral-medium-3-5 is also available via 1 other route. Pricing, regions, and capabilities can differ — compare before routing production traffic.
| Provider | Input / 1M | Output / 1M | Verified |
|---|---|---|---|
| Azure AI Foundry | $1.50/M | $7.50/M | Oct 22, 2026 |
Explore similar models
Grouped by Chatbot Arena tier (Mistral Medium 3.5 sits at 1426 ELO). Side-by-side links appear where a comparison page exists; otherwise, open the model profile.
- Mistral Large latestMistral AI · $0.500/M in · $1.50/M out · 262,144 ctxView model →
- Mistral Large 2411Mistral AI · $2.00/M in · $6.00/M out · 128,000 ctxView model →
- Mistral Medium 2505Mistral AI · $0.400/M in · $2.00/M out · 131,072 ctxView model →
- Mistral Small latestMistral AI · $0.150/M in · $0.600/M out · 262,144 ctxView model →
Arena ELO within −25, ≤70% of price
- Gemini 3 Pro PreviewGoogle AI · $2.00/M in · $12.00/M out · 1,048,576 ctxView model →
- GPT-5.6 SolAzure OpenAI · $4.00/M in · $20.00/M out · 922,000 ctxView model →
- Gemini 3.6 FlashGoogle Vertex AI · $0.750/M in · $3.75/M out · 1,048,576 ctxView model →
- GPT-6.1 SolAzure AI Foundry · $2.00/M in · $10.00/M out · 922,000 ctxView model →
≥30 ELO higher
- Gemini 4 ArgonGoogle AI · $2.00/M in · $10.00/M out · 1,048,576 ctxView model →
- Claude Opus 5.5Azure AI Foundry · $4.00/M in · $20.00/M out · 1,000,000 ctxView model →
- Claude Fable 5Azure AI Foundry · $10.00/M in · $50.00/M out · 1,000,000 ctxView model →
- Claude Fable 5.1Azure AI Foundry · $10.00/M in · $50.00/M out · 1,000,000 ctxView model →
25–100 ELO lower, ≤50% of price
- GPT-5 nanoAzure OpenAI · $0.0500/M in · $0.400/M out · 272,000 ctxView model →
- GPT-5 nano (2025-08-07)Azure OpenAI · $0.0500/M in · $0.400/M out · 272,000 ctxView model →
- Gemini 2.0 FlashGoogle AI · $0.1000/M in · $0.400/M out · 1,048,576 ctxView model →
- DeepSeek V3DeepSeek · $0.270/M in · $1.10/M out · 65,536 ctxView model →
FAQ
How much does Mistral Medium 3.5 cost?
Input is priced at $1.50 per 1M tokens and output at $7.50 per 1M tokens (Mistral AI, last verified Oct 22, 2026).
What is the context window of Mistral Medium 3.5?
Mistral Medium 3.5 supports a 262,144-token context window with up to 262,144 output tokens.
Does Mistral Medium 3.5 support function calling?
Yes — Mistral Medium 3.5 supports function (tool) calling.
Is Mistral Medium 3.5 good for production?
Mistral Medium 3.5 is well-suited for long-form generation — 262,144-token max output, top-5% of peers.
How can I route to Mistral Medium 3.5 with fallback?
Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.
Useful links for Mistral Medium 3.5
Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.
Start here — vendor docs are the only authoritative spec.
Third-party evals — verify the marketing.
Cross-check our number against the rest of the ecosystem.