Mistral Medium
Mistral AI chatMistral Medium is a Mistral AI chat model.It supports a 32,000-token context windowwith up to 8,191 output tokens.Input is priced at $2.70/M tokens and output at $8.10/M tokens. Route Mistral Medium via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
Estimate Mistral Medium spend
Pick a workload, fine-tune the sliders, and see the monthly bill.
Estimate uses $2.70/M input · $8.10/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 May 12, 2026.
| Input | $2.70/M | |
| Output | $8.10/M |
Limits
- Context window
- 32,000 tokens
- Max input
- 32,000 tokens
- Max output
- 8,191 tokens
- Modalities
- text
Capabilities
- Function calling — not advertised
- Parallel tool calls — not advertised
- Vision input — not advertised
- Audio input — not advertised
- Audio output — not advertised
- PDF input — not advertised
- Streaming ✓ supported
- Structured output ✓ supported
- Prompt caching — not advertised
- Reasoning — not advertised
Where it's strong
- +pricing — cheaper than 76% of priced chat models on Future AGI
Watch out for
- !limited context — 32,000-token window is in the bottom quartile; not ideal for long documents or large RAG
- !agentic workflows — no advertised function-calling; use a tool-capable model and route via Agent Command Center for fallback
Benchmark scores
Reported public benchmark numbers. Each row links to the source.
Call Mistral Medium 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 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",
messages=[{"role": "user", "content": "Hello, Mistral Medium!"}],
)
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",
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 ↗Compare with similar models
Mistral Medium doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark.
FAQ
How much does Mistral Medium cost?
Input is priced at $2.70 per 1M tokens and output at $8.10 per 1M tokens (Mistral AI, last verified May 12, 2026).
What is the context window of Mistral Medium?
Mistral Medium supports a 32,000-token context window with up to 8,191 output tokens.
Does Mistral Medium support function calling?
Mistral Medium does not currently advertise function-calling support. For agentic workloads, prefer a tool-calling-capable model and route via Agent Command Center for fallback.
Is Mistral Medium good for production?
Mistral Medium is well-suited for pricing — cheaper than 76% of priced chat models on Future AGI. Consider alternatives if you need limited context — 32,000-token window is in the bottom quartile; not ideal for long documents or large RAG.
How can I route to Mistral Medium 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
Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.
Third-party evals — verify the marketing.
Cross-check our number against the rest of the ecosystem.