LLMHOSTING.AI the compute price terminal

Mistral Medium 3.5 API pricing

2 providers serve Mistral Medium 3.5. Mistral Medium 3.5 is an open-weight model (Modified MIT (revenue cap)) with 128B total parameters, up to 262K context. Prices below are per 1M tokens, cheapest input first (self-hosting math further down).

Refreshed 2026-08-23 · list prices from provider APIs
Input floor $1.50/1M at Mistral AI and OpenRouter Output floor $7.50/1M at Mistral AI and OpenRouter Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
Mistral AI $1.50 $7.50output floor - 262K Use
OpenRouter marketplace quote $1.50 $7.50 - 262K Use

The cheapest way to run Mistral Medium 3.5

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $330/month — the same at Mistral AI and OpenRouter. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. On output-token cost alone, a busy self-hosted deployment can work out cheaper (~$0.876/1M output on MI300X). See the math below. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Or run it yourself: Mistral Medium 3.5 self-hosting economics

Mistral Medium 3.5 is open-weight (Modified MIT (revenue cap)), so the API price above competes with the GPU-hour market. 128B total parameters needs roughly 176 GB VRAM at FP8 or 88 GB at INT4, KV-cache headroom included.

GPU that fits (FP8, single card)VRAMFrom $/hrCheapest at
MI300X 192 GB $0.500community RunPod Rent
B200 180 GB $3.06spot Verda
B300 288 GB $3.75spot Verda
GB300 288 GB $4.31spot Verda
Breakeven estimate: a well-batched vLLM deployment on one MI300X ($0.500/hr) at ~317 aggregate tok/s and 50% utilization works out to roughly $0.876 per 1M output tokens, versus $7.50 via the cheapest output-token API (Mistral AI and OpenRouter). Self-hosting wins on cost if you can keep the GPU busy. Planning estimate: throughput varies with hardware, quantization, batch size and context. Tune it in the calculator.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
Mistral Nemo $0.019 $0.030 9
Mistral Large $0.500 $1.50 7
Mistral Small 4 $0.100 $0.300 7
Mistral-7b $0.070 $0.130 4
Mistral Small 3.2 24B $0.075 $0.200 4
Mistral-Large-3 $0.500 $1.20 3

FAQ

What is the cheapest API for Mistral Medium 3.5?

As of 2026-08-23, the lowest input price for Mistral Medium 3.5, $1.50 per 1M tokens, is the same list price at Mistral AI and OpenRouter. The lowest output price, $7.50 per 1M tokens, is likewise shared by the same providers. The cheapest provider for a real workload depends on its input/output mix.

How much VRAM do you need to self-host Mistral Medium 3.5?

Mistral Medium 3.5 has 128B parameters, so plan for roughly 176 GB of VRAM at FP8 or 88 GB at INT4/AWQ, KV-cache headroom included. A single MI300X (192 GB) fits it.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON