Mistral Medium 3.5 Thinking
nano-gpt/medium-3-5-thinkingVon nano-gpt · veröffentlicht 2026-04-30
⚠ Dies ist ein Community-Finetune oder Derivat — keine offizielle Anbieter-Veröffentlichung.
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Fähigkeiten
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding79
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)8/20
- Provider availability1/10
Agents91
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability1/10
JSON / structured output72
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control0/10
- Price-friendly for high-volume2/20
Cost efficiency39
- Headline price (log-scaled)39/95
- Has prompt-cache pricing0/5
Long context60
- Context window (100K → 2M)50/90
- Has published price for full window10/10
Vision82
- Accepts image input50/50
- Context window (10K → 1M)21/30
- Has published price10/10
- Provider availability1/10
Production-readiness50
- Number of independent providers5/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers10/10
- Official model (not derivative)0/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $11.25 $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $22.50 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $6.75 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $19.50 $0.02 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $22.50 $0.02 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Preis-Details
Empfohlene Preise von nano-gpt · mistral/mistral-medium-3.5:thinking
Bei 1 Anbietern verfügbar
| Anbieter | Anbieter-Modell-ID | Eingabe / 1M | Ausgabe / 1M | Kontext | Veröffentlicht |
|---|---|---|---|---|---|
| NanoGPT nano-gpt | mistral/mistral-medium-3.5:thinking | $1.50 | $7.50 | 256K | 2026-04-30 |
Frequently asked questions
How much does Mistral Medium 3.5 Thinking cost?
Mistral Medium 3.5 Thinking costs $1.50 per 1M input tokens and $7.50 per 1M output tokens, sourced from nano-gpt. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Mistral Medium 3.5 Thinking?
Mistral Medium 3.5 Thinking has a context window of 256K tokens, with a max output of 33K tokens per reply. This is the total combined size of prompt + completion.
Does Mistral Medium 3.5 Thinking support tool calling?
Yes. Mistral Medium 3.5 Thinking supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Mistral Medium 3.5 Thinking support structured output / JSON mode?
Yes. Mistral Medium 3.5 Thinking supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can Mistral Medium 3.5 Thinking accept image input?
Yes. Mistral Medium 3.5 Thinking accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check nano-gpt's docs for the exact rule.
Is Mistral Medium 3.5 Thinking open-weight?
No. Mistral Medium 3.5 Thinking is a proprietary model — only nano-gpt (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to Mistral Medium 3.5 Thinking?
If Mistral Medium 3.5 Thinking doesn't fit, consider ERNIE X1.1, Brave (Research), MiroThinker 1.7 Deep Research Mini. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More nano-gpt models
- ERNIE X1.1$0.15 in / $0.60 out
- Brave (Research)$5.00 in / $5.00 out
- MiroThinker 1.7 Deep Research Mini$1.25 in / $10.00 out
- Baichuan 4 Turbo$2.42 in / $2.42 out
- v0 1.0 MD$3.00 in / $15.00 out
Capability lists this model is in
Zuletzt aktualisiert:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.