mistralai--mistral-medium-instruct
sap-ai-core/mistral-medium-instructVon sap-ai-core · Familie: mistral-medium · veröffentlicht 2025-05-07 · Wissensstand: 2025-05
⚠ 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.
Coding43
- Tool calling40/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)2/20
- Provider availability1/10
Agents51
- Tool calling35/35
- Structured output0/25
- Reasoning0/15
- Output token limit15/15
- Provider availability1/10
JSON / structured output47
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume17/20
Cost efficiency57
- Headline price (log-scaled)57/95
- Has prompt-cache pricing0/5
Long context45
- Context window (100K → 2M)35/90
- Has published price for full window10/10
Vision78
- Accepts image input50/50
- Context window (10K → 1M)17/30
- 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 | $2.41 < $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 | $4.82 < $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 | $1.33 < $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 | $4.10 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $5.05 < $0.01 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 sap-ai-core · mistralai--mistral-medium-instruct
Bei 1 Anbietern verfügbar
| Anbieter | Anbieter-Modell-ID | Eingabe / 1M | Ausgabe / 1M | Kontext | Veröffentlicht |
|---|---|---|---|---|---|
| SAP AI Core sap-ai-core | mistralai--mistral-medium-instruct | $0.360 | $1.22 | 128K | 2025-05-07 |
Frequently asked questions
How much does mistralai--mistral-medium-instruct cost?
mistralai--mistral-medium-instruct costs $0.360 per 1M input tokens and $1.22 per 1M output tokens, sourced from sap-ai-core. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of mistralai--mistral-medium-instruct?
mistralai--mistral-medium-instruct has a context window of 128K tokens, with a max output of 128K tokens per reply. This is the total combined size of prompt + completion.
Does mistralai--mistral-medium-instruct support tool calling?
Yes. mistralai--mistral-medium-instruct 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 mistralai--mistral-medium-instruct support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for mistralai--mistral-medium-instruct in our data source. Verify with sap-ai-core's official documentation before relying on it in production.
Can mistralai--mistral-medium-instruct accept image input?
Yes. mistralai--mistral-medium-instruct accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check sap-ai-core's docs for the exact rule.
Is mistralai--mistral-medium-instruct open-weight?
No. mistralai--mistral-medium-instruct is a proprietary model — only sap-ai-core (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to mistralai--mistral-medium-instruct?
If mistralai--mistral-medium-instruct doesn't fit, consider text-embedding-3-large, amazon--titan-embed-text, sap-abap-1. 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 sap-ai-core models
- text-embedding-3-large$0.09 in / $0.00 out
- amazon--titan-embed-text$0.14 in / $0.00 out
- sap-abap-1$0.48 in / $1.70 out
- amazon--nova-pro$0.56 in / $2.13 out
- amazon--nova-micro$0.03 in / $0.10 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.