Mistral Large 4 API Pricing and Speed
Mistral Large 4 API pricing: $0.70 per 1M tokens for input and $2.10 per 1M tokens for output, from the official API price list of Mistral AI. Official rate checked (source); OpenRouter is a separate channel below. Our measured latency and output speed are shown by route and country below. Published OpenRouter: Last checked · Source (data) · Methodology
OpenRouter: Amount worked out from the source page: $0.70 per 1M tokens, in USD · as shown in the United States on 9 Nov 2026 · the page does not say whether tax is included; we do not assume it is excluded · last price change seen on 30 Oct 2026.
Price changed 4 Nov 2026. input $1.36 → $0.70 (−48.5 %); output $4.18 → $2.10 (−49.8 %) per 1M tokens on the provider's price list. Confirmed by a later check on 5 Nov 2026.
Quality on your task: not measured by Measured Lab yet. On our data, Mistral Large 4 fits 6 of 6 common tasks by published prices, context window and terms, with calculated monthly costs.
What can I use it for?
Six common tasks cost a month at list prices
- Calculated Answer customer messages: $12.42 for 5,000 customer messages a month
- Calculated Pull data from invoices and documents with strict JSON and page images: $4.48 for 2,000 documents a month
- Calculated Summarize documents and meetings: $6.16 for 1,000 documents or meetings a month
- Calculated Translate content: $7.77 for 3,000 pages a month
- Calculated Chat assistant on your website: $133.35 for 10,000 conversations a month
- Calculated Write and review code with tool calls: $38.32 for 500 coding tasks a month
What our data confirms
- Published Strict JSON output, in Mistral documentation, read 17 Oct 2026
- Published Calls your tools, in Mistral documentation, read 17 Oct 2026
- Published Reads images; OpenRouter listing, 9 Nov 2026
Example to try
“Review this pull request and list bugs and missing tests, with the file and line of each.” Run it on your own data before you choose.
What we measured
- Observed Speed on a short test request: first token 0.6 s, 91 tokens/s (median of 65 test requests on 13 dates, short request)
Stated by the provider
- Stated by the provider Mistral for this model: DeepSWE v1.1 61.7%, Terminal-Bench 4 28.3%, SWE-Atlas-QnA 59.4%; quotes and test conditions in Quality signals
Before you choose
- Published Training on your data, per Mistral AI Commercial Terms of Service: depends on plan — not used unless the product is set to train by default and you have not opted out, or you opted in; Labs and Preview Models are used, read 9 Nov 2026
- Unknown Where requests are processed: Unknown
Prices USD per 1M tokens, as listed
- $0.70Input per 1M tokens, from Mistral AI Published
- $2.10Output per 1M tokens, from Mistral AI Published
- $0.07Cached input per 1M tokens, from Mistral AI Published
All prices by channel
| Price per 1M tokens | Mistral AI direct | Through OpenRouter | Previous prices by channel |
|---|---|---|---|
| Input | $0.70 Published | $0.70 Published | Official API: OpenRouter: |
| Output | $2.10 Published | $2.10 Published | Official API: OpenRouter: |
| Cached input · read | $0.07 Published | $0.07 Published | — |
Input price from Mistral AI, 24 Oct 2026 – 9 Nov 2026
24 Oct 2026$1.36 → $0.709 Nov 2026
Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$0.68 → $1.36 → $0.709 Nov 2026
Context window1,048,576tokens Published
Max output262,144tokens Published
OpenRouter providers who serves this model through OpenRouter, at what price
OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.
Pinned min: $0.70 / $2.10 · Mistral (mistral/zdr)
Unpinned range: input $0.70–$0.77, output $2.10–$2.31 across 2 endpoints of 1 provider (listing shows $0.70 / $2.10).
Models with the widest provider price spread on OpenRouter
Request fragment that pins Mistral (mistral/zdr):
{"provider": {"order": ["mistral/zdr"], "allow_fallbacks": false}}With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).
All endpoints (2), by input price
| Provider | Endpoint tag | Precision | Input | Output | Context, tokens |
|---|---|---|---|---|---|
| Mistral | mistral/zdr | Not stated | $0.70 | $2.10 | 1,048,576 |
| Mistral | mistral/eu | Not stated | $0.77 | $2.31 | 524,288 |
Sorted by input price, then output price. Precision is the quantization field of the endpoints list.
Measured by us our own short test request: about 380 tokens in, a short JSON answer out · medians from answers on two dates or more
United States
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Mistralreasoning: off65 answers on 13 dates · 100 % answered | 634 msrange 0.49–7.39 s · slow 10 %: 1.71 s Observed | 91.3 tokens/srange 12.9–212 · slowest 10 %: 41.2 tokens/s | $0.000376range $0.000375–$0.000378 Calculated | 0for 64 visible |
| OpenRouter → Mistralreasoning: off65 answers on 13 dates · 100 % answered | 753 msrange 0.49–6.02 s · slow 10 %: 2.98 s Observed | 82.2 tokens/srange 7.0–222 · slowest 10 %: 34.6 tokens/s | $0.000376range $0.000375–$0.000379 Calculated | 0for 64 visible |
United Kingdom
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Mistralreasoning: off55 answers on 11 dates · 100 % answered | 684 msrange 0.39–4.03 s · slow 10 %: 2.28 s Observed | 96.4 tokens/srange 7.7–159 · slowest 10 %: 34.6 tokens/s | $0.000376range $0.000375–$0.000379 Calculated | 0for 64 visible |
| OpenRouter → Mistralreasoning: off55 answers on 11 dates · 100 % answered | 744 msrange 0.46–4.26 s · slow 10 %: 2.02 s Observed | 89.6 tokens/srange 10.0–300 · slowest 10 %: 29.8 tokens/s | $0.000377range $0.000375–$0.000377 Calculated | 0for 64 visible |
Germany
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Mistralreasoning: off55 answers on 11 dates · 100 % answered | 626 msrange 0.42–3.51 s · slow 10 %: 2.24 s Observed | 97.0 tokens/srange 17.4–181 · slowest 10 %: 30.2 tokens/s | $0.000377range $0.000375–$0.000378 Calculated | 0for 64 visible |
| OpenRouter → Mistralreasoning: off55 answers on 11 dates · 100 % answered | 790 msrange 0.38–4.72 s · slow 10 %: 2.07 s Observed | 98.5 tokens/srange 8.5–268 · slowest 10 %: 34.7 tokens/s | $0.000377range $0.000375–$0.000379 Calculated | 0for 64 visible |
Canada
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Mistralreasoning: off55 answers on 11 dates · 100 % answered | 774 msrange 0.43–8.77 s · slow 10 %: 2.49 s Observed | 101 tokens/srange 9.8–373 · slowest 10 %: 42.5 tokens/s | $0.000377range $0.000375–$0.000379 Calculated | 0for 64 visible |
| OpenRouter → Mistralreasoning: off55 answers on 11 dates · 100 % answered | 748 msrange 0.55–5.08 s · slow 10 %: 2.17 s Observed | 89.7 tokens/srange 15.5–181 · slowest 10 %: 47.1 tokens/s | $0.000376range $0.000375–$0.000378 Calculated | 0for 64 visible |
Australia
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Mistralreasoning: off55 answers on 11 dates · 100 % answered | 842 msrange 0.70–4.30 s · slow 10 %: 2.53 s Observed | 90.8 tokens/srange 9.3–216 · slowest 10 %: 21.9 tokens/s | $0.000377range $0.000375–$0.000379 Calculated | 0for 64 visible |
| OpenRouter → Mistralreasoning: off55 answers on 11 dates · 100 % answered | 1.09 srange 0.70–4.43 s · slow 10 %: 2.44 s Observed | 95.2 tokens/srange 24.5–216 · slowest 10 %: 49.2 tokens/s | $0.000377range $0.000375–$0.000378 Calculated | 0for 64 visible |
- Hidden reasoning tokens are billed as output, at the output price, even though they are not part of the answer.
- Through OpenRouter, the request goes to the named provider; the price and speed can differ from the direct API.
How the test works and what each number means: methodology. The figures are also in our open data.
Quality signals public test results, each with its source and date
| Signal | Result | Source |
|---|---|---|
| Instruction followingIFEval, 50 prompts · reasoning: off | 88 % Observedof 50 prompts with every instruction followed | Our run of a fixed IFEval subset, checked by code88 % on 22 Oct 2026 · 90 % on 17 Oct 2026 · instruction level 91 % |
Figures the provider publishes (6)
| Benchmark | Provider's figure | Where the provider says it |
|---|---|---|
| DeepSWE v1.1 | 61.7% Stated by the provider | ML4 excels across software engineering, repository understanding, and complex terminal workflows, scoring 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA, and 28.3% on Terminal-Bench 4.Introducing Mistral Large 4 | Mistralread 17 Oct 2026 |
| Terminal-Bench 4 | 28.3% Stated by the provider | ML4 excels across software engineering, repository understanding, and complex terminal workflows, scoring 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA, and 28.3% on Terminal-Bench 4.Introducing Mistral Large 4 | Mistralread 17 Oct 2026 |
| SWE-Atlas-QnA | 59.4% Stated by the provider | ML4 excels across software engineering, repository understanding, and complex terminal workflows, scoring 61.7% on DeepSWE v1.1, 59.4% on SWE-Atlas-QnA, and 28.3% on Terminal-Bench 4.Introducing Mistral Large 4 | Mistralread 17 Oct 2026 |
| AutomationBench | 59.9% Stated by the provider | On AutomationBench — 657 business workflows across apps like Gmail, Google Sheets, Slack, and Salesforce — it scores 59.9%, ahead of Kimi K3, MiMo-V2.6-Pro, and DeepSeek V4 Pro.Introducing Mistral Large 4 | Mistralread 17 Oct 2026 |
| AA-Briefcase | 1,393 Elo Stated by the provider | On AA-Briefcase, which evaluates long-horizon knowledge work, it reaches 1,393 Elo, ahead of DeepSeek V4 Pro.Introducing Mistral Large 4 | Mistralread 17 Oct 2026 |
| Cybench | 93% Stated by the provider | It also solves 93% of the challenges in Cybench, a set of 40 exercises drawn from security competitions, one of the highest scores reported for an open-weight model.Introducing Mistral Large 4 | Mistralread 17 Oct 2026 |
- Your own task: quality on it is not measured here. These are public test sets; a short trial on a few of your own examples is the check that fits your work.
- Other public leaderboards, without figures copied here: human preference votes on open-ended answers: Arena (LMArena) text leaderboard; long tasks in coding, data analysis and research: LiveBench.
What each signal covers and how our run is scored: methodology.
How we got this number
- What we read: the published price on openrouter.ai/api/v1/models
- Checked: ; tracked since 16 Oct 2026
- Shown in: the United States
- Checks so far: 25 checks since 16 Oct 2026
- What changed: the price last changed on ; every change is listed under History
- Page updated:
Other measured facts
| Question | Answer | Checked | Status |
|---|---|---|---|
| How much does Mistral Large 4 cost per 1M cache-read tokens (cache hits) directly from Mistral AI (official API price)? | $0.07 per 1M tokens | Published | |
| How much does Mistral Large 4 cost per 1M cache-read tokens (cache hits) on OpenRouter? | $0.07 per 1M tokens | Published | |
| How much does Mistral Large 4 cost per 1M input tokens directly from Mistral AI (official API price)? | $0.70 per 1M tokens | Published | |
| How much does Mistral Large 4 cost per 1M output tokens directly from Mistral AI (official API price)? | $2.10 per 1M tokens | Published | |
| How much does Mistral Large 4 cost per 1M output tokens on OpenRouter? | $2.10 per 1M tokens | Published | |
| What is the context window of Mistral Large 4 on OpenRouter, in tokens? | 1,048,576 tokens | Published | |
| What is the maximum output length of Mistral Large 4 on OpenRouter, in tokens? | 262,144 tokens | Published |
History
- — $4.18 per 1M tokens → $2.10 per 1M tokens (How much does Mistral Large 4 cost per 1M output tokens directly from Mistral AI (official API price)?) Confirmed by the check on 5 Nov 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — $0.14 per 1M tokens → $0.07 per 1M tokens (How much does Mistral Large 4 cost per 1M cache-read tokens (cache hits) directly from Mistral AI (official API price)?) Confirmed by the check on 5 Nov 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — $1.36 per 1M tokens → $0.70 per 1M tokens (How much does Mistral Large 4 cost per 1M input tokens directly from Mistral AI (official API price)?) Confirmed by the check on 5 Nov 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — $4.18 per 1M tokens → $2.10 per 1M tokens (How much does Mistral Large 4 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 31 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — $1.36 per 1M tokens → $0.70 per 1M tokens Confirmed by the check on 31 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — $0.14 per 1M tokens → $0.07 per 1M tokens (How much does Mistral Large 4 cost per 1M cache-read tokens (cache hits) on OpenRouter?) Confirmed by the check on 31 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — $2.09 per 1M tokens → $4.18 per 1M tokens (How much does Mistral Large 4 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 22 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — $0.68 per 1M tokens → $1.36 per 1M tokens Confirmed by the check on 22 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
- — First check: $0.68 per 1M tokens
The source record lists $0.0000007 per token ($0.70 per 1M tokens), fetched on 9 Nov 2026.
The source record, as published
"prompt":"0.0000007"
Latest briefings each price change recalculated as a task cost
- DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
- DeepSeek V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)
- MoonshotAI Kimi K2.5: price rise input $0.500 → $0.532 per 1M tokens (+6 %), output $2.50 → $3.33 per 1M tokens (+33 %)
Official price over time
Record history — 164 records for 8 questions
- Last record
- Shown in
- the United States
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.70 per 1M tokens | Published |
| 8 Nov 2026 | $0.70 per 1M tokens | Published |
| 7 Nov 2026 | $0.70 per 1M tokens | Published |
| 6 Nov 2026 | $0.70 per 1M tokens | Published |
| 5 Nov 2026 | $0.70 per 1M tokens | Published |
| 4 Nov 2026 | $0.70 per 1M tokens | Published |
| 3 Nov 2026 | $0.70 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.07 per 1M tokens | Published |
| 8 Nov 2026 | $0.07 per 1M tokens | Published |
| 7 Nov 2026 | $0.07 per 1M tokens | Published |
| 6 Nov 2026 | $0.07 per 1M tokens | Published |
| 5 Nov 2026 | $0.07 per 1M tokens | Published |
| 4 Nov 2026 | $0.07 per 1M tokens | Published |
| 3 Nov 2026 | Unknown | Unknown |
| 2 Nov 2026 | Unknown | Unknown |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.07 per 1M tokens | Published |
| 8 Nov 2026 | $0.07 per 1M tokens | Published |
| 7 Nov 2026 | $0.07 per 1M tokens | Published |
| 6 Nov 2026 | $0.07 per 1M tokens | Published |
| 5 Nov 2026 | $0.07 per 1M tokens | Published |
| 4 Nov 2026 | $0.07 per 1M tokens | Published |
| 3 Nov 2026 | $0.07 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.70 per 1M tokens | Published |
| 8 Nov 2026 | $0.70 per 1M tokens | Published |
| 7 Nov 2026 | $0.70 per 1M tokens | Published |
| 6 Nov 2026 | $0.70 per 1M tokens | Published |
| 5 Nov 2026 | $0.70 per 1M tokens | Published |
| 4 Nov 2026 | $0.70 per 1M tokens | Published |
| 3 Nov 2026 | Unknown | Unknown |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $2.10 per 1M tokens | Published |
| 8 Nov 2026 | $2.10 per 1M tokens | Published |
| 7 Nov 2026 | $2.10 per 1M tokens | Published |
| 6 Nov 2026 | $2.10 per 1M tokens | Published |
| 5 Nov 2026 | $2.10 per 1M tokens | Published |
| 4 Nov 2026 | $2.10 per 1M tokens | Published |
| 3 Nov 2026 | Unknown | Unknown |
| 2 Nov 2026 | Unknown | Unknown |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $2.10 per 1M tokens | Published |
| 8 Nov 2026 | $2.10 per 1M tokens | Published |
| 7 Nov 2026 | $2.10 per 1M tokens | Published |
| 6 Nov 2026 | $2.10 per 1M tokens | Published |
| 5 Nov 2026 | $2.10 per 1M tokens | Published |
| 4 Nov 2026 | $2.10 per 1M tokens | Published |
| 3 Nov 2026 | $2.10 per 1M tokens | Published |
| 2 Nov 2026 | $2.10 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 1,048,576 tokens | Published |
| 8 Nov 2026 | 1,048,576 tokens | Published |
| 7 Nov 2026 | 1,048,576 tokens | Published |
| 6 Nov 2026 | 1,048,576 tokens | Published |
| 5 Nov 2026 | 1,048,576 tokens | Published |
| 4 Nov 2026 | 1,048,576 tokens | Published |
| 3 Nov 2026 | 1,048,576 tokens | Published |
| 2 Nov 2026 | 1,048,576 tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 262,144 tokens | Published |
| 8 Nov 2026 | 262,144 tokens | Published |
| 7 Nov 2026 | 262,144 tokens | Published |
| 6 Nov 2026 | 262,144 tokens | Published |
| 5 Nov 2026 | 262,144 tokens | Published |
| 4 Nov 2026 | 262,144 tokens | Published |
| 3 Nov 2026 | 262,144 tokens | Published |
Showing the latest 60 of 164 records; the full history is in data.json and data.csv.