MiniMax-M2.7
MiniMax
Input / 1M
$0.0389
Output / 1M
$0.1943
Cache read / 1M
$0.0039
Cache write / 1M
$0.0194
Image support unknown
View details83% below official
Pricing and Billing
What you are charged for, how caching lowers your cost, and how to check any single call against your bill.
1. What you pay for
Pricing is per token, quoted per 1 million tokens, and charged in USD ($). There is no subscription and no monthly minimum — you buy credits, and each call deducts what it actually used. Credits never expire.
Every call is billed across up to four separate token types, each with its own rate. This matters more than it sounds: output is typically 5–6× the input rate on the same model, so a rough estimate based on input alone will understate your bill.
| Token type | Typical rate | What it is |
|---|---|---|
| Input | Baseline | The prompt you send, minus anything served from cache. |
| Output | 5–6× input on most models | What the model generates. Usually the largest line on your bill — cap it with max_tokens if cost matters more than length. A few models price output far lower, so check the model you actually use. |
| Cache read | ~10% of input on most models | Prompt content the provider already had cached from an earlier call. Heavily discounted — but not on every model: on a few, cached input costs the same as or more than regular input, so caching is not automatically a saving. |
| Cache write | Varies by model | Content being placed into the cache so later calls can reuse it. On Claude models this runs above the input rate; on several others it is below. Per-model rates are on the pricing page. |
One API key reaches every model in your key's scope — you do not need a separate key per model. All of your keys draw on the same account balance.
2. All model prices
Every rate below is what your account is actually charged — these come from the same price records the billing system reads, so nothing here can drift out of sync with your bill. Token prices are shown in USD per 1 million tokens; image models show a price per image, and video models a price per second.
Models available
73
Providers
15
Lowest input price
$0.0389 / 1M
Showing 73 of 73 models/All models
claude-haiku-4-5-20251001
Anthropic
Input / 1M
$0.0777
Output / 1M
$0.3886
Cache read / 1M
$0.0078
Cache write / 1M
$0.1166
256K contextUnderstands imagesEveryday chatCodingHigh throughputImage understanding
View details92% below official
doubao-seed-2.0-lite
ByteDance / Doubao
Input / 1M
$0.0777
Output / 1M
$0.3886
Cache read / 1M
$0.0078
Cache write / 1M
$0.0389
Image support unknownEveryday chatHigh throughput
View details8% below official
jzs-max-3.0
JZS Token
Input / 1M
$0.0777
Output / 1M
$0.3886
Cache read / 1M
$0.0078
Cache write / 1M
$0.0777
1M contextUnderstands imagesEveryday chatCodingAgentsLong documentsImage understandingExclusive
Free until Nov 30, 2026 (UTC) · $0 billed during the promotion
LongCat-2.0
Meituan / LongCat
Input / 1M
$0.0777
Output / 1M
$0.3109
Cache read / 1M
$0.0078
Cache write / 1M
$0.0777
1M contextText input onlyEveryday chatHigh throughputLong documents
View details74% below official
LongCat-2.5
Meituan / LongCat
Input / 1M
$0.0777
Output / 1M
$0.3109
Cache read / 1M
$0.0078
Cache write / 1M
$0.0777
Image support unknown
mimo-v2.6-flash
Xiaomi / MiMo
Input / 1M
$0.0777
Output / 1M
$0.3886
Cache read / 1M
$0.0078
Cache write / 1M
$0.0777
Image support unknownEveryday chatCodingHigh throughput
MiniMax-M2.7-highspeed
MiniMax
Input / 1M
$0.0777
Output / 1M
$0.3886
Cache read / 1M
$0.0078
Cache write / 1M
$0.0389
Image support unknown
View details83% below official
MiniMax-M3
MiniMax
Input / 1M
$0.0777
Output / 1M
$0.3886
Cache read / 1M
$0.0078
Cache write / 1M
$0.0194
1M contextUnderstands imagesEveryday chatLong documentsImage understandingHigh throughput
View details67% below official
MiniMax-M3.1-flash
MiniMax
Input / 1M
$0.0777
Output / 1M
$0.3886
Cache read / 1M
$0.0078
Cache write / 1M
$0.0777
Image support unknownEveryday chatLong documentsHigh throughput
step-3.7-flash
StepFun
Input / 1M
$0.0777
Output / 1M
$0.3886
Cache read / 1M
$0.0078
Cache write / 1M
$0.0389
256K contextUnderstands imagesEveryday chatHigh throughputImage understanding
View details59% below official
deepseek-v4-flash
DeepSeek
Input / 1M
$0.1495
Output / 1M
$0.7474
Cache read / 1M
$0.0149
Cache write / 1M
$0.1495
1M contextText input onlyEveryday chatCodingHigh throughput
⏱ Off-peak rate · peak 09:00–12:00 ×2, 14:00–18:00 ×2 (Asia/Shanghai)
deepseek-v4.1-flash
DeepSeek
Input / 1M
$0.1495
Output / 1M
$0.7474
Cache read / 1M
$0.0149
Cache write / 1M
$0.1495
Image support unknownEveryday chatCodingHigh throughput
⏱ Off-peak rate · peak 09:00–12:00 ×2, 14:00–18:00 ×2 (Asia/Shanghai)
glm-5.3-flash
Zhipu / Z.ai
Input / 1M
$0.1555
Output / 1M
$0.7773
Cache read / 1M
$0.0155
Cache write / 1M
$0.1555
Image support unknownEveryday chatCodingHigh throughput
gpt-5.6-luna
OpenAI
Input / 1M
$0.1555
Output / 1M
$0.7773
Cache read / 1M
$0.0155
Cache write / 1M
$0.1555
258K contextUnderstands imagesEveryday chatHigh throughputImage understanding
View details22% below official
gpt-6-luna
OpenAI
Input / 1M
$0.1555
Output / 1M
$0.7773
Cache read / 1M
$0.0155
Cache write / 1M
$0.1555
Image support unknownEveryday chatHigh throughputImage understanding
gpt-6.1-terra
OpenAI
Input / 1M
$0.1555
Output / 1M
$0.7773
Cache read / 1M
$0.0155
Cache write / 1M
$0.1555
Image support unknownEveryday chatCodingAgentsImage understanding
View details84% below official
kimi-k2.6
Moonshot / Kimi
Input / 1M
$0.1555
Output / 1M
$0.7773
Cache read / 1M
$0.0155
Cache write / 1M
$0.1555
Image support unknown
View details80% below official
MiniMax-M3-highspeed
MiniMax
Input / 1M
$0.1555
Output / 1M
$0.7773
Cache read / 1M
$0.0155
Cache write / 1M
$0.0777
Image support unknownEveryday chatLong documentsHigh throughput
MiniMax-M3.1
MiniMax
Input / 1M
$0.1555
Output / 1M
$0.7773
Cache read / 1M
$0.0155
Cache write / 1M
$0.1555
Image support unknownEveryday chatLong documentsHigh throughput
qwen3.8-flash
Alibaba / Qwen
Input / 1M
$0.1555
Output / 1M
$0.7773
Cache read / 1M
$0.0155
Cache write / 1M
$0.1555
Image support unknownEveryday chatCodingHigh throughput
doubao-seed-2.0-code
ByteDance / Doubao
Input / 1M
$0.2332
Output / 1M
$1.17
Cache read / 1M
$0.0233
Cache write / 1M
$0.2332
200K contextUnderstands imagesCodingAgentsImage understanding
View details48% below official
doubao-seed-2.0-pro
ByteDance / Doubao
Input / 1M
$0.2332
Output / 1M
$1.17
Cache read / 1M
$0.0233
Cache write / 1M
$0.2332
128K contextUnderstands imagesEveryday chatCodingImage understanding
View details48% below official
doubao-seed-2.1-turbo
ByteDance / Doubao
Input / 1M
$0.2332
Output / 1M
$1.17
Cache read / 1M
$0.0233
Cache write / 1M
$0.2332
Image support unknownEveryday chatHigh throughput
View details44% below official
gpt-5.6-terra
OpenAI
Input / 1M
$0.2332
Output / 1M
$1.40
Cache read / 1M
$0.0233
Cache write / 1M
$0.3498
258K contextUnderstands imagesEveryday chatCodingAgentsImage understanding
View details88% below official
gpt-6-sol
OpenAI
Input / 1M
$0.3109
Output / 1M
$1.87
Cache read / 1M
$0.0311
Cache write / 1M
$0.3886
Image support unknownEveryday chatCodingComplex reasoningImage understanding
View details81% below official
gpt-6.1-sol
OpenAI
Input / 1M
$0.3109
Output / 1M
$1.87
Cache read / 1M
$0.0311
Cache write / 1M
$0.3886
Image support unknownCodingAgentsComplex reasoningImage understanding
View details81% below official
mimo-v2.5-pro
Xiaomi / MiMo
Input / 1M
$0.3109
Output / 1M
$1.55
Cache read / 1M
$0.0311
Cache write / 1M
$0.3109
1M contextText input onlyCodingComplex reasoningLong documents
mimo-v2.6-pro
Xiaomi / MiMo
Input / 1M
$0.3109
Output / 1M
$1.55
Cache read / 1M
$0.0311
Cache write / 1M
$0.3109
Image support unknownCodingComplex reasoningLong documents
qwen3.7-plus
Alibaba / Qwen
Input / 1M
$0.3109
Output / 1M
$1.55
Cache read / 1M
$0.0311
Cache write / 1M
$0.3109
1M contextUnderstands imagesEveryday chatCodingLong documentsImage understanding
gpt-5.5
OpenAI
Input / 1M
$0.3886
Output / 1M
$2.33
Cache read / 1M
$0.0389
Cache write / 1M
$0.3886
258K contextUnderstands imagesEveryday chatCodingAgentsImage understanding
View details92% below official
grok-4.5
xAI / Grok
Input / 1M
$0.3886
Output / 1M
$1.94
Cache read / 1M
$0.4858
Cache write / 1M
$0.3886
500K contextUnderstands imagesEveryday chatComplex reasoningLong documentsImage understanding
grok-4.6
xAI / Grok
Input / 1M
$0.3886
Output / 1M
$1.94
Cache read / 1M
$0.4858
Cache write / 1M
$0.3886
Image support unknownEveryday chatComplex reasoningLong documents
grok-4.7
xAI / Grok
Input / 1M
$0.3886
Output / 1M
$1.94
Cache read / 1M
$0.0389
Cache write / 1M
$0.4858
Image support unknownEveryday chatComplex reasoningLong documents
View details67% below official
deepseek-v4-pro
DeepSeek
Input / 1M
$0.4484
Output / 1M
$2.24
Cache read / 1M
$0.0448
Cache write / 1M
$0.4484
1M contextText input onlyCodingComplex reasoningLong documents
⏱ Off-peak rate · peak 09:00–12:00 ×2, 14:00–18:00 ×2 (Asia/Shanghai)
kimi-k2.7
Moonshot / Kimi
Input / 1M
$0.4664
Output / 1M
$2.33
Cache read / 1M
$0.0466
Cache write / 1M
$0.4664
Image support unknownEveryday chatCodingLong documents
kimi-k2.8
Moonshot / Kimi
Input / 1M
$0.4664
Output / 1M
$2.33
Cache read / 1M
$0.0466
Cache write / 1M
$0.4664
Image support unknownEveryday chatCodingLong documents
glm-5.2
Zhipu / Z.ai
Input / 1M
$0.6218
Output / 1M
$3.11
Cache read / 1M
$0.0622
Cache write / 1M
$0.6218
1M contextUnderstands imagesEveryday chatCodingAgentsLong documentsImage understanding
View details29% below official
glm-5.3
Zhipu / Z.ai
Input / 1M
$0.6218
Output / 1M
$3.11
Cache read / 1M
$0.0622
Cache write / 1M
$0.6218
Image support unknownEveryday chatCodingAgentsLong documents
View details29% below official
gpt-5.6-sol
OpenAI
Input / 1M
$0.6218
Output / 1M
$2.80
Cache read / 1M
$0.0622
Cache write / 1M
$0.7773
258K contextUnderstands imagesCodingAgentsComplex reasoningImage understanding
View details84% below official
claude-sonnet-5
Anthropic
Input / 1M
$0.7773
Output / 1M
$3.89
Cache read / 1M
$0.0777
Cache write / 1M
$0.9716
1M contextUnderstands imagesCodingAgentsComplex reasoningLong documentsImage understanding
View details61% below official
claude-sonnet-5.5
Anthropic
Input / 1M
$0.7773
Output / 1M
$3.89
Cache read / 1M
$0.0777
Cache write / 1M
$0.9716
Image support unknownCodingAgentsComplex reasoningLong documentsImage understanding
View details61% below official
qwen3.7-max
Alibaba / Qwen
Input / 1M
$0.7773
Output / 1M
$2.33
Cache read / 1M
$0.0972
Cache write / 1M
$0.9716
1M contextText input onlyCodingComplex reasoningLong documents
View details68% below official
claude-opus-4-6
Anthropic
Input / 1M
$1.17
Output / 1M
$5.83
Cache read / 1M
$0.1166
Cache write / 1M
$1.46
1M contextUnderstands imagesCodingAgentsComplex reasoningLong documentsImage understanding
View details76% below official
claude-opus-4-7
Anthropic
Input / 1M
$1.17
Output / 1M
$5.83
Cache read / 1M
$0.1166
Cache write / 1M
$1.46
1M contextUnderstands imagesCodingAgentsComplex reasoningLong documentsImage understanding
View details76% below official
claude-opus-4-8
Anthropic
Input / 1M
$1.17
Output / 1M
$5.83
Cache read / 1M
$0.1166
Cache write / 1M
$1.46
1M contextUnderstands imagesCodingAgentsComplex reasoningLong documentsImage understanding
View details76% below official
claude-opus-5
Anthropic
Input / 1M
$1.17
Output / 1M
$5.83
Cache read / 1M
$0.1166
Cache write / 1M
$1.46
1M contextUnderstands imagesCodingAgentsComplex reasoningLong documentsImage understanding
View details76% below official
claude-opus-5.5
Anthropic
Input / 1M
$1.17
Output / 1M
$5.83
Cache read / 1M
$0.1166
Cache write / 1M
$1.46
Image support unknownCodingAgentsComplex reasoningLong documentsImage understanding
View details70% below official
gpt-6-astra
OpenAI
Input / 1M
$1.17
Output / 1M
$7.00
Cache read / 1M
$0.1166
Cache write / 1M
$1.75
Image support unknownCodingAgentsComplex reasoningImage understanding
View details86% below official
kimi-k3.1-pro
Moonshot / Kimi
Input / 1M
$1.17
Output / 1M
$5.83
Cache read / 1M
$0.0777
Cache write / 1M
$1.17
Image support unknownComplex reasoningLong documentsWriting
claude-opus-4-5-20251101
Anthropic
Input / 1M
$1.55
Output / 1M
$7.77
Cache read / 1M
$0.0155
Cache write / 1M
$1.94
Image support unknownCodingAgentsComplex reasoningLong documentsImage understanding
View details68% below official
qwen3.8-max
Alibaba / Qwen
Input / 1M
$1.55
Output / 1M
$4.66
Cache read / 1M
$0.1943
Cache write / 1M
$1.94
1M contextUnderstands imagesEveryday chatCodingComplex reasoningLong documentsImage understanding
View details22% below official
kimi-k3
Moonshot / Kimi
Input / 1M
$1.94
Output / 1M
$9.72
Cache read / 1M
$0.1943
Cache write / 1M
$1.94
1M contextUnderstands imagesComplex reasoningLong documentsWritingImage understanding
View details35% below official
nano-banana-2
Google / Gemini
Per image
$0.0117
Generates images
gpt-image-2-4k
OpenAI
Per image
$0.1943
4K outputGenerates imagesImage generation
gpt-image-2
OpenAI
Per image
$0.0058
1–2K outputGenerates imagesImage generation
gpt-image-2.5
OpenAI
Per image
$0.0058
Generates images
gpt-image-2.5-sunburst
OpenAI
Per image
$0.0194
Generates images
gpt-image-2.5-flare
OpenAI
Per image
$0.0194
Generates images
minimax-h3
MiniMax
480p / sec
$0.0097
768p / sec
$0.0136
1080p / sec
$0.0291
Generates video
nano-banana-pro
Google / Gemini
Per image
$0.0175
Generates images
nano-banana-2-lite
Google / Gemini
Per image
$0.0043
Generates images
nano-banana-fast
Google / Gemini
Per image
$0.0043
Generates images
nano-banana-2-cl
Google / Gemini
Per image
$0.0583
Generates images
nano-banana-pro-cl
Google / Gemini
Per image
$0.0972
Generates images
nano-banana-2-2k-cl
Google / Gemini
Per image
$0.0874
Generates images
nano-banana-pro-4k-vip
Google / Gemini
Per image
$0.1749
Generates images
nano-banana-pro-vip
Google / Gemini
Per image
$0.0972
Generates images
nano-banana-2-4k-cl
Google / Gemini
Per image
$0.1263
Generates images
nano-banana-2.1
Google / Gemini
Per image
$0.0117
Generates images
agnes-video-2.5
Other
2k / sec
$0.0447
720p / sec
$0.0194
1080p / sec
$0.0330
Generates video
wan-3.0
Other
480p / sec
$0.0321
720p / sec
$0.0641
1080p / sec
$0.1283
Generates video
gpt-image-2.6
OpenAI
Per image
$0.0058
Generates images
Last updated Nov 7, 2026, 12:17 AM UTC. The pricing page shows the same catalogue with model comparisons and copyable model IDs.
3. Caching, and how to actually benefit from it
When consecutive requests share a long identical prefix, the provider can reuse the work it already did on that prefix instead of reprocessing it. You are charged the discounted cache-read rate for that portion. Long conversations, follow-up questions on the same document, code completion, and agent loops all hit this case naturally.
The practical rule: keep the unchanging part of your prompt at the front, and put what varies at the end. Caching matches on a shared prefix, so a system prompt or document that sits before your question stays cacheable across turns. Move a timestamp or a request ID to the top and you invalidate the prefix on every single call — you then pay full input rate for the whole thing, plus a cache write.
Cache writes are not free, so a one-off call that will never be followed up gains nothing from caching. The benefit shows up from the second call onward, which is exactly the pattern agents and multi-turn chat produce.
4. Image and video models
Image generation is not billed per token. Each image is a fixed price regardless of prompt length, and the rate depends on the output resolution. Current per-image prices are on the pricing page.
Image calls go to POST /v1/images/generations, not the chat endpoint. In your usage records they show a cost with zero tokens — that is expected, since tokens play no part in what you were charged.
Video models are billed per second of video: the per-second rate for the resolution you pick, times the duration. The full amount is reserved when you submit and refunded automatically if the video fails. See the video generation guide.
5. Checking a call against your bill
The usage lookup page takes an API key and shows your balance, per-model totals, and recent calls. The four token types appear as separate columns, so you can multiply each one by its rate on the pricing page and land on the exact figure that was deducted.
The token counts come from the provider's usage block on the response — the same numbers your own client receives, so you can verify them against your logs without asking us.
Failed calls are listed too, with the reason in the Details column and a cost of zero. A call that errored is never billed. If the failure came from the upstream provider rather than your request, that column says so — you do not need to go debugging your own code first.
6. When prices change
Model prices track what the providers charge, and those move occasionally. Our price records sync automatically and the pricing page shows when they were last updated. Each call is billed at the rate in effect at that moment, and your usage records keep the resulting cost, so a later price change never restates what you already paid.
A few models are priced by time of day, meaning a call during the provider's peak window costs more than the same call off-peak. Where that applies, the pricing page notes it on the model. If your workload is flexible, shifting it out of the peak window is the simplest saving available.
Questions about a specific charge
Send us the call's timestamp and the model, plus the masked form of your API key — never a full working key. See the contact page for how to reach us.