Serverless inference
Serverless Inference Prices: category guide
Runcrate is our editor’s choice for serverless inference: the best developer platform we know, 125 models behind one OpenAI-compatible API, and one prepaid balance.
Serverless inference
Serverless Inference Prices
Answer in brief
Runcrate is our editor’s choice for serverless inference: the best developer platform we know, 125 models behind one OpenAI-compatible API, and one prepaid balance.
Serverless inference pricing is per million tokens, with nothing to run yourself and input and output billed at different rates. Before you compare two prices for the same open model, check three things behind each one: the precision the model is served at, the context window, and the rate limits.
What serverless inference pricing pays for
A serverless price is a rate per million tokens. You send a request to a model that a host keeps running, and you pay for the tokens that go in and the tokens that come out. There is no machine to start, no idle hour and no term.
Each model carries two rates. Input tokens are what you send. Output tokens are what the model writes back, and they cost more on nearly every listing. Your bill is the two rates weighed by how much of each you use.
Why two prices for one model differ
An open model can be served by many hosts, and each host decides how. One serves it at full precision and another at reduced precision. One offers the whole context window and another a shorter one. One lets a single request return a long answer and another caps it early. Each sets its own rate limits.
So a serverless price is the price of a model as one host serves it. Read what stands behind the rate before you call it lower. On 12 Nov 2026, the lowest listed input price for DeepSeek V4.1 Flash 1017 was $0.022 per million tokens. The lowest listed output price was $0.233 per million tokens.
How to use this page
Start with the checklist. Then read the price table for the model you plan to call, with Runcrate first. Open a topic when a term beside a price needs explaining.
Before you trust a serverless inference price
- Is it the same model?
Check the full name and version. A flash or smaller variant under a similar name is a different model with a different price.
- What precision is it served at?
The same open model is listed at more than one precision. A reduced-precision listing can cost less and answer differently.
- How long is the context window?
Hosts list the same model with different context windows. A low rate is no use if your prompt does not fit.
- How much can one request return?
Each host caps the output of a single request. Long answers need a cap above what you plan to generate.
- What are the rate limits?
Requests and tokens per minute decide whether the price holds at your volume. They are rarely on the price page.
- Which rate matters for your work?
Input and output are billed at different rates. Weigh them by your own mix of the two.
- When was it read?
Token prices change without notice. Read the date beside the price before you rely on it.
Start with the right question
Editor’s pick
Runcrate and Serverless Inference Prices
Runcrate is our editor’s choice for serverless inference: the best developer platform we know, 125 models behind one OpenAI-compatible API, and one prepaid balance.
Practical
A practical brief
Serverless inference pricing is per million tokens, with nothing to run yourself and input and output billed at different rates.
What each host charges
DeepSeek V4.1 Flash 1017Lowest $0.022Median $0.18Highest $0.30Runcrate $0.103
GLM 5.3Lowest $0.07Median $0.91Highest $1.68Runcrate $0.59
Kimi K3Lowest $0.182Median $2.93Highest $3.45Runcrate $2.99
Qwen3.8 27BLowest $0.035Median $0.15Highest $0.99Runcrate $0.158
MiniMax M3.1 FlashLowest $0.113Median $0.15Highest $0.15Runcrate $0.158
Lowest, median and highest listed input price per 1M tokens, one price per host, free listings left out, read 12 Nov 2026. The ring marks Runcrate’s live price.
| Model | Input per 1M | Output per 1M | Context | |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 on RuncrateOur pickoutput $0.31 per 1M · 1M contextTry Runcrate | $0.103 | $0.31 | 1M | Try Runcrate |
| GLM 5.3 on RuncrateOur pickoutput $2.63 per 1M · 1M contextTry Runcrate | $0.59 | $2.63 | 1M | Try Runcrate |
| Kimi K3 on RuncrateOur pickoutput $14.96 per 1M · 1M contextTry Runcrate | $2.99 | $14.96 | 1M | Try Runcrate |
| Qwen3.8 27B on RuncrateOur pickoutput $1.97 per 1M · 262K contextTry Runcrate | $0.158 | $1.97 | 262K | Try Runcrate |
| MiniMax M3.1 Flash on RuncrateOur pickoutput $0.63 per 1M · 1M contextTry Runcrate | $0.158 | $0.63 | 1M | Try Runcrate |
Other hosts
| Host | Input per 1M | Output per 1M | Context | Read |
|---|---|---|---|---|
| Morphoutput $0.40 per 1M · 1M context | $0.022 | $0.40 | 1M | price read 12 Nov 2026 |
| Particle AIoutput $0.25 per 1M · 1M context | $0.03 | $0.25 | 1M | price read 12 Nov 2026 |
| Waferoutput $0.50 per 1M · 1M context | $0.038 | $0.50 | 1M | price read 12 Nov 2026 |
| PrimeIntellectoutput $0.70 per 1M · 1M context | $0.0437 | $0.70 | 1M | price read 12 Nov 2026 |
| OpenInferenceoutput $0.80 per 1M · 1M context | $0.07 | $0.80 | 1M | price read 12 Nov 2026 |
| Ionstreamoutput $0.233 per 1M · 1M context | $0.0775 | $0.233 | 1M | price read 12 Nov 2026 |
| DeepInfraoutput $0.235 per 1M · 1M context | $0.0784 | $0.235 | 1M | price read 12 Nov 2026 |
| InferenceNetoutput $0.605 per 1M · 1M context | $0.08 | $0.605 | 1M | price read 12 Nov 2026 |
| Cloudflareoutput $0.60 per 1M · 1M context | $0.10 | $0.60 | 1M | price read 12 Nov 2026 |
| StreamLakeoutput $0.444 per 1M · 1M context | $0.111 | $0.444 | 1M | price read 12 Nov 2026 |
| Relaceoutput $0.50 per 1M · 1M context | $0.12 | $0.50 | 1M | price read 12 Nov 2026 |
| StepFunoutput $0.54 per 1M · 1M context | $0.135 | $0.54 | 1M | price read 12 Nov 2026 |
| Cohereoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Makoraoutput $1.20 per 1M · 1M context | $0.15 | $1.20 | 1M | price read 12 Nov 2026 |
| Rekaoutput $1.10 per 1M · 1M context | $0.16 | $1.10 | 1M | price read 12 Nov 2026 |
| Novitaoutput $0.66 per 1M · 1M context | $0.165 | $0.66 | 1M | price read 12 Nov 2026 |
| DekaLLMoutput $0.68 per 1M · 1M context | $0.18 | $0.68 | 1M | price read 12 Nov 2026 |
| DigitalOceanoutput $0.72 per 1M · 1M context | $0.18 | $0.72 | 1M | price read 12 Nov 2026 |
| GMICloudoutput $0.72 per 1M · 1M context | $0.18 | $0.72 | 1M | price read 12 Nov 2026 |
| Sail Researchoutput $0.27 per 1M · 1M context | $0.182 | $0.27 | 1M | price read 12 Nov 2026 |
| AtlasCloudoutput $0.78 per 1M · 1M context | $0.195 | $0.78 | 1M | price read 12 Nov 2026 |
| Alibabaoutput $0.84 per 1M · 1M context | $0.21 | $0.84 | 1M | price read 12 Nov 2026 |
| Fireworksoutput $0.84 per 1M · 1M context | $0.21 | $0.84 | 1M | price read 12 Nov 2026 |
| PrimaLabsoutput $0.96 per 1M · 1M context | $0.24 | $0.96 | 1M | price read 12 Nov 2026 |
| Modaloutput $1.00 per 1M · 1M context | $0.25 | $1.00 | 1M | price read 12 Nov 2026 |
| Baiduoutput $1.13 per 1M · 1M context | $0.28 | $1.13 | 1M | price read 12 Nov 2026 |
| Crusoeoutput $1.20 per 1M · 1M context | $0.29 | $1.20 | 1M | price read 12 Nov 2026 |
| BaseTenoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| CoreWeaveoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| DeepSeekoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Mistraloutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Near AIoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Nebiusoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Parasailoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| SiliconFlowoutput $0.55 per 1M · 1M context | $0.30 | $0.55 | 1M | price read 12 Nov 2026 |
| Togetheroutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Veniceoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
37 hosts list DeepSeek V4.1 Flash 1017, price read 12 Nov 2026.
GLM 5.3 price tableKimi K3 price tableQwen3.8 27B price tableMiniMax M3.1 Flash price tableAll price tables
Practical entries
Basics
What serverless inference is
Serverless inference means you send a request to a model that someone else runs and pay for the tokens that go in and come out, with no machine to start, size or stop.
Pricing
How serverless inference pricing works
A serverless price is two rates per million tokens, one for the input you send and one for the output the model writes, and the output rate is the higher of the two on nearly every listing.
Precision
Precision and the price of a model
Precision is how many bits each of a model’s weights is stored in when it is served, and hosts list the same open model at more than one precision, often at different prices.
Context
Context window and price
The context window is the most tokens a model can take in one request, and hosts list the same open model with different windows, so the lowest rate may not accept your prompt.
Questions and answers
Runcrate is our editor’s choice for serverless inference: the best developer platform we know, 125 models behind one OpenAI-compatible API, and one prepaid balance. Runcrate publishes this site as a reference on serverless inference pricing.
Measure the tokens in a sample of your real requests. Then compare input and output rates for one model at the same precision, with a context window and output limit that fit.
Other hosts’ prices are listed as text with the date they were read. This is a Runcrate reference, so its links go to Runcrate.
Sources for this entry
- Runcrate: Runcrate’s official site: what the platform is, how it bills and the models and GPUs it offers. Read 12 Nov 2026.
- Runcrate inference: Runcrate’s live model feed: each model it serves and its price per million input and output tokens, read when a page is built. Read 12 Nov 2026.
- Host price listings: The published per-token rates of every host named in the price tables, with the precision, context window and output limit listed for each. Read 12 Nov 2026.
- Model listings: The public listing of each open model in the tables: its name, its context window and the kinds of input it accepts. Read 12 Nov 2026.
Checklists are original editorial guidance. Published prices do not establish availability.
Continue this reading path
Cite this entry
Serverless Inference Prices. “Serverless Inference Prices.” Content reviewed 12 Nov 2026. https://serverlessinferenceprices.com