Model prices
The per-token retail price of every model Else can run, and which model each tier uses by default.
Every figure on this page is a retail price per million tokens — what you are charged, not an estimate. Prices are the same whether a model runs in a chat or in a handed-off task.
Tokens are how models measure text: roughly 4 characters, or about ¾ of a word. A short question and answer is a few hundred tokens; a long report with source material can be tens of thousands.
What each tier runs
Section titled “What each tier runs”You do not have to choose a model. The four options in the composer’s engine menu are Auto, Fast, Smart and Max — Auto picks for each request, and the other three each run one model by default:
| Tier | What it is for | Default model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|---|
| Fast | Cheapest acceptable answer | gemini-3.6-flash |
$1.80 | $9.00 |
| Smart | Balanced quality, long context | gpt-5.6-terra |
$2.40 up to 272K · $4.80 over 272K | $14.40 up to 272K · $21.60 over 272K |
| Max | Deepest reasoning | claude-opus-5 |
$6.00 | $30.00 |
You can point any tier at a different model in Settings → How it works → Set an engine per speed tier, and you can pick a model for a single request from Pick an exact engine in the composer’s engine menu. See Engines and tiers for how that interacts with what you are charged.
Every model you can pick
Section titled “Every model you can pick”All 81 models below are selectable today. Output tokens cost more than input tokens on nearly every model, which is why a long answer costs more than a long question.
A cell with more than one price is a model that charges more for a bigger prompt. Each price is followed by the prompt size it applies to — up to 128K, 200K and up — and the size is measured on the prompt you send, not on the answer. When a prompt lands in a higher band, every token in that request bills at the higher rate, input and output alike. The Long prompts section below lists the same bands as a table. A single price means one rate at any prompt size.
Images in is a measurement, not a guess: yes means image input was measured working, no means it was measured not working, and untested means we have not measured it and will not claim it either way.
Repeated context is the rate for input tokens the model has already been sent in this conversation. When a request re-sends context, those tokens bill at that lower rate instead of the full input rate. It is applied by the biller automatically — there is nothing to switch on, and a dash means this model has no separate rate for it.
What we know about it links to every page that covers that model — all of them, not just one — and each link says what kind of fact is on the other end. Reads images and images untested are our own probe results; PDFs (maker’s claim) is the maker’s published specification and nothing we measured. A dash means no page covers this model beyond the row you are reading.
| Model | Context | Images in | Input / 1M tokens | Output / 1M tokens | Repeated context / 1M | What we know about it |
|---|---|---|---|---|---|---|
glm-4.7-flash |
131K | no | $0.00 | $0.00 | — | — |
granite-4.0-h-micro |
131K | no | $0.02 | $0.13 | — | — |
llama-3.2-1b-instruct |
60K | no | $0.03 | $0.24 | — | — |
gpt-5-nano |
128K | untested | $0.06 | $0.48 | $0.01 | images untested |
llama-3.2-3b-instruct |
80K | no | $0.06 | $0.40 | — | — |
qwen3-30b-a3b-fp8 |
33K | no | $0.06 | $0.40 | — | — |
gemini-2.5-flash-lite |
1M | yes | $0.12 | $0.48 | $0.01 | reads images · takes a whole document · PDFs (maker’s claim) |
gpt-4.1-nano |
1M | untested | $0.12 | $0.48 | $0.03 | takes a whole document · images untested |
deepseek-v4-flash |
— | untested | $0.17 | $0.34 | $0.004 | images untested |
mimo-v2.5 |
— | untested | $0.17 | $0.34 | $0.004 | images untested |
gpt-4o-mini |
128K | yes | $0.18 | $0.72 | $0.09 | reads images |
llama-3.1-8b-instruct-fp8 |
32K | no | $0.18 | $0.34 | — | — |
gpt-5.4-nano |
128K | untested | $0.24 | $1.50 | $0.02 | images untested |
gpt-5.6-luna |
1.1M | untested | $0.24 up to 272K · $0.48 over 272K | $1.44 up to 272K · $2.16 over 272K | $0.02 up to 272K · $0.05 over 272K | takes a whole document · images untested |
gpt-oss-20b |
128K | no | $0.24 | $0.36 | — | — |
gemini-3.1-flash-lite |
1M | yes | $0.30 | $1.80 | $0.04 | reads images · takes a whole document |
gpt-5-mini |
128K | untested | $0.30 | $2.40 | $0.03 | images untested |
llama-4-scout-17b-16e-instruct |
131K | yes | $0.32 | $1.02 | — | reads images |
llama-3.3-70b-instruct-fp8-fast |
24K | no | $0.35 | $2.70 | — | — |
gemini-2.5-flash |
1M | untested | $0.36 | $3.00 | $0.09 | takes a whole document · PDFs (maker’s claim) · images untested |
gemini-3.5-flash-lite |
1M | untested | $0.36 | $3.00 | $0.04 | takes a whole document · PDFs (maker’s claim) · images untested |
m3 |
1M | no | $0.36 up to 512K · $0.72 over 512K | $1.44 up to 512K · $2.88 over 512K | $0.07 up to 512K · $0.14 over 512K | takes a whole document |
minimax-m2 |
— | untested | $0.36 | $1.44 | $0.04 | images untested |
minimax-m2.1 |
— | untested | $0.36 | $1.44 | $0.04 | images untested |
minimax-m2.5 |
— | untested | $0.36 | $1.44 | $0.04 | images untested |
minimax-m2.7 |
— | untested | $0.36 | $1.44 | $0.07 | images untested |
minimax-m3 |
— | untested | $0.36 up to 512K · $0.72 over 512K | $1.44 up to 512K · $2.88 over 512K | $0.07 up to 512K · $0.14 over 512K | images untested |
gpt-oss-120b |
128K | no | $0.42 | $0.90 | — | — |
mistral-small-3.1-24b-instruct |
128K | yes | $0.42 | $0.67 | — | reads images |
qwen3.7-plus |
— | untested | $0.48 up to 256K · $1.44 over 256K | $1.92 up to 256K · $5.76 over 256K | — | images untested |
gpt-4.1-mini |
1M | untested | $0.48 | $1.92 | $0.12 | takes a whole document · images untested |
deepseek-v4-pro |
131K | untested | $0.52 | $1.04 | $0.01 | images untested |
mimo-v2.5-pro |
— | untested | $0.52 | $1.04 | $0.01 | images untested |
gemini-3-flash |
1M | no | $0.60 | $3.60 | $0.06 | takes a whole document |
nemotron-3-120b-a12b |
256K | no | $0.60 | $1.80 | — | — |
qwen3.5-397b-a17b |
— | yes | $0.72 | $4.32 | — | reads images |
minimax-m2.7-highspeed |
— | untested | $0.72 | $2.88 | $0.07 | images untested |
glm-4.6 |
— | untested | $0.72 | $2.64 | $0.13 | images untested |
glm-4.7 |
— | untested | $0.72 | $2.64 | $0.13 | images untested |
qwq-32b |
24K | no | $0.79 | $1.20 | — | — |
gpt-5.4-mini |
128K | yes | $0.90 | $5.40 | $0.09 | reads images |
kimi-k2.6 |
— | untested | $1.14 | $4.80 | $0.19 | images untested |
kimi-k2.7-code |
— | untested | $1.14 | $4.80 | $0.23 | images untested |
kimi-k2.6 |
262K | no | $1.14 | $4.80 | $0.19 | — |
kimi-k2.7-code |
262K | no | $1.14 | $4.80 | $0.23 | — |
qwen3-coder-plus |
— | untested | $1.20 up to 32K · $2.16 up to 128K · $3.60 up to 256K · $7.20 over 256K | $6.00 up to 32K · $10.80 up to 128K · $18.00 up to 256K · $72.00 over 256K | — | images untested |
claude-haiku-4.5 |
200K | yes | $1.20 | $6.00 | $0.12 | reads images · PDFs (maker’s claim) |
glm-5 |
— | untested | $1.20 | $3.84 | $0.24 | images untested |
o4-mini |
200K | untested | $1.32 | $5.28 | $0.33 | images untested |
qwen3-max |
— | untested | $1.44 up to 32K · $2.88 up to 128K · $3.60 over 128K | $7.20 up to 32K · $14.40 up to 128K · $18.00 over 128K | — | images untested |
glm-5-turbo |
— | untested | $1.44 | $4.80 | $0.29 | images untested |
gemini-2.5-pro |
1M | yes | $1.50 up to 200K · $3.00 over 200K | $12.00 up to 200K · $18.00 over 200K | $0.15 up to 200K · $0.30 over 200K | reads images · takes a whole document · PDFs (maker’s claim) |
gpt-5 |
128K | untested | $1.50 | $12.00 | $0.15 | images untested |
gpt-5.1 |
128K | yes | $1.50 | $12.00 | $0.15 | reads images |
grok-4.3 |
1M | yes | $1.50 under 200K · $3.00 200K and up | $3.00 under 200K · $6.00 200K and up | $0.24 under 200K · $0.48 200K and up | reads images · takes a whole document |
glm-5.2 |
262K | no | $1.68 | $5.28 | $0.31 | — |
glm-5.1 |
— | untested | $1.68 | $5.28 | $0.31 | images untested |
glm-5.2 |
— | untested | $1.68 | $5.28 | $0.31 | images untested |
gemini-3.5-flash |
1M | yes | $1.80 | $10.80 | $0.18 | reads images · takes a whole document |
gemini-3.6-flash |
1M | untested | $1.80 | $9.00 | $0.18 | takes a whole document · PDFs (maker’s claim) · images untested |
gpt-5.2 |
— | yes | $2.10 | $16.80 | $0.21 | reads images |
kimi-k2.7-code-highspeed |
— | untested | $2.28 | $9.60 | $0.46 | images untested |
qwen3.8-max |
— | yes | $2.40 | $7.20 | — | reads images |
claude-sonnet-5 |
1M | untested | $2.40 | $12.00 | $0.24 | takes a whole document · images untested |
gpt-4.1 |
1M | yes | $2.40 | $9.60 | $0.60 | reads images · takes a whole document |
gpt-5.6-terra |
1.1M | untested | $2.40 up to 272K · $4.80 over 272K | $14.40 up to 272K · $21.60 over 272K | $0.24 up to 272K · $0.48 over 272K | takes a whole document · images untested |
grok-4.5 |
500K | untested | $2.40 under 200K · $4.80 200K and up | $7.20 under 200K · $14.40 200K and up | $0.36 under 200K · $0.72 200K and up | images untested |
qwen3.7-max |
— | untested | $3.00 | $9.00 | — | images untested |
gpt-4o |
128K | yes | $3.00 | $12.00 | $1.50 | reads images |
gpt-5.4 |
1M | yes | $3.00 up to 272K · $6.00 over 272K | $18.00 up to 272K · $27.00 over 272K | $0.30 up to 272K · $0.60 over 272K | reads images · takes a whole document |
claude-sonnet-4.5 |
200K | yes | $3.60 | $18.00 | $0.36 | reads images · PDFs (maker’s claim) |
claude-sonnet-4.6 |
200K | untested | $3.60 | $18.00 | $0.36 | PDFs (maker’s claim) · images untested |
kimi-k3 |
1M | untested | $3.60 | $18.00 | $0.36 | takes a whole document · images untested |
claude-opus-4.5 |
200K | untested | $6.00 | $30.00 | $0.60 | PDFs (maker’s claim) · images untested |
claude-opus-4.6 |
1M | untested | $6.00 | $30.00 | $0.60 | takes a whole document · PDFs (maker’s claim) · images untested |
claude-opus-4.7 |
1M | untested | $6.00 | $30.00 | $0.60 | takes a whole document · PDFs (maker’s claim) · images untested |
claude-opus-4.8 |
1M | untested | $6.00 | $30.00 | $0.60 | takes a whole document · images untested |
claude-opus-5 |
1M | yes | $6.00 | $30.00 | $0.60 | reads images · takes a whole document |
gpt-5.5 |
1M | yes | $6.00 up to 272K · $12.00 over 272K | $36.00 up to 272K · $54.00 over 272K | $0.60 up to 272K · $1.20 over 272K | reads images · takes a whole document |
gpt-5.6-sol |
1.1M | untested | $6.00 up to 272K · $12.00 over 272K | $36.00 up to 272K · $54.00 over 272K | $0.60 up to 272K · $1.20 over 272K | takes a whole document · images untested |
claude-fable-5 |
1M | untested | $12.00 | $60.00 | $1.20 | takes a whole document · images untested |
A model appears here only while it has real capacity behind it, so this list changes. If a model you picked stops being available, the tier it was bound to falls back to its default and tells you it did.
Long prompts cost more on 13 models
Section titled “Long prompts cost more on 13 models”Most models charge one rate however long your prompt is. 13 models on this list do not: once the prompt passes a size, every input and output token in that request bills at the higher rate — not just the tokens past the line. Some of them step more than once.
The bands below are the same ones shown inline in the table above, spelled out. “Prompt up to 200K” means a prompt of exactly 200,000 tokens still pays that rate; “prompt 200K and up” starts at exactly 200,000.
| Model | Runs as | Prompt size | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|---|
qwen3-coder-plus |
Exact engine pick | prompt up to 32K | $1.20 | $6.00 |
qwen3-coder-plus |
Exact engine pick | prompt up to 128K | $2.16 | $10.80 |
qwen3-coder-plus |
Exact engine pick | prompt up to 256K | $3.60 | $18.00 |
qwen3-coder-plus |
Exact engine pick | prompt over 256K | $7.20 | $72.00 |
qwen3-max |
Exact engine pick | prompt up to 32K | $1.44 | $7.20 |
qwen3-max |
Exact engine pick | prompt up to 128K | $2.88 | $14.40 |
qwen3-max |
Exact engine pick | prompt over 128K | $3.60 | $18.00 |
qwen3.7-plus |
Exact engine pick | prompt up to 256K | $0.48 | $1.92 |
qwen3.7-plus |
Exact engine pick | prompt over 256K | $1.44 | $5.76 |
gemini-2.5-pro |
Exact engine pick | prompt up to 200K | $1.50 | $12.00 |
gemini-2.5-pro |
Exact engine pick | prompt over 200K | $3.00 | $18.00 |
m3 |
Exact engine pick | prompt up to 512K | $0.36 | $1.44 |
m3 |
Exact engine pick | prompt over 512K | $0.72 | $2.88 |
minimax-m3 |
Exact engine pick | prompt up to 512K | $0.36 | $1.44 |
minimax-m3 |
Exact engine pick | prompt over 512K | $0.72 | $2.88 |
gpt-5.4 |
Exact engine pick | prompt up to 272K | $3.00 | $18.00 |
gpt-5.4 |
Exact engine pick | prompt over 272K | $6.00 | $27.00 |
gpt-5.5 |
Exact engine pick | prompt up to 272K | $6.00 | $36.00 |
gpt-5.5 |
Exact engine pick | prompt over 272K | $12.00 | $54.00 |
gpt-5.6-luna |
Exact engine pick | prompt up to 272K | $0.24 | $1.44 |
gpt-5.6-luna |
Exact engine pick | prompt over 272K | $0.48 | $2.16 |
gpt-5.6-sol |
Exact engine pick | prompt up to 272K | $6.00 | $36.00 |
gpt-5.6-sol |
Exact engine pick | prompt over 272K | $12.00 | $54.00 |
gpt-5.6-terra |
Exact engine pick | prompt up to 272K | $2.40 | $14.40 |
gpt-5.6-terra |
Exact engine pick | prompt over 272K | $4.80 | $21.60 |
grok-4.3 |
Exact engine pick | prompt under 200K | $1.50 | $3.00 |
grok-4.3 |
Exact engine pick | prompt 200K and up | $3.00 | $6.00 |
grok-4.5 |
Exact engine pick | prompt under 200K | $2.40 | $7.20 |
grok-4.5 |
Exact engine pick | prompt 200K and up | $4.80 | $14.40 |
Which band you land in is decided by the size of the prompt you send, and the receipt shows what you were actually charged.
Image generation
Section titled “Image generation”Generated images are priced per image, by size, not by tokens:
| Model | Size | Price per image |
|---|---|---|
gemini-2.5-flash-image |
default | $0.0585 |
gemini-3-pro-image |
1K | $0.201 |
gemini-3-pro-image |
2K | $0.201 |
gemini-3-pro-image |
4K | $0.36 |
gemini-3.1-flash-image |
0.5K | $0.0675 |
gemini-3.1-flash-image |
1K | $0.1005 |
gemini-3.1-flash-image |
2K | $0.1515 |
gemini-3.1-flash-image |
4K | $0.2265 |
gemini-3.1-flash-lite-image |
1K | $0.0504 |
gpt-image-1.5 |
1024x1024 | $0.051 |
gpt-image-1.5 |
1024x1536 | $0.075 |
gpt-image-1.5 |
1536x1024 | $0.075 |
gpt-image-1 |
1024x1024 | $0.063 |
gpt-image-1 |
1024x1536 | $0.0945 |
gpt-image-1 |
1536x1024 | $0.0945 |
gpt-image-2 |
1024x1024 | $0.0795 |
gpt-image-2 |
1024x1536 | $0.0615 |
gpt-image-2 |
1536x1024 | $0.0615 |
Everything else on your bill
Section titled “Everything else on your bill”Three other things can appear on a receipt. Each is metered per unit of real use, and the amount charged is always itemized on the receipt itself:
| Item | Metered by | Price |
|---|---|---|
| Reading a web page | per page rendered | $0.002 per page |
| Running code in the secure workspace | per minute of run time | $0.0048 per minute |
| Transcribing audio you send | per minute of audio | itemized on the receipt |
Two notes on those, because a price is only useful if you know what it is measuring.
Reading a web page is a flat rate per page, not per second spent on it. A page that takes a long time to load costs the same as one that loads instantly.
Run time is measured while your code is actually executing, not for the whole time a run is open. A run that spends most of its time waiting on a model is not accruing workspace time.
Audio transcription is the one item without a rate on this page. It is charged at the metered rate we are charged for it, with nothing added — so the figure is not ours to publish, and quoting it here would be publishing someone else’s rate card. The amount is always itemized on your receipt, and the unit is per minute of audio.
See How billing works for what triggers each of these, and Reading a receipt for where they appear.
Where these numbers come from
Section titled “Where these numbers come from”Every price on this page is generated directly from the same pricing code that bills your runs — it is not transcribed by hand, and it cannot disagree with what you are charged.
Prices last changed 2026-08-05 (source f7e2787). If that date
looks old, that is because nothing has moved, not because the page was forgotten.