Models
Rendered from the live model table: what is served and charged now.
| model | id | in | cached in | out | list in | list out | context | max output | status |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K3.1 Pro | kimi-k3.1-pro-crow |
$6.25 | $0.625 | $15.00 | — | — | 1M | 32.8K | live |
| GLM 5.3 | crow-2 |
$3.50 | $0.50 | $5.00 | — | — | 1M | 32.8K | live |
| GLM 5.3 [Cyber] | glm-5.3 |
$1.35 | $0.25 | $4.00 | — | — | 1M | 131K | live |
| GLM 5.3 Flash (default) | glm-5.3-flash-crow |
$0.20 | $0.10 | $0.60 | — | — | 1M | 32.8K | live |
| DeepSeek V4.1 Flash 1017 | deepseek-v4.1-flash-1017-crow |
$0.35 | $0.015 | $1.35 | — | — | 1M | 32.8K | live |
| GPT 6.1 Sol | gpt-6.1-sol |
$0.16 | $0.008 | $0.80 | $2.00 | $10.00 | 1M | 128K | live |
| Claude Opus 5.5 | claude-opus-5-5 |
$0.68 | $0.034 | $3.40 | $4.00 | $20.00 | 1M | 128K | off_sale |
| Kimi K3.1 Pro | kimi-k3.1-pro |
$0.21 | $0.021 | $1.05 | $2.00 | $10.00 | 1M | 1M | live |
| DeepSeek V4.1 Flash 1017 [CHEAP] | deepseek-v4.1-flash |
$0.03 | $0.0006 | $0.12 | $0.15 | $0.60 | 1M | 128K | live |
| GLM 5.3 [CHEAP] | glm-5.3-cheap |
$0.07 | $0.013 | $0.22 | $1.40 | $4.40 | 1M | 128K | live |
| Gemini 4 Argon | gemini-4-argon |
$0.30 | $0.015 | $1.50 | $2.00 | $10.00 | 1M | 65.5K | live |
| Gemini 4 Carbon | gemini-4-carbon |
$0.30 | $0.015 | $1.50 | $2.00 | $10.00 | 1M | 65.5K | live |
| Odin | odin |
$0.60 | $0.012 | $1.80 | — | — | 1M | 32.8K | live |
| Odin [CHEAP] | odin-cheap |
$0.05 | $0.005 | $0.25 | — | — | 1M | 128K | live |
| Qwen 3.6 | crow-1 |
$2.50 | $0.25 | $3.00 | — | — | 262K | 32.8K | deprecated |
| Claude Opus 5 | claude-opus-5 |
$0.15 | $0.015 | $0.75 | $5.00 | $25.00 | 1M | 128K | deprecated |
| GPT 5.6 Sol | gpt-5.6-sol |
$0.24 | $0.024 | $1.20 | $4.00 | $20.00 | 1M | 128K | deprecated |
USD per million tokens; input, cached input and output each bill at their own rate.
Cached input bills at the cached rate whenever the upstream reports a hit, at the ratio we get. Not every model reports hits, so budget for the full input rate, and keep the stable part of your prompt first: one changed token near the front invalidates everything after it.
Directions
One key reaches every direction below.
Frontier models, resold. The frontier models are sold at a fixed discount off the vendor's own published price, so your price moves only when theirs does. list in/list out show their price; a row without them is not resold. How the resellers are tested, and what we keep: why it's this cheap.
Uncensored models, our own. The CROW line runs abliterated weights with no policy layer at the model level, at fixed rates. Same endpoint, same key, same wallet.
There is no cached output rate, here or at any vendor. Caching stores the state of a prompt prefix; output tokens are generated fresh on every call, so there is nothing to reuse.
Statuses
| status | in the chat picker | callable via /v1 |
|---|---|---|
live |
selectable | yes |
off_sale |
shown, greyed out | no: a 503 until it is back on sale |
coming_soon |
shown, greyed out | no |
deprecated |
not shown | no |
hidden |
not shown | no |
A retired model keeps its row, so past usage stays attributable. Naming a non-live model over /v1 is a 404 model_not_found listing what is live; an id we do not recognise at all falls back to the default, since agentic clients routinely send other providers' names.
Choosing
- Kimi K3.1 Pro (
kimi-k3.1-pro-crow) — Kimi K3.1 Abliterated
$6.25 in / $15.00 out per 1M, 1M context — cached input $0.625, 10x cheaper. - GLM 5.3 (
crow-2) — GLM 5.3 Abliterated FP8
$3.50 in / $5.00 out per 1M, 1M context. - GLM 5.3 [Cyber] (
glm-5.3) — Experimental: may refuse but cheaper
$1.35 in / $4.00 out per 1M, 1M context — cached input $0.25, 5x cheaper. - GLM 5.3 Flash (
glm-5.3-flash-crow, the default) — GLM 5.3 Flash Abliterated
$0.20 in / $0.60 out per 1M, 1M context. - DeepSeek V4.1 Flash 1017 (
deepseek-v4.1-flash-1017-crow) — The abliterated variant.
$0.35 in / $1.35 out per 1M, 1M context — cached input $0.015, 23x cheaper. - GPT 6.1 Sol (
gpt-6.1-sol) — OpenAI's fast one, newest release.
$0.16 in / $0.80 out per 1M, 1M context (list price $2.00 in / $10.00 out). - Kimi K3.1 Pro (
kimi-k3.1-pro) — Moonshot's newest, a step past K3.
$0.21 in / $1.05 out per 1M, 1M context (list price $2.00 in / $10.00 out). - DeepSeek V4.1 Flash 1017 [CHEAP] (
deepseek-v4.1-flash) — DeepSeek's fast one. Cheap enough to leave running.
$0.03 in / $0.12 out per 1M, 1M context — cached input $0.0006, 50x cheaper (list price $0.15 in / $0.60 out). - GLM 5.3 [CHEAP] (
glm-5.3-cheap) — Zhipu's flagship. Cheap enough to leave running.
$0.07 in / $0.22 out per 1M, 1M context — cached input $0.013, 5x cheaper (list price $1.40 in / $4.40 out). - Gemini 4 Argon (
gemini-4-argon) — Google's heavyweight. Slower to start, built for the hard problems.
$0.30 in / $1.50 out per 1M, 1M context (list price $2.00 in / $10.00 out). - Gemini 4 Carbon (
gemini-4-carbon) — Google's newest Gemini 4.
$0.30 in / $1.50 out per 1M, 1M context (list price $2.00 in / $10.00 out). - Odin (
odin) — 500 tokens/s beast (experimental: may refuse)
$0.60 in / $1.80 out per 1M, 1M context — cached input $0.012, 50x cheaper. - Odin [CHEAP] (
odin-cheap) — Cheapest Cybersecurity Available
$0.05 in / $0.25 out per 1M, 1M context.
Every live model streams. Reasoning models return their thinking trace in reasoning_content; /v1/models says per model which of tool calling, reasoning, temperature and prompt caching it has, under capabilities.
Pick on price; the lineup above says which is the default, and omitting model gets it.
Limits
context is the prompt window; max output is the ceiling on one response, clamped rather than rejected. Both are editable without a deploy, so treat /v1/models as authoritative.