Real-time pricing data

Supported Models & Pricing

Transparent pricing based on official rates and service multipliers — updated automatically

Millions of monthly requests
Pricing auto-synced every 10min
Claude · GPT · GLM · Kimi · DeepSeek · Qwen

Service Rate

QCode Price = Official Price × Service Rate. Rates are set per provider by the platform. For GPT models, when a single request has more than 272K input tokens (cached tokens included), the whole request is billed at the long-context rate.

Anthropic Claude

×1.0

OpenAI / Codex

×1.0

Google Gemini Temporarily unavailable

×2.0

Latest models on QCode

Newly added flagships — available to every plan from day one, at the same service rate.

Show cache pricing

All plans can call every model on this page (except those marked “Temporarily unavailable”)

The “Traffic share” column shows how QCode's overall request volume was distributed across models over the last 30 days. It is not a whitelist, a quota, or a routing restriction — model access is identical on every plan, and a 0% model works exactly the same as a 34% one (except those marked “Temporarily unavailable”).

GPT-6 Luna (gpt-6-luna / gpt-5.6-luna) is currently not supported. Please use another GPT model.

Official vendor status (not QCode service status)

Claude Operational GPT Operational

These lights mirror what Anthropic and OpenAI publish on their own official status pages, for reference only. They are only loosely correlated with QCode's own availability and should not be used to judge whether QCode is up.

Anthropic Claude Series

15 active models (30d)

Model	Input $/M	Output $/M	Cache W $/M	Cache R $/M	Context Window	Features	Traffic share (30d) ⓘ
claude-haiku-5-5 NEW Claude Haiku 5.5	$0.10 >100K $0.50	$0.50 >100K $2.50	$0.12	$0.01 >100K $0.05	1M / 128K	Vision Tools Cache	3.7%
Popular claude-opus-5-5 NEW Claude Opus 5.5	$4.00	$20.00	$5.00	$0.20	1M / 128K	Vision Tools Cache	19.0%
claude-opus-5 Claude Opus 5	$5.00	$25.00	$6.25	$0.50	1M / 128K	Vision Tools Cache	1.5%
claude-fable-5 Claude Fable 5	$10.00	$50.00	$12.50	$1.00	1M / 128K	Vision Tools Cache	0.5%
Popular claude-sonnet-5 Claude Sonnet 5	$2.00	$10.00	$2.50	$0.20	1M / 128K	Vision Tools Cache	12.2%
Popular claude-sonnet-5-5 Claude Sonnet 5.5	$2.00	$10.00	$2.50	$0.10	1M / 128K	Vision Tools Cache	15.1%
claude-fable-5-1 Claude Fable 5.1	$10.00	$50.00	$12.50	$0.25	1M / 128K	Vision Tools Cache	1.3%
claude-sonnet-4-6 Claude Sonnet 4.6	$3.00	$15.00	$3.75	$0.30	1M / 128K	Vision Tools Cache	1.2%
claude-opus-4-8 Claude Opus 4.8	$5.00	$25.00	$6.25	$0.50	1M / 128K	Vision Tools Cache	0.5%
claude-opus-4-6 Claude Opus 4.6	$5.00	$25.00	$6.25	$0.50	1M / 128K	Vision Tools Cache	0.2%
claude-opus-4-7 Claude Opus 4.7	$5.00	$25.00	$6.25	$0.50	1M / 128K	Vision Tools Cache	0.1%
claude-opus-4-5-20251101 Retiring Claude Opus 4.5	$5.00	$25.00	$6.25	$0.50	200K / 64K	Vision Tools Cache	<0.1%
claude-opus-5[1m] Claude Opus 5[1m]	$5.00	$25.00	$6.25	$0.50	1M / 128K	Vision Tools Cache	<0.1%
claude-sonnet-5-5[1m] Claude Sonnet 5.5[1m]	$2.00	$10.00	$2.50	$0.10	1M / 128K	Vision Tools Cache	<0.1%
claude-sonnet-5[1m] Claude Sonnet 5[1m]	$2.00	$10.00	$2.50	$0.20	1M / 128K	Vision Tools Cache	<0.1%

claude-haiku-5-5 NEW

3.7% of platform traffic (30d)

Input $/M

$0.10/M

>100K $0.50

Output $/M

$0.50/M

>100K $2.50

1M / 128K Vision Tools Cache

Popular

claude-opus-5-5 NEW

19.0% of platform traffic (30d)

Input $/M

$4.00/M

Output $/M

$20.00/M

1M / 128K Vision Tools Cache

claude-opus-5

1.5% of platform traffic (30d)

Input $/M

$5.00/M

Output $/M

$25.00/M

1M / 128K Vision Tools Cache

claude-fable-5

0.5% of platform traffic (30d)

Input $/M

$10.00/M

Output $/M

$50.00/M

1M / 128K Vision Tools Cache

Popular

claude-sonnet-5

12.2% of platform traffic (30d)

Input $/M

$2.00/M

Output $/M

$10.00/M

1M / 128K Vision Tools Cache

Popular

claude-sonnet-5-5

15.1% of platform traffic (30d)

Input $/M

$2.00/M

Output $/M

$10.00/M

1M / 128K Vision Tools Cache

claude-fable-5-1

1.3% of platform traffic (30d)

Input $/M

$10.00/M

Output $/M

$50.00/M

1M / 128K Vision Tools Cache

claude-sonnet-4-6

1.2% of platform traffic (30d)

Input $/M

$3.00/M

Output $/M

$15.00/M

1M / 128K Vision Tools Cache

claude-opus-4-8

0.5% of platform traffic (30d)

Input $/M

$5.00/M

Output $/M

$25.00/M

1M / 128K Vision Tools Cache

claude-opus-4-6

0.2% of platform traffic (30d)

Input $/M

$5.00/M

Output $/M

$25.00/M

1M / 128K Vision Tools Cache

claude-opus-4-7

0.1% of platform traffic (30d)

Input $/M

$5.00/M

Output $/M

$25.00/M

1M / 128K Vision Tools Cache

claude-opus-4-5-20251101 Retiring

<0.1% of platform traffic (30d)

Input $/M

$5.00/M

Output $/M

$25.00/M

200K / 64K Vision Tools Cache

claude-opus-5[1m]

<0.1% of platform traffic (30d)

Input $/M

$5.00/M

Output $/M

$25.00/M

1M / 128K Vision Tools Cache

claude-sonnet-5-5[1m]

<0.1% of platform traffic (30d)

Input $/M

$2.00/M

Output $/M

$10.00/M

1M / 128K Vision Tools Cache

claude-sonnet-5[1m]

<0.1% of platform traffic (30d)

Input $/M

$2.00/M

Output $/M

$10.00/M

1M / 128K Vision Tools Cache

Haiku models (claude-haiku-*) have usage protection: if one API key uses a lot of Haiku within 60 minutes or 24 hours, Haiku is temporarily rate-limited for that key and recovers automatically; limits vary by plan. Only Haiku is affected — Sonnet and Opus are not. For long sessions or batch workloads we recommend Sonnet.

OpenAI / Codex Series

5 active models (30d)

Model	Input $/M	Output $/M	Cache W $/M	Cache R $/M	Context Window	Features	Traffic share (30d) ⓘ
Popular gpt-6.1-sol NEW GPT 6.1 sol	$2.00 >272K $4.00	$10.00 >272K $15.00	$2.50	$0.10 >272K $0.20	922K / 128K	Vision Tools Cache	6.8%
Popular gpt-6-sol NEW GPT 6 sol	$2.00 >272K $4.00	$10.00 >272K $15.00	$2.50	$0.20 >272K $0.40	922K / 128K	Vision Tools Cache	5.5%
gpt-5.6-sol GPT 5.6 sol	$5.00 >272K $10.00	$30.00 >272K $45.00	$6.25	$0.50 >272K $1.00	922K / 128K	Vision Tools Cache	3.2%
gpt-5.6-terra GPT 5.6 terra	$2.00 >272K $4.00	$12.00 >272K $18.00	$2.50	$0.20 >272K $0.40	922K / 128K	Vision Tools Cache	2.0%
gpt-6-astra GPT 6 astra	$10.00 >272K $20.00	$50.00 >272K $75.00	$12.50	$1.00 >272K $2.00	922K / 128K	Vision Tools Cache	2.3%
gpt-image-2 GPT Image 2	—	QCode per-image price $0.30 / image	—	—	—	Image	—

Popular

gpt-6.1-sol NEW

6.8% of platform traffic (30d)

Input $/M

$2.00/M

>272K $4.00

Output $/M

$10.00/M

>272K $15.00

922K / 128K Vision Tools Cache

Popular

gpt-6-sol NEW

5.5% of platform traffic (30d)

Input $/M

$2.00/M

>272K $4.00

Output $/M

$10.00/M

>272K $15.00

922K / 128K Vision Tools Cache

gpt-5.6-sol

3.2% of platform traffic (30d)

Input $/M

$5.00/M

>272K $10.00

Output $/M

$30.00/M

>272K $45.00

922K / 128K Vision Tools Cache

gpt-5.6-terra

2.0% of platform traffic (30d)

Input $/M

$2.00/M

>272K $4.00

Output $/M

$12.00/M

>272K $18.00

922K / 128K Vision Tools Cache

gpt-6-astra

2.3% of platform traffic (30d)

Input $/M

$10.00/M

>272K $20.00

Output $/M

$50.00/M

>272K $75.00

922K / 128K Vision Tools Cache

gpt-image-2

Input $/M

—

QCode per-image price

$0.30

/ image

— Image

Billed per output image at $0.30, the same for generations and edits; gpt-image-2.5 / -flare / -sunburst are compatibility names with identical billing, not separate rows

Google Gemini Series Temporarily unavailable

0 active models (30d) Service Rate: ×2.0

Model	Input $/M	Output $/M	Cache W $/M	Cache R $/M	Context Window	Features	Traffic share (30d) ⓘ
gemini-3.5-flash Temporarily unavailable Gemini 3.5 Flash	$3.00 $1.50	$18.00 $9.00	—	$0.15	1M / 65K	Vision Tools Cache	—

gemini-3.5-flash Temporarily unavailable

Input $/M

$3.00/M

$1.50

Output $/M

$18.00/M

$9.00

1M / 65K Vision Tools Cache

Zhipu GLM Series

3 active models (30d)

Model	Input $/M	Output $/M	Cache W $/M	Cache R $/M	Context Window	Features	Traffic share (30d) ⓘ
glm-5.2 glm 5.2	$2.38	$8.32	$2.97	$0.59	200K / 131K	Vision Tools Cache	0.1%
glm-5.3-flash glm 5.3 Flash	$0.14	$0.49	$0.17	$0.04	1M / 128K	Vision Tools Cache	4.9%
glm-5.3 glm 5.3	$2.38	$8.32	$2.97	$0.59	1M / 128K	Vision Tools Cache	1.3%

glm-5.2

0.1% of platform traffic (30d)

Input $/M

$2.38/M

Output $/M

$8.32/M

200K / 131K Vision Tools Cache

glm-5.3-flash

4.9% of platform traffic (30d)

Input $/M

$0.14/M

Output $/M

$0.49/M

1M / 128K Vision Tools Cache

glm-5.3

1.3% of platform traffic (30d)

Input $/M

$2.38/M

Output $/M

$8.32/M

1M / 128K Vision Tools Cache

Moonshot Kimi Series

1 active models (30d)

Model	Input $/M	Output $/M	Cache W $/M	Cache R $/M	Context Window	Features	Traffic share (30d) ⓘ
kimi-k3 kimi k3	$21.00	$105.00	$26.25	$2.10	1M / 131K	Vision Tools Cache	<0.1%

kimi-k3

<0.1% of platform traffic (30d)

Input $/M

$21.00/M

Output $/M

$105.00/M

1M / 131K Vision Tools Cache

DeepSeek Series

3 active models (30d)

Model	Input $/M	Output $/M	Cache W $/M	Cache R $/M	Context Window	Traffic share (30d) ⓘ
deepseek-v4-pro deepseek v4 Pro	$0.66	$1.98	$0.82	$0.06	1M / 384K	0.5%
Popular deepseek-v4.1-flash deepseek v4.1 Flash	$0.57	$1.70	$0.71	$0.06	1M / 384K	8.0%
deepseek-v4-flash deepseek v4 Flash	$0.57	$1.70	$0.71	$0.06	1M / 384K	0.6%

deepseek-v4-pro

0.5% of platform traffic (30d)

Input $/M

$0.66/M

Output $/M

$1.98/M

1M / 384K

Popular

deepseek-v4.1-flash

8.0% of platform traffic (30d)

Input $/M

$0.57/M

Output $/M

$1.70/M

1M / 384K

deepseek-v4-flash

0.6% of platform traffic (30d)

Input $/M

$0.57/M

Output $/M

$1.70/M

1M / 384K

Alibaba Qwen Series

3 active models (30d)

Model	Input $/M	Output $/M	Cache W $/M	Cache R $/M	Context Window	Features	Traffic share (30d) ⓘ
qwen3.8-flash qwen3.8 Flash	$0.35	$1.05	$0.44	$0.09	1M / 128K	Vision Tools Cache	1.9%
qwen3.7-plus qwen3.7 plus	$0.40	$1.60	$0.50	$0.10	1M / 131K	Vision Tools	<0.1%
qwen3.8-max qwen3.8 max	$4.20	$12.59	$5.24	$1.05	1M / 128K	Vision Tools Cache	<0.1%

qwen3.8-flash

1.9% of platform traffic (30d)

Input $/M

$0.35/M

Output $/M

$1.05/M

1M / 128K Vision Tools Cache

qwen3.7-plus

<0.1% of platform traffic (30d)

Input $/M

$0.40/M

Output $/M

$1.60/M

1M / 131K Vision Tools

qwen3.8-max

<0.1% of platform traffic (30d)

Input $/M

$4.20/M

Output $/M

$12.59/M

1M / 128K Vision Tools Cache

Start Using These Models Now

Choose a plan that fits your workflow — from individual developer to enterprise team.

Personal Plans

Monthly plans with a daily quota, from $9.00/mo. Pay monthly, use all models.

View Pricing

Pay-as-you-go Packs

No monthly plan, from $4: one-time quota valid for 7 days, same models as personal plans.

View packs

Enterprise Teams

unified subscription, team management, dedicated support. Custom configurations available.

Learn More

Or create an account first — activate a plan whenever you are ready

Frequently Asked Questions

QCode applies a service rate multiplier on top of official model pricing. For example, Claude Sonnet 5 at $3/M tokens input with a 1.0× rate costs $3/M on QCode. Some providers may have different rates — see the rate cards above for current values.

The service rate is the tooling subscription fee QCode charges on top of underlying model pricing. The current rate for each series is listed in the rate cards above.

Pricing data is sourced from the LiteLLM pricing database, automatically synchronized by QCode's CRS service via hash check every 10 minutes. Page cache refreshes every 10 minutes.

Same rule as OpenAI: for the GPT series (gpt-6.1-sol, gpt-6-sol, gpt-6-astra), when a single request has more than 272K input tokens (cached tokens included), the whole request bills input and cache reads at 2x and output at 1.5x; at or below 272K the standard rates apply. The long-context price for each model is the ">272K" line under the price in the table above. Only the GPT series is split into short and long tiers — Claude and every other model bill at the listed rates.

Pricing data sourced from the LiteLLM model pricing database, auto-synced by QCode CRS. Updated: 2026-10-27 19:08

Model pricing documentation · Billing documentation