AnvilHub

Transparency

Pricing

How Anvil computes cost.

Anvil estimates what every turn costs by multiplying measured token counts by published provider rates. This page shows those rates, how they have moved, and exactly where the estimate stops being certain.

Providers supported
35
Providers priced
26
Models priced
1173
Plans tracked
59
Rates verified
2026-09-08

Input price over time ($ per 1M tokens)

2026-08-09 → 2026-09-08

$0.000$41.25$82.50$123.75$165.00openai/o1-pro — $150.00 / 1M inputopenai/o1-pro:batch — unpriced / 1M inputgpt-5.4-pro (global · gt_272k) — $60.00 / 1M inputgpt-4-32k (global) — $60.00 / 1M inputGLM-5.2 GLM-5.1 GLM-5 — $40.00 / 1M inputGLM-5 GLM-5.1 — unpriced / 1M inputGLM-5 GLM-5.1 — unpriced / 1M inputgpt-5.4-pro (global · le_272k) — $30.00 / 1M inputgpt-4-8k (global) — $30.00 / 1M inputgpt-5.5-pro — $30.00 / 1M inputgpt-5.4-pro — $30.00 / 1M inputopenai/gpt-5.5-pro — $30.00 / 1M inputopenai/gpt-5.4-pro — $30.00 / 1M inputopenai/gpt-4 — $30.00 / 1M inputgpt-5.5-pro — unpriced / 1M input
  • openai/o1-pro
  • openai/o1-pro:batch
  • gpt-5.4-pro (global · gt_272k)
  • gpt-4-32k (global)
  • GLM-5.2 GLM-5.1 GLM-5
  • GLM-5 GLM-5.1
  • gpt-5.4-pro (global · le_272k)
  • gpt-4-8k (global)
  • gpt-5.5-pro
  • gpt-5.4-pro
  • openai/gpt-5.5-pro
  • openai/gpt-5.4-pro
  • openai/gpt-4
  • gpt-5.5-pro

Showing the 14 priciest of 1306 series. 1,292 not plotted — narrow by provider to see the rest, or read exact rates in the tables below.

OpenRouter

API pricing ↗Plans ↗

Subscription plans

  • Free

    $0 / mo

    25+ free models across 4 providers, 50 requests/day. No platform fee (free models only).

  • Pay-as-you-go

    $0 / mo

    5.5% platform fee on inference. 400+ models, 70+ providers, no minimum spend. BYOK: no fee up to $25,000/mo of list-price inference, 5% after.

  • Enterprise

    price on request

    Fee discounts available, volume commitments, SSO/SAML, contractual SLAs. BYOK: no fee up to $200,000/mo of list-price inference, 5% after.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
inclusionai/ling-3.0-flash-sante:free$0.000$0.000$0.000$0.0002026-09-05
inclusionai/ling-3.0-flash-fin:free$0.000$0.000$0.000$0.0002026-08-28
dots-studio/dots-3-note-preview:free$0.000$0.000$0.000$0.0002026-08-16
liquid/lfm-2.5-2.6b:free$0.000$0.000$0.000$0.0002026-08-20
nvidia/nemotron-3.5-lightning:free$0.000$0.000$0.000$0.0002026-08-12
thinkingmachines/inkling-small:free$0.000$0.000$0.000$0.0002026-08-22
poolside/laguna-s-2.1:free$0.000$0.000$0.000$0.0002026-08-04
thinkingmachines/inkling:free$0.000$0.000$0.000$0.0002026-08-22
poolside/laguna-xs-2.1:free$0.000$0.000$0.000$0.0002026-08-04
cohere/north-mini-code:free$0.000$0.000$0.000$0.0002026-08-04
nvidia/nemotron-3.5-content-safety:free$0.000$0.000$0.000$0.0002026-08-04
nvidia/nemotron-3-ultra-550b-a55b:free$0.000$0.000$0.000$0.0002026-08-04
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free$0.000$0.000$0.000$0.0002026-08-04
google/gemma-4-26b-a4b-it:free$0.000$0.000$0.000$0.0002026-08-04
google/gemma-4-31b-it:free$0.000$0.000$0.000$0.0002026-08-04
google/lyria-3-pro-preview$0.000$0.000$0.000$0.0002026-08-04
google/lyria-3-clip-preview$0.000$0.000$0.000$0.0002026-08-04
nvidia/nemotron-3-super-120b-a12b:free$0.000$0.000$0.000$0.0002026-08-04
openrouter/free$0.000$0.000$0.000$0.0002026-08-04
ibm-granite/granite-4.0-h-micro$0.017$0.112$0.000$0.0002026-08-04
mistralai/mistral-nemo$0.019$0.030$0.000$0.0002026-08-04
inclusionai/ling-3.0-flash$0.021$0.063$0.000$0.0042026-08-07
nex-agi/nex-n2-mini$0.025$0.100$0.000$0.0032026-08-04
openai/gpt-5-nano:batch$0.025$0.200$0.000$0.0032026-09-01
meta-llama/llama-3.2-1b-instruct$0.027$0.201$0.000$0.0002026-08-04
upstage/solar-pro4$0.030$0.120$0.000$0.0062026-08-11
qwen/qwen3.7-flash$0.030$0.130$0.038$0.0062026-08-04
openai/gpt-oss-20b$0.030$0.130$0.000$0.0302026-08-04
amazon/nova-micro-v1$0.035$0.140$0.000$0.0002026-08-04
openai/gpt-oss-120b$0.037$0.170$0.000$0.0002026-08-23
cohere/command-r7b-12-2024$0.037$0.150$0.000$0.0002026-08-04
inception/mercury-2.5-preview$0.040$0.150$0.000$0.0042026-09-03
sao10k/l3-lunaris-8b$0.040$0.050$0.000$0.0002026-08-04
tencent/hy-mt2-1.8b$0.044$0.177$0.000$0.0002026-08-21
qwen/qwen3-30b-a3b-instruct-2507$0.048$0.193$0.000$0.0002026-08-04
~deepseek/deepseek-v4-flash-latest$0.050$0.160$0.000$0.0132026-09-07
nvidia/nemotron-3-nano-30b-a3b$0.050$0.200$0.000$0.0302026-09-03
openai/gpt-5-nano$0.050$0.400$0.000$0.0052026-08-04
openai/gpt-oss-20b:batch$0.050$0.200$0.000$0.0002026-08-29
google/gemini-2.5-flash-lite:batch$0.050$0.200$0.000$0.0102026-08-07
openai/gpt-4.1-nano:batch$0.050$0.200$0.000$0.0132026-09-01
google/gemma-3-4b-it$0.050$0.100$0.000$0.0002026-08-04
google/gemma-3-12b-it$0.050$0.150$0.000$0.0002026-08-04
mistralai/mistral-small-24b-instruct-2501$0.050$0.080$0.000$0.0002026-08-04
meta-llama/llama-3.2-3b-instruct$0.050$0.330$0.000$0.0002026-08-04
meta-llama/llama-3.1-8b-instruct$0.050$0.080$0.000$0.0252026-08-04
inclusionai/ling-3.0-flash-fin$0.060$0.180$0.000$0.0122026-09-04
poolside/laguna-xs-2.1$0.060$0.120$0.000$0.0302026-08-04
amazon/nova-lite-v1$0.060$0.240$0.000$0.0002026-08-04
gryphe/mythomax-l2-13b$0.060$0.060$0.000$0.0002026-09-03
z-ai/glm-4.7-flash$0.060$0.400$0.000$0.0002026-09-08
qwen/qwen3.5-flash-02-23$0.065$0.260$0.000$0.0002026-08-04
google/gemma-4-26b-a4b-it$0.070$0.340$0.000$0.0002026-08-18
qwen/qwen3-coder-30b-a3b-instruct$0.070$0.280$0.000$0.0002026-08-11
microsoft/phi-4$0.070$0.140$0.000$0.0002026-08-04
~z-ai/glm-flash-latest$0.071$0.237$0.000$0.0142026-09-08
tencent/hy-mt2-30b-a3b$0.074$0.295$0.000$0.0002026-08-21
tencent/hy-mt2-7b$0.074$0.295$0.000$0.0002026-08-23
z-ai/glm-5.3-flash$0.075$0.250$0.000$0.0152026-08-27
bytedance-seed/seed-1.6-flash$0.075$0.300$0.000$0.0002026-08-04
openai/gpt-oss-safeguard-20b$0.075$0.300$0.000$0.0372026-08-04
mistralai/mistral-small-3.2-24b-instruct$0.075$0.200$0.000$0.0002026-08-22
openai/gpt-4o-mini:batch$0.075$0.300$0.000$0.0372026-09-01
nvidia/nemotron-3.5-lightning$0.080$0.200$0.000$0.0402026-08-29
qwen/qwen3-32b$0.080$0.280$0.000$0.0002026-08-04
google/gemma-3-27b-it$0.080$0.450$0.000$0.0402026-08-04
nvidia/nemotron-3-super-120b-a12b$0.085$0.400$0.000$0.0002026-08-10
deepseek/deepseek-v4-flash$0.089$0.177$0.000$0.0182026-09-07
poolside/laguna-s-2.1$0.090$0.180$0.000$0.0092026-08-04
google/gemma-4-31b-it$0.090$0.340$0.000$0.0502026-08-26
qwen/qwen3-235b-a22b-2507$0.090$0.550$0.000$0.0002026-09-05
meta/muse-spark-1.3-contributor$0.100$0.200$0.000$0.0022026-09-03
ibm-granite/granite-4.2-8b$0.100$0.150$0.000$0.0502026-09-01
meta/muse-spark-1.2-contributor$0.100$0.200$0.000$0.0022026-08-22
openai/gpt-5.6-luna-pro:batch$0.100$0.600$0.000$0.0102026-09-01
openai/gpt-5.6-luna:batch$0.100$0.600$0.000$0.0102026-09-01
qwen/qwen3.6-35b-a3b$0.100$0.900$0.000$0.0502026-08-28
rekaai/reka-edge$0.100$0.100$0.000$0.0002026-08-04
openai/gpt-5.4-nano:batch$0.100$0.625$0.000$0.0102026-09-01
qwen/qwen3.5-9b$0.100$0.150$0.000$0.0002026-08-04
bytedance-seed/seed-2.0-mini$0.100$0.400$0.000$0.0002026-08-04
stepfun/step-3.5-flash$0.100$0.300$0.000$0.0002026-08-04
mistralai/ministral-3b-2512$0.100$0.100$0.000$0.0102026-08-04
mistralai/voxtral-small-24b-2507$0.100$0.300$0.000$0.0102026-08-04
qwen/qwen3-next-80b-a3b-instruct$0.100$1.10$0.000$0.0702026-09-01
bytedance/ui-tars-1.5-7b$0.100$0.200$0.000$0.1002026-08-04
google/gemini-2.5-flash-lite$0.100$0.400$0.083$0.0102026-08-04
openai/gpt-4.1-nano$0.100$0.400$0.000$0.0252026-08-31
meta-llama/llama-4-scout$0.100$0.300$0.000$0.0002026-09-03
rekaai/reka-flash-3$0.100$0.200$0.000$0.0002026-08-04
meta-llama/llama-3.3-70b-instruct$0.100$0.320$0.000$0.0002026-09-04
qwen/qwen-2.5-7b-instruct$0.100$0.200$0.000$0.0002026-08-04
qwen/qwen3-vl-32b-instruct$0.104$0.416$0.000$0.0002026-08-04
qwen/qwen3-vl-8b-instruct$0.117$0.455$0.000$0.0002026-08-04
qwen/qwen3-8b$0.117$0.455$0.000$0.0002026-08-04
qwen/qwen3-coder-next$0.120$0.800$0.000$0.0702026-08-04
qwen/qwen3-30b-a3b$0.120$0.500$0.000$0.0002026-08-23
google/gemini-3.1-flash-lite:batch$0.125$0.750$0.000$0.0132026-08-07
openai/gpt-5-mini:batch$0.125$1.00$0.000$0.0132026-09-01
nousresearch/hermes-4-70b$0.130$0.400$0.000$0.0002026-08-04
z-ai/glm-4.5-air$0.130$0.850$0.000$0.0252026-08-04
tencent/hy3$0.132$0.528$0.000$0.0332026-08-04
deepseek/deepseek-v4-flash-0731$0.140$0.280$0.000$0.0282026-09-07
deepseek/deepseek-v4-flash-0731:batch$0.140$0.280$0.000$0.0302026-08-29
xiaomi/mimo-v2.5$0.140$0.280$0.000$0.0032026-08-04
tencent/hunyuan-a13b-instruct$0.140$0.570$0.000$0.0002026-08-04
qwen/qwen3.8-flash$0.150$0.470$0.200$0.0162026-08-28
z-ai/glm-5.3-flash:batch$0.150$0.500$0.000$0.0302026-08-29
google/gemini-3.5-flash-lite:batch$0.150$1.25$0.000$0.0152026-08-07
perceptron/perceptron-mk1$0.150$1.50$0.000$0.0002026-08-04
mistralai/mistral-small-2603$0.150$0.600$0.000$0.0152026-08-04
upstage/solar-pro-3$0.150$0.600$0.000$0.0152026-08-04
mistralai/ministral-8b-2512$0.150$0.150$0.000$0.0152026-08-04
qwen/qwen3-vl-30b-a3b-instruct$0.150$0.600$0.000$0.0002026-08-29
qwen/qwen3-next-80b-a3b-thinking$0.150$1.20$0.000$0.0002026-08-04
openai/gpt-oss-120b:batch$0.150$0.600$0.000$0.0002026-08-29
google/gemini-2.5-flash:batch$0.150$1.25$0.000$0.0302026-08-07
cohere/command-r-08-2024$0.150$0.600$0.000$0.0002026-08-04
openai/gpt-4o-mini$0.150$0.600$0.000$0.0752026-08-04
openai/gpt-4o-mini-2024-07-18$0.150$0.600$0.000$0.0752026-08-04
qwen/qwen3.5-9b:batch$0.170$0.250$0.000$0.0002026-08-29
tencent/hy3-preview$0.180$0.600$0.000$0.0602026-08-16
qwen/qwen3-vl-8b-thinking$0.180$2.10$0.000$0.0002026-08-04
meta-llama/llama-guard-4-12b$0.180$0.180$0.000$0.0002026-08-04
qwen/qwen3.6-flash$0.188$1.13$0.234$0.0002026-08-04
qwen/qwen3.5-27b$0.195$1.56$0.000$0.0002026-08-04
qwen/qwen3-coder-flash$0.195$0.975$0.244$0.0392026-08-04
openai/gpt-5.6-luna-pro$0.200$1.20$0.250$0.0202026-08-18
openai/gpt-5.6-luna$0.200$1.20$0.250$0.0202026-08-18
nvidia/nemotron-3.5-content-safety$0.200$0.200$0.000$0.0002026-09-04
stepfun/step-3.7-flash$0.200$1.15$0.000$0.0402026-08-04
openai/gpt-5.4-nano$0.200$1.25$0.000$0.0202026-08-04
mistralai/ministral-14b-2512$0.200$0.200$0.000$0.0202026-08-04
qwen/qwen3-vl-30b-a3b-thinking$0.200$2.40$0.000$0.0002026-08-04
qwen/qwen3-30b-a3b-thinking-2507$0.200$2.40$0.000$0.0002026-08-04
cognitivecomputations/dolphin-mistral-24b-venice-edition$0.200$0.900$0.000$0.0002026-08-04
openai/gpt-4.1-mini:batch$0.200$0.800$0.000$0.0502026-09-01
meta-llama/llama-4-maverick$0.200$0.696$0.000$0.0002026-08-31
mistralai/mistral-saba$0.200$0.600$0.000$0.0202026-08-04
minimax/minimax-01$0.200$1.10$0.000$0.0002026-08-04
qwen/qwen3-vl-235b-a22b-instruct$0.210$1.90$0.000$0.1002026-08-18
deepseek/deepseek-v4-flash-vision-exp$0.220$0.660$0.000$0.0072026-08-22
qwen/qwen3-14b$0.228$0.910$0.000$0.0002026-09-08
qwen/qwen3-235b-a22b-thinking-2507$0.230$2.30$0.000$0.0002026-08-04
google/gemini-3.1-flash-lite-image$0.250$1.50$0.000$0.0002026-08-04
nex-agi/nex-n2-pro$0.250$1.00$0.000$0.0252026-08-04
google/gemini-3.1-flash-lite$0.250$1.50$0.083$0.0252026-08-04
arcee-ai/trinity-large-thinking$0.250$0.800$0.000$0.0602026-08-31
bytedance-seed/seed-2.0-lite$0.250$2.00$0.000$0.0002026-08-04
inception/mercury-2$0.250$0.750$0.000$0.0252026-08-04
google/gemini-3.1-flash-lite-preview$0.250$1.50$0.083$0.0252026-08-04
bytedance-seed/seed-1.6$0.250$2.00$0.000$0.0002026-08-04
google/gemini-3-flash-preview:batch$0.250$1.50$0.000$0.0002026-08-07
openai/gpt-5.1-codex-mini$0.250$2.00$0.000$0.0302026-08-04
deepseek/deepseek-chat-v3.1$0.250$0.950$0.000$0.1302026-09-08
openai/gpt-5-mini$0.250$2.00$0.000$0.0252026-08-04
anthropic/claude-3-haiku$0.250$1.25$0.300$0.0302026-08-04
openai/gpt-3.5-turbo:batch$0.250$0.750$0.000$0.0002026-09-01
minimax/minimax-m2$0.255$1.02$0.000$0.0002026-08-04
qwen/qwen3.5-plus-02-15$0.260$1.56$0.000$0.0002026-08-04
qwen/qwen-plus-2025-07-28$0.260$0.780$0.000$0.0002026-08-04
qwen/qwen-plus$0.260$0.780$0.325$0.0522026-08-04
deepseek/deepseek-v3.2$0.269$0.400$0.000$0.1352026-08-30
minimax/minimax-m2.5$0.270$1.08$0.000$0.0272026-08-22
deepseek/deepseek-v3.2-exp$0.270$0.410$0.000$0.0002026-08-04
deepseek/deepseek-v3.1-terminus$0.270$1.00$0.000$0.1352026-08-21
qwen/qwen3.5-122b-a10b$0.290$2.40$0.000$0.0002026-08-29
deepseek/deepseek-chat-v3-0324$0.290$1.14$0.000$0.1102026-09-08
meta/muse-glimmer-30b$0.300$1.10$0.000$0.0402026-09-03
google/gemini-3.5-flash-lite$0.300$2.50$0.083$0.0302026-08-04
meituan/longcat-2.0$0.300$1.20$0.000$0.0062026-08-04
minimax/minimax-m3$0.300$1.20$0.000$0.0602026-08-04
minimax/minimax-m3:batch$0.300$1.20$0.000$0.0602026-08-19
qwen/qwen3.5-plus-20260420$0.300$1.80$0.375$0.0002026-08-04
qwen/qwen3.6-27b$0.300$2.00$0.000$0.0302026-09-05
kwaipilot/kat-coder-pro-v2$0.300$1.20$0.000$0.0602026-08-04
minimax/minimax-m2.7$0.300$1.20$0.000$0.0602026-08-25
minimax/minimax-m2-her$0.300$1.20$0.000$0.0302026-08-04
minimax/minimax-m2.1$0.300$1.20$0.000$0.0302026-08-04
z-ai/glm-4.6v$0.300$0.900$0.000$0.0552026-08-04
amazon/nova-2-lite-v1$0.300$2.50$0.000$0.0002026-08-04
google/gemini-2.5-flash-image$0.300$2.50$0.083$0.0302026-08-04
thedrummer/cydonia-24b-v4.1$0.300$0.500$0.000$0.1502026-08-04
mistralai/codestral-2508$0.300$0.900$0.000$0.0302026-08-04
qwen/qwen3-coder$0.300$1.00$0.000$0.1002026-08-04
google/gemini-2.5-flash$0.300$2.50$0.083$0.0302026-08-04
qwen/qwen3.5-35b-a3b$0.313$1.25$0.000$0.1562026-09-06
qwen/qwen3.7-plus$0.320$1.28$0.400$0.0642026-08-04
deepseek/deepseek-chat$0.320$0.890$0.000$0.0002026-09-04
qwen/qwen3.6-plus$0.325$1.95$0.406$0.0002026-08-04
meta/muse-glimmer-30b:batch$0.350$1.50$0.000$0.0402026-08-29
undi95/remm-slerp-l2-13b$0.350$0.650$0.000$0.0002026-09-04
mistralai/mistral-small-3.1-24b-instruct$0.351$0.555$0.000$0.0002026-08-04
qwen/qwen-2.5-72b-instruct$0.360$0.400$0.000$0.0002026-08-04
google/gemini-3.8-flash:batch$0.375$1.88$0.042$0.0372026-09-03
google/gemini-3.7-flash:batch$0.375$1.88$0.042$0.0372026-09-03
google/gemini-3.6-flash:batch$0.375$1.88$0.042$0.0372026-08-14
openai/gpt-5.4-mini:batch$0.375$2.25$0.000$0.0372026-09-01
google/gemma-4-31b-it:batch$0.390$0.970$0.000$0.0002026-08-29
qwen/qwen3.5-397b-a17b$0.390$2.34$0.000$0.0002026-09-07
z-ai/glm-4.7$0.400$1.75$0.000$0.0802026-08-04
mistralai/devstral-2512$0.400$2.00$0.000$0.0402026-08-31
qwen/qwen3-vl-235b-a22b-thinking$0.400$4.00$0.000$0.0002026-08-07
mistralai/mistral-medium-3.1$0.400$2.00$0.000$0.0402026-08-04
minimax/minimax-m1$0.400$2.20$0.000$0.0002026-09-08
mistralai/mistral-medium-3$0.400$2.00$0.000$0.0402026-08-04
openai/gpt-4.1-mini$0.400$1.60$0.000$0.1002026-08-04
thedrummer/unslopnemo-12b$0.400$0.400$0.000$0.0002026-08-04
meta-llama/llama-3.1-70b-instruct$0.400$0.400$0.000$0.0002026-08-04
mancer/weaver$0.400$0.750$0.000$0.0002026-09-01
qwen/qwen3.8-27b$0.420$3.00$0.000$0.0852026-09-04
baidu/ernie-4.5-vl-424b-a47b$0.420$1.25$0.000$0.0002026-08-04
xiaomi/mimo-v2.5-pro$0.435$0.870$0.000$0.0042026-08-04
thinkingmachines/inkling-small$0.450$1.20$0.000$0.1002026-08-08
moonshotai/kimi-k2.5$0.450$2.25$0.000$0.0702026-08-31
qwen/qwen3-235b-a22b$0.455$1.82$0.000$0.0002026-08-04
bytedance-seed/seed-2-1-turbo$0.500$2.50$0.000$0.0002026-08-13
bytedance-seed/seed-2.0-code$0.500$3.00$0.000$0.0002026-08-12
thinkingmachines/inkling-small:batch$0.500$1.20$0.000$0.1002026-08-29
google/gemini-3.1-flash-image$0.500$3.00$0.000$0.0002026-08-04
google/gemini-3.1-flash-image-preview$0.500$3.00$0.000$0.0002026-08-04
google/gemini-3-flash-preview$0.500$3.00$0.083$0.0502026-08-04
mistralai/mistral-large-2512$0.500$1.50$0.000$0.0502026-08-04
anthropic/claude-haiku-4.5:batch$0.500$2.50$0.625$0.0502026-08-07
deepseek/deepseek-r1-0528$0.500$2.15$0.000$0.3502026-08-04
openai/gpt-3.5-turbo$0.500$1.50$0.000$0.0002026-08-04
z-ai/glm-4.6$0.550$2.20$0.000$0.1102026-09-08
openai/o4-mini:batch$0.550$2.20$0.000$0.1382026-09-01
thedrummer/skyfall-36b-v2$0.550$0.800$0.000$0.2502026-08-04
openai/o3-mini:batch$0.550$2.20$0.000$0.2752026-09-01
moonshotai/kimi-k2$0.570$2.30$0.000$0.0002026-08-04
z-ai/glm-5$0.600$1.92$0.000$0.1202026-08-16
writer/palmyra-x5$0.600$6.00$0.000$0.0002026-08-04
openai/gpt-audio-mini$0.600$2.40$0.000$0.0002026-08-04
moonshotai/kimi-k2-thinking$0.600$2.50$0.000$0.0002026-09-08
moonshotai/kimi-k2-0905$0.600$2.50$0.000$0.0002026-08-04
z-ai/glm-4.5v$0.600$1.80$0.000$0.1102026-08-04
z-ai/glm-4.5$0.600$2.20$0.000$0.1102026-08-04
microsoft/wizardlm-2-8x22b$0.620$0.620$0.000$0.0002026-08-04
nvidia/nemotron-3-ultra-550b-a55b$0.625$3.13$0.000$0.1882026-09-04
openai/gpt-5.1:batch$0.625$5.00$0.000$0.0632026-09-01
openai/gpt-5:batch$0.625$5.00$0.000$0.0632026-09-01
google/gemini-2.5-pro:batch$0.625$5.00$0.000$0.1252026-08-07
qwen/qwen3-coder-plus$0.650$3.25$0.813$0.1302026-08-04
sao10k/l3.3-euryale-70b$0.650$0.750$0.000$0.0002026-08-04
google/gemma-2-27b-it$0.650$0.650$0.000$0.0002026-08-04
qwen/qwen-2.5-coder-32b-instruct$0.660$1.00$0.000$0.0002026-08-04
aion-labs/aion-3.0-mini$0.700$1.40$0.000$0.1802026-08-04
deepseek/deepseek-r1$0.700$2.50$0.000$0.0002026-08-04
nousresearch/hermes-3-llama-3.1-70b$0.700$0.700$0.000$0.0002026-08-04
moonshotai/kimi-k2.7-code$0.710$3.50$0.000$0.1502026-09-08
kwaipilot/kat-coder-pro-v2.5$0.740$2.96$0.000$0.1502026-08-04
google/gemini-3.8-flash$0.750$3.75$0.042$0.0752026-09-03
google/gemini-3.7-flash$0.750$3.75$0.042$0.0752026-08-29
google/gemini-3.6-flash$0.750$3.75$0.042$0.0752026-08-14
google/gemini-3.5-flash:batch$0.750$4.50$0.000$0.0752026-08-07
mistralai/mistral-medium-3-5:batch$0.750$3.75$0.000$0.0002026-08-29
~openai/gpt-mini-latest$0.750$4.50$0.000$0.0752026-08-04
~google/gemini-flash-latest$0.750$3.75$0.042$0.0752026-08-29
openai/gpt-5.4-mini$0.750$4.50$0.000$0.0752026-08-04
qwen/qwen3-max-thinking$0.780$3.90$0.000$0.0002026-08-04
qwen/qwen3-max$0.780$3.90$0.975$0.1562026-08-04
aion-labs/aion-2.0$0.800$1.60$0.000$0.2002026-08-04
morph/morph-v3-fast$0.800$1.20$0.000$0.0002026-08-04
aion-labs/aion-rp-llama-3.1-8b$0.800$1.60$0.000$0.0002026-08-04
qwen/qwen2.5-vl-72b-instruct$0.800$1.00$0.000$0.4002026-09-04
deepseek/deepseek-r1-distill-llama-70b$0.800$0.800$0.000$0.0002026-08-04
amazon/nova-pro-v1$0.800$3.20$0.000$0.0002026-08-04
tencent/hy4-preview$0.834$2.50$0.000$0.0422026-08-29
relace/relace-apply-3$0.850$1.25$0.000$0.0002026-08-04
sao10k/l3.1-euryale-70b$0.850$0.850$0.000$0.0002026-08-04
openai/gpt-5.2:batch$0.875$7.00$0.000$0.0872026-09-01
morph/morph-v3-large$0.900$1.90$0.000$0.0002026-08-04
sakana/sakana-namazu$0.950$4.00$0.000$0.1502026-08-11
moonshotai/kimi-k2.6$0.950$4.00$0.000$0.1602026-08-23
deepseek/deepseek-v4-pro$0.955$1.91$0.000$0.0802026-09-08
z-ai/glm-5.2$0.966$3.04$0.000$0.1932026-09-03
z-ai/glm-5.1$0.966$3.04$0.000$0.1792026-08-30
thinkingmachines/inkling$1.00$4.05$0.000$0.1702026-08-30
thinkingmachines/inkling:batch$1.00$4.05$0.000$0.1702026-08-19
openai/gpt-5.6-terra-pro:batch$1.00$6.00$0.000$0.1002026-09-01
openai/gpt-5.6-terra:batch$1.00$6.00$0.000$0.1002026-09-01
openai/gpt-5.6-sol-pro:batch$1.00$5.00$1.25$0.1002026-09-01
openai/gpt-5.6-sol:batch$1.00$5.00$1.25$0.1002026-09-01
anthropic/claude-sonnet-5:batch$1.00$5.00$1.25$0.1002026-08-07
x-ai/grok-build-0.1$1.00$2.00$0.000$0.2002026-08-04
x-ai/grok-4.3:batch$1.00$2.00$0.000$0.1602026-09-04
~anthropic/claude-haiku-latest$1.00$5.00$1.25$0.1002026-08-04
google/gemini-3.1-pro-preview:batch$1.00$6.00$0.000$0.0002026-08-07
relace/relace-search$1.00$3.00$0.000$0.0002026-08-04
anthropic/claude-haiku-4.5$1.00$5.00$1.25$0.1002026-08-04
nousresearch/hermes-4-405b$1.00$3.00$0.000$0.0002026-08-04
openai/o3:batch$1.00$4.00$0.000$0.2502026-09-01
openai/gpt-4.1:batch$1.00$4.00$0.000$0.2502026-09-01
perplexity/sonar$1.00$1.00$0.000$0.0002026-08-04
nousresearch/hermes-3-llama-3.1-405b$1.00$1.00$0.000$0.0002026-08-04
openai/gpt-3.5-turbo-0613$1.00$2.00$0.000$0.0002026-08-04
qwen/qwen3.6-max-preview$1.03$6.16$1.28$0.0002026-08-04
deepseek/deepseek-v4-pro-0813$1.05$3.15$0.000$0.0352026-09-08
openai/o4-mini-high$1.10$4.40$0.000$0.2752026-08-04
openai/o4-mini$1.10$4.40$0.000$0.2752026-08-04
openai/o3-mini-high$1.10$4.40$0.000$0.5502026-08-04
openai/o3-mini$1.10$4.40$0.000$0.5502026-08-04
~z-ai/glm-latest$1.12$3.52$0.000$0.2082026-09-08
z-ai/glm-5v-turbo$1.20$4.00$0.000$0.2402026-08-04
z-ai/glm-5-turbo$1.20$4.00$0.000$0.2402026-08-04
meta/muse-spark-1.3$1.25$4.25$0.000$0.1502026-09-03
meta/muse-spark-1.2$1.25$4.25$0.000$0.1502026-08-06
meta/muse-spark-1.1$1.25$4.25$0.000$0.1502026-08-04
x-ai/grok-4.3$1.25$2.50$0.000$0.2002026-08-04
x-ai/grok-4.20-multi-agent$1.25$2.50$0.000$0.2002026-08-04
x-ai/grok-4.20$1.25$2.50$0.000$0.2002026-08-04
openai/gpt-5.4:batch$1.25$7.50$0.000$0.1252026-09-01
openai/gpt-5.1-codex-max$1.25$10.00$0.000$0.1252026-08-04
openai/gpt-5.1$1.25$10.00$0.000$0.1252026-08-04
openai/gpt-5.1-codex$1.25$10.00$0.000$0.1302026-08-04
openai/gpt-5$1.25$10.00$0.000$0.1252026-08-04
google/gemini-2.5-pro$1.25$10.00$0.375$0.1252026-08-04
google/gemini-2.5-pro-preview$1.25$10.00$0.375$0.1252026-08-04
google/gemini-2.5-pro-preview-05-06$1.25$10.00$0.375$0.1252026-08-04
openai/gpt-4o:batch$1.25$5.00$0.000$0.6252026-09-01
deepseek/deepseek-v4-pro-0813:batch$1.32$3.96$0.000$0.1302026-08-29
z-ai/glm-5.3$1.40$4.40$0.000$0.2602026-09-07
qwen/qwen3.7-max$1.48$4.42$1.84$0.2952026-08-04
google/gemini-3.5-flash$1.50$9.00$0.083$0.1502026-08-04
mistralai/mistral-medium-3-5$1.50$7.50$0.000$0.0002026-08-04
anthropic/claude-sonnet-4.6:batch$1.50$7.50$1.88$0.1502026-08-07
anthropic/claude-sonnet-4.5:batch$1.50$7.50$1.88$0.1502026-08-07
openai/gpt-3.5-turbo-instruct$1.50$2.00$0.000$0.0002026-08-04
openai/gpt-5.3-codex$1.75$14.00$0.000$0.1752026-08-04
openai/gpt-5.2-codex$1.75$14.00$0.000$0.1752026-08-04
openai/gpt-5.2-chat$1.75$14.00$0.000$0.1752026-08-04
openai/gpt-5.2$1.75$14.00$0.000$0.1752026-08-04
qwen/qwen3.8-max-0902$2.00$6.00$2.50$0.2502026-09-06
qwen/qwen3.8-2.4t-a95b$2.00$6.00$0.000$0.2502026-08-14
qwen/qwen3.8-2.4t-a95b:batch$2.00$6.00$0.000$0.2502026-09-03
x-ai/grok-4.6$2.00$6.00$0.000$0.5002026-08-13
openai/gpt-5.6-terra-pro$2.00$12.00$2.50$0.2002026-08-18
openai/gpt-5.6-terra$2.00$12.00$2.50$0.2002026-08-18
openai/gpt-5.6-sol-pro$2.00$10.00$2.50$0.2002026-08-22
openai/gpt-5.6-sol$2.00$10.00$2.50$0.2002026-08-22
x-ai/grok-4.5$2.00$6.00$0.000$0.3002026-08-04
~x-ai/grok-latest$2.00$6.00$0.000$0.5002026-08-13
anthropic/claude-sonnet-5$2.00$10.00$2.50$0.2002026-08-04
google/gemini-3-pro-image$2.00$12.00$0.375$0.2002026-08-04
~google/gemini-pro-latest$2.00$12.00$0.375$0.2002026-08-04
~anthropic/claude-sonnet-latest$2.00$10.00$2.50$0.2002026-08-04
~openai/gpt-latest$2.00$10.00$2.50$0.2002026-08-22
google/gemini-3.1-pro-preview-customtools$2.00$12.00$0.375$0.2002026-08-04
google/gemini-3.1-pro-preview$2.00$12.00$0.375$0.2002026-08-04
google/gemini-3-pro-image-preview$2.00$12.00$0.375$0.2002026-08-04
openai/o3$2.00$8.00$0.000$0.5002026-08-04
openai/gpt-4.1$2.00$8.00$0.000$0.5002026-08-04
perplexity/sonar-reasoning-pro$2.00$8.00$0.000$0.0002026-08-04
perplexity/sonar-deep-research$2.00$8.00$0.000$0.0002026-08-04
mistralai/mistral-large-2407$2.00$6.00$0.000$0.2002026-08-04
mistralai/mixtral-8x22b-instruct$2.00$6.00$0.000$0.2002026-08-04
mistralai/mistral-large$2.00$6.00$0.000$0.2002026-08-04
anthropic/claude-opus-5:batch$2.50$12.50$3.13$0.2502026-08-07
anthropic/claude-opus-4.8:batch$2.50$12.50$3.13$0.2502026-08-07
~moonshotai/kimi-latest$2.50$14.00$0.000$0.2902026-09-08
openai/gpt-5.5:batch$2.50$15.00$0.000$0.2502026-09-01
anthropic/claude-opus-4.7:batch$2.50$12.50$3.13$0.2502026-08-07
openai/gpt-5.4$2.50$15.00$0.000$0.2502026-08-04
anthropic/claude-opus-4.6:batch$2.50$12.50$3.13$0.2502026-08-07
openai/gpt-audio$2.50$10.00$0.000$0.0002026-08-04
anthropic/claude-opus-4.5:batch$2.50$12.50$3.13$0.2502026-08-07
amazon/nova-premier-v1$2.50$12.50$0.000$0.6252026-08-04
openai/gpt-5-image-mini$2.50$2.00$0.000$0.2502026-08-04
cohere/command-a$2.50$10.00$0.000$0.0002026-08-04
openai/gpt-4o-2024-11-20$2.50$10.00$0.000$1.252026-08-04
anthracite-org/magnum-v4-72b$2.50$5.00$0.000$0.0002026-09-01
cohere/command-r-plus-08-2024$2.50$10.00$0.000$0.0002026-08-04
openai/gpt-4o-2024-08-06$2.50$10.00$0.000$1.252026-08-04
openai/gpt-4o$2.50$10.00$0.000$1.252026-08-04
moonshotai/kimi-k3$3.00$15.00$0.000$0.3002026-08-04
moonshotai/kimi-k3:batch$3.00$15.00$0.000$0.3002026-08-29
aion-labs/aion-3.0$3.00$6.00$0.000$0.7502026-08-04
anthropic/claude-sonnet-4.6$3.00$15.00$3.75$0.3002026-08-04
perplexity/sonar-pro-search$3.00$15.00$0.000$0.0002026-08-04
anthropic/claude-sonnet-4.5$3.00$15.00$3.75$0.3002026-08-04
anthropic/claude-sonnet-4$3.00$15.00$3.75$0.3002026-08-04
perplexity/sonar-pro$3.00$15.00$0.000$0.0002026-08-04
openai/gpt-3.5-turbo-16k$3.00$4.00$0.000$0.0002026-08-04
openai/gpt-6-astra:batch$5.00$25.00$6.25$0.5002026-09-05
openai/gpt-6-astra-pro:batch$5.00$25.00$6.25$0.5002026-09-05
anthropic/claude-fable-5.1:batch$5.00$25.00$6.25$0.1252026-09-03
anthropic/claude-opus-5$5.00$25.00$6.25$0.5002026-08-04
sakana/fugu-ultra$5.00$30.00$0.000$0.5002026-08-04
anthropic/claude-fable-5:batch$5.00$25.00$6.25$0.5002026-08-07
anthropic/claude-opus-4.8$5.00$25.00$6.25$0.5002026-08-04
openai/gpt-chat-latest$5.00$30.00$0.000$0.5002026-08-04
openai/gpt-5.5$5.00$30.00$0.000$0.5002026-08-04
~anthropic/claude-opus-latest$5.00$25.00$6.25$0.5002026-08-04
anthropic/claude-opus-4.7$5.00$25.00$6.25$0.5002026-08-04
anthropic/claude-opus-4.6$5.00$25.00$6.25$0.5002026-08-04
anthropic/claude-opus-4.5$5.00$25.00$6.25$0.5002026-08-04
openai/gpt-4o-2024-05-13$5.00$15.00$0.000$0.0002026-08-04
openai/gpt-4-turbo:batch$5.00$15.00$0.000$0.0002026-09-01
openai/gpt-5-pro:batch$7.50$60.00$0.000$0.0002026-09-01
anthropic/claude-opus-4.1:batch$7.50$37.50$9.38$0.7502026-08-07
openai/gpt-5.4-image-2$8.00$15.00$0.000$2.002026-08-04
openai/gpt-6-astra$10.00$50.00$12.50$1.002026-09-05
openai/gpt-6-astra-pro$10.00$50.00$12.50$1.002026-09-05
anthropic/claude-fable-5.1$10.00$50.00$12.50$0.2502026-09-03
~anthropic/claude-fable-latest$10.00$50.00$12.50$0.2502026-09-03
anthropic/claude-fable-5$10.00$50.00$12.50$1.002026-08-04
openai/gpt-5-image$10.00$10.00$0.000$1.252026-08-04
openai/gpt-4-turbo$10.00$30.00$0.000$0.0002026-08-04
openai/gpt-4-turbo-preview$10.00$30.00$0.000$0.0002026-08-04
openai/gpt-5.2-pro:batch$10.50$84.00$0.000$0.0002026-09-01
openai/gpt-5.5-pro:batch$15.00$90.00$0.000$0.0002026-09-01
openai/gpt-5.4-pro:batch$15.00$90.00$0.000$0.0002026-09-01
openai/gpt-5-pro$15.00$120.00$0.000$0.0002026-08-04
anthropic/claude-opus-4.1$15.00$75.00$18.75$1.502026-08-04
anthropic/claude-opus-4$15.00$75.00$18.75$1.502026-08-04
openai/o1$15.00$60.00$0.000$7.502026-08-04
openai/o3-pro$20.00$80.00$0.000$0.0002026-08-04
openai/gpt-5.2-pro$21.00$168.00$0.000$0.0002026-08-04
openai/gpt-5.5-pro$30.00$180.00$0.000$0.0002026-08-04
openai/gpt-5.4-pro$30.00$180.00$0.000$0.0002026-08-04
openai/gpt-4$30.00$60.00$0.000$0.0002026-08-04
openai/o1-pro$150.00$600.00$0.000$0.0002026-08-04

Alibaba DashScope

API pricing ↗Plans ↗

Subscription plans

  • AI Token Plan

    from $6 / mo

    'Starts from $6/mo. Build more, spend less — one plan, every modality.'

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
qwen3.7-flash≤32K ctx$0.030$0.130$0.000$0.0032026-08-29
qwen3.7-flash-2026-07-15≤32K ctx$0.030$0.130$0.000$0.0032026-08-29
qwen-flash≤256K ctx$0.050$0.400$0.000$0.0052026-08-11
qwen-flash-2025-07-28≤256K ctx$0.050$0.400$0.000$0.0052026-08-11
qwen-turbo$0.050$0.200$0.000$0.0052026-08-11
qwen3-vl-flash≤32K ctx$0.050$0.400$0.000$0.0052026-08-11
qwen3-vl-flash-2026-01-22≤32K ctx$0.050$0.400$0.000$0.0052026-08-11
qwen3-vl-flash-2025-10-15≤32K ctx$0.050$0.400$0.000$0.0052026-08-11
qwen-flash-character$0.050$0.400$0.000$0.0052026-08-11
qwen-omni-turbo$0.070$4.44$0.000$0.0072026-08-11
qwen-omni-turbo-latest$0.070$4.44$0.000$0.0072026-08-11
qwen-omni-turbo-2025-03-26$0.070$4.44$0.000$0.0072026-08-11
qwen-vl-ocr$0.070$0.160$0.000$0.0072026-08-11
qwen3.5-flash≤1M ctx$0.100$0.400$0.000$0.0102026-08-11
qwen3.5-flash-2026-02-23≤1M ctx$0.100$0.400$0.000$0.0102026-08-11
qwen2.5-omni-7b$0.100$6.76$0.000$0.0102026-08-11
qwen-mt-lite$0.120$0.360$0.000$0.0122026-08-11
qwen3.8-flash≤1M ctx$0.150$0.470$0.000$0.0152026-08-29
qwen3-next-80b-a3b-thinking$0.150$1.20$0.000$0.0152026-08-11
qwen3-next-80b-a3b-instruct$0.150$1.20$0.000$0.0152026-08-11
qwen-mt-flash$0.160$0.490$0.000$0.0162026-08-11
qwen-mt-turbo$0.160$0.490$0.000$0.0162026-08-11
qwen3-32b$0.160$0.640$0.000$0.0162026-08-11
qwen3-vl-32b-thinking$0.160$0.640$0.000$0.0162026-08-11
qwen3-vl-32b-instruct$0.160$0.640$0.000$0.0162026-08-11
qwen3-8b$0.180$0.700$0.000$0.0182026-08-11
qwen3-vl-8b-thinking$0.180$2.10$0.000$0.0182026-08-11
qwen3-vl-8b-instruct$0.180$0.700$0.000$0.0182026-08-11
qwen3-vl-plus≤32K ctx$0.200$1.60$0.000$0.0202026-08-11
qwen3-vl-plus-2025-12-19≤32K ctx$0.200$1.60$0.000$0.0202026-08-11
qwen3-vl-plus-2025-09-23≤32K ctx$0.200$1.60$0.000$0.0202026-08-11
qwen3-30b-a3b-thinking-2507$0.200$2.40$0.000$0.0202026-08-11
qwen3-30b-a3b-instruct-2507$0.200$0.800$0.000$0.0202026-08-11
qwen3-30b-a3b$0.200$0.800$0.000$0.0202026-08-11
qwen3-vl-30b-a3b-thinking$0.200$2.40$0.000$0.0202026-08-11
qwen3-vl-30b-a3b-instruct$0.200$0.800$0.000$0.0202026-08-11
qwen-vl-plus$0.210$0.630$0.000$0.0212026-08-11
qwen3-235b-a22b-thinking-2507$0.230$2.30$0.000$0.0232026-08-11
qwen3-235b-a22b-instruct-2507$0.230$0.920$0.000$0.0232026-08-11
qwen3.6-flash≤256K ctx$0.250$1.50$0.000$0.0252026-08-11
qwen3.6-flash-2026-04-16≤256K ctx$0.250$1.50$0.000$0.0252026-08-11
qwen3.5-35b-a3b≤256K ctx$0.250$2.00$0.000$0.0252026-08-11
qwen-omni-turbo-realtime$0.270$4.44$0.000$0.0272026-08-11
qwen-omni-turbo-realtime-latest$0.270$4.44$0.000$0.0272026-08-11
qwen-omni-turbo-realtime-2025-05-08$0.270$4.44$0.000$0.0272026-08-11
qwen3-coder-flash≤32K ctx$0.300$1.50$0.000$0.0302026-08-11
qwen3-coder-flash-2025-07-28≤32K ctx$0.300$1.50$0.000$0.0302026-08-11
qwen3.5-27b≤256K ctx$0.300$2.40$0.000$0.0302026-08-11
qwen3-coder-next≤32K ctx$0.300$1.50$0.000$0.0302026-08-11
qwen3-14b$0.350$1.40$0.000$0.0352026-08-11
qwen3.6-35b-a3b≤256K ctx$0.375$2.25$0.000$0.0372026-08-11
qwen3.7-plus≤256K ctx$0.400$1.60$0.000$0.0402026-08-03
qwen-plus≤256K ctxthinking$0.400$4.00$0.000$0.0402026-08-03
qwen3.7-plus-2026-05-26≤256K ctx$0.400$1.60$0.000$0.0402026-08-03
qwen3.5-plus≤256K ctx$0.400$2.40$0.000$0.0402026-08-03
qwen3.5-plus-2026-04-20≤256K ctx$0.400$2.40$0.000$0.0402026-08-03
qwen3.5-plus-2026-02-15≤256K ctx$0.400$2.40$0.000$0.0402026-08-03
qwen-plus≤256K ctx$0.400$1.20$0.000$0.0402026-08-03
qwen-plus-latest≤256K ctx$0.400$1.20$0.000$0.0402026-08-03
qwen-plus-2025-12-01≤256K ctx$0.400$1.20$0.000$0.0402026-08-03
qwen-plus-2025-09-11≤256K ctx$0.400$1.20$0.000$0.0402026-08-03
qwen-plus-2025-07-28≤256K ctx$0.400$1.20$0.000$0.0402026-08-03
qwen-plus-2025-07-14$0.400$1.20$0.000$0.0402026-08-03
qwen-plus-2025-04-28$0.400$1.20$0.000$0.0402026-08-03
qwen-plus-2025-01-25$0.400$1.20$0.000$0.0402026-08-03
qwen3.5-omni-flash$0.400$3.00$0.000$0.0402026-08-11
qwen3.5-omni-flash-2026-03-15$0.400$3.00$0.000$0.0402026-08-11
qwen3.5-122b-a10b≤256K ctx$0.400$3.20$0.000$0.0402026-08-11
qwen3-vl-235b-a22b-thinking$0.400$4.00$0.000$0.0402026-08-11
qwen3-vl-235b-a22b-instruct$0.400$1.60$0.000$0.0402026-08-11
qwen3-omni-flash$0.430$3.81$0.000$0.0432026-08-11
qwen3-omni-flash-2025-12-01$0.430$3.81$0.000$0.0432026-08-11
qwen3-omni-flash-2025-09-15$0.430$3.81$0.000$0.0432026-08-11
qwen3-coder-30b-a3b-instruct≤32K ctx$0.450$2.25$0.000$0.0452026-08-11
qwen-audio-3.0-realtime-flash$0.450$4.50$0.000$0.0452026-08-29
qwen3.5-plus>256K ctx$0.500$3.00$0.000$0.0502026-08-03
qwen3.6-plus≤256K ctx$0.500$3.00$0.000$0.0502026-08-03
qwen3.6-plus-2026-04-02≤256K ctx$0.500$3.00$0.000$0.0502026-08-03
qwen3.8-27b≤1M ctx$0.500$3.00$0.000$0.0502026-08-29
qwen-plus-character$0.500$1.40$0.000$0.0502026-08-11
qwen-plus-character-ja$0.500$1.40$0.000$0.0502026-08-11
qwen3-omni-flash-realtime$0.520$4.57$0.000$0.0522026-08-11
qwen3-omni-flash-realtime-2025-12-01$0.520$4.57$0.000$0.0522026-08-11
qwen3-omni-flash-realtime-2025-09-15$0.520$4.57$0.000$0.0522026-08-11
qwen3.5-omni-flash-realtime$0.550$4.50$0.000$0.0552026-08-11
qwen3.5-omni-flash-realtime-2026-03-15$0.550$4.50$0.000$0.0552026-08-11
qwen3.6-27b≤256K ctx$0.600$3.60$0.000$0.0602026-08-11
qwen3.5-397b-a17b≤256K ctx$0.600$3.60$0.000$0.0602026-08-11
qwen3-235b-a22b$0.700$2.80$0.000$0.0702026-08-11
qwen-vl-max$0.800$3.20$0.000$0.0802026-08-11
qwen-audio-3.0-realtime-plus$0.800$6.40$0.000$0.0802026-08-29
qwen3-coder-plus≤32K ctx$1.00$5.00$0.000$0.1002026-08-11
qwen3-coder-plus-2025-09-23≤32K ctx$1.00$5.00$0.000$0.1002026-08-11
qwen3-coder-plus-2025-07-22≤32K ctx$1.00$5.00$0.000$0.1002026-08-11
qwen3.7-plus>256K ctx$1.20$4.80$0.000$0.1202026-08-03
qwen3.7-plus-2026-05-26>256K ctx$1.20$4.80$0.000$0.1202026-08-03
qwen-plus>256K ctx$1.20$3.60$0.000$0.1202026-08-03
qwen-plus>256K ctxthinking$1.20$12.00$0.000$0.1202026-08-03
qwen3-max≤32K ctx$1.20$6.00$0.000$0.1202026-08-03
qwen3-max-2026-01-23≤32K ctx$1.20$6.00$0.000$0.1202026-08-03
qwen3-max-2025-09-23≤32K ctx$1.20$6.00$0.000$0.1202026-08-03
qwen3-max-preview≤32K ctx$1.20$6.00$0.000$0.1202026-08-03
qwen3.6-max-preview≤128K ctx$1.30$7.80$0.000$0.1302026-08-03
qwen3.5-omni-plus$1.40$11.00$0.000$0.1402026-08-11
qwen3.5-omni-plus-2026-03-15$1.40$11.00$0.000$0.1402026-08-11
qwen3-coder-480b-a35b-instruct≤32K ctx$1.50$7.50$0.000$0.1502026-08-11
qwen3-livetranslate-flash$1.58$0.631$0.000$0.1582026-08-11
qwen3-livetranslate-flash-2025-12-01$1.58$0.631$0.000$0.1582026-08-11
qwen-max$1.60$6.40$0.000$0.1602026-08-03
qwen3.6-max-preview>128K ctx$2.00$12.00$0.000$0.2002026-08-03
qwen3.6-plus>256K ctx$2.00$6.00$0.000$0.2002026-08-03
qwen3.8-max≤1M ctx$2.00$6.00$0.000$0.2002026-08-03
qwen3.8-max-0902≤1M ctx$2.00$6.00$0.000$0.2002026-09-03
qwen3.8-2.4t-a95b≤1M ctx$2.00$6.00$0.000$0.2002026-08-29
qwen3.5-omni-plus-realtime$2.10$16.50$0.000$0.2102026-08-11
qwen3.5-omni-plus-realtime-2026-03-15$2.10$16.50$0.000$0.2102026-08-11
qwen3-max≤128K ctx$2.40$12.00$0.000$0.2402026-08-03
qwen-mt-plus$2.46$7.37$0.000$0.2462026-08-11
qwen3.7-max≤1M ctx$2.50$7.50$0.000$0.2502026-08-03
qwen3.7-max-2026-06-08≤1M ctx$2.50$7.50$0.000$0.2502026-08-03
qwen3.7-max-2026-05-20≤1M ctx$2.50$7.50$0.000$0.2502026-08-03
qwen3.7-max-preview≤1M ctx$2.50$7.50$0.000$0.2502026-08-03
qwen3.7-max-2026-05-17≤1M ctx$2.50$7.50$0.000$0.2502026-08-03
qwen3-max≤256K ctx$3.00$15.00$0.000$0.3002026-08-03
qwen3-omni-30b-a3b-captioner$3.81$3.06$0.000$0.3812026-08-11
qwen3.5-livetranslate-flash-realtime$7.50$0.550$0.000$0.7502026-08-11
qwen3.5-livetranslate-flash-realtime-2026-05-19$7.50$0.550$0.000$0.7502026-08-11
qwen3-livetranslate-flash-realtime$10.00$1.30$0.000$1.002026-08-11
qwen3-livetranslate-flash-realtime-2025-09-22$10.00$1.30$0.000$1.002026-08-11

Cortecs

API pricing ↗
ModelInputOutputCache writeCache readSince
qwen3guard-gen-8b€0.000€0.000€0.000€0.0002026-08-04
qwen3guard-gen-0.6b€0.000€0.000€0.000€0.0002026-08-04
nova-micro-v1€0.036€0.143€0.000€0.0002026-08-04
gpt-oss-20b€0.040€0.150€0.000€0.0002026-08-04
nvidia-nemotron-3-nano-30b-a3b€0.054€0.215€0.000€0.0002026-08-04
gpt-5-nano€0.054€0.394€0.000€0.0172026-08-04
qwen3-coder-30b-a3b-instruct€0.060€0.220€0.000€0.0002026-08-04
qwen3-235b-a22b-instruct-2507€0.062€0.408€0.000€0.0162026-08-04
nova-lite-v1€0.062€0.247€0.000€0.0002026-08-04
glm-4.7-flash€0.072€0.429€0.000€0.0002026-08-04
gpt-oss-120b€0.080€0.400€0.000€0.0002026-08-04
qwen3-32b€0.080€0.280€0.000€0.0002026-09-05
qwen3-30b-a3b-instruct-2507€0.089€0.268€0.000€0.0002026-08-04
gemma-3-27b-it€0.089€0.268€0.000€0.0002026-08-04
mistral-small-3.2-24b-instruct-2506€0.090€0.280€0.000€0.0002026-08-04
gemma-4-26b-a4b-it€0.100€0.500€0.000€0.0002026-08-04
qwen3.5-9b€0.100€0.150€0.000€0.0002026-08-04
voxtral-small-2507€0.100€0.300€0.000€0.0102026-08-04
ministral-3b-2512€0.100€0.100€0.000€0.0102026-08-04
mistral-7b-instruct-v0.3€0.100€0.100€0.000€0.0002026-08-04
gpt-4.1-nano€0.100€0.390€0.000€0.0502026-08-04
mistral-small-2503€0.100€0.300€0.000€0.0002026-08-04
llama-3.3-70b-instruct€0.116€0.358€0.000€0.0002026-08-04
deepseek-v4-flash-0731€0.117€0.251€0.000€0.0272026-08-12
mistral-small-2603€0.128€0.510€0.000€0.0132026-08-04
mistral-nemo-instruct-2407€0.130€0.130€0.000€0.0002026-08-04
mistral-7b-instruct-v0.2€0.143€0.197€0.000€0.0002026-08-04
gpt-4o-mini€0.143€0.573€0.000€0.0732026-08-04
qwen3.6-35b-a3b€0.150€0.500€0.000€0.0002026-08-04
qwen3-coder-next€0.150€0.800€0.000€0.0002026-08-04
ministral-8b-2512€0.150€0.150€0.000€0.0152026-08-04
llama-3.1-8b-instruct€0.150€0.150€0.000€0.0002026-08-04
gpt-oss-safeguard-120b€0.161€0.626€0.000€0.0002026-08-04
qwen3.8-flash-next€0.180€0.449€0.000€0.0452026-08-29
glm-5.3-flash€0.180€0.449€0.000€0.0452026-08-29
gpt-5.6-luna€0.197€1.19€0.000€0.0202026-08-22
gemma-4-31b-it€0.200€0.350€0.000€0.0002026-08-04
ministral-14b-2512€0.200€0.200€0.000€0.0202026-08-04
pixtral-12b-2409€0.200€0.200€0.000€0.0002026-08-04
nemotron-nano-v2-12b€0.215€0.635€0.000€0.0002026-08-04
gemini-3.1-flash-lite€0.244€1.46€0.000€0.0222026-08-04
gpt-5-mini€0.250€1.97€0.000€0.0502026-08-04
deepseek-v3.2€0.266€0.444€0.000€0.0672026-08-04
minimax-m2.5€0.266€1.06€0.000€0.0672026-08-21
gemini-2.5-flash€0.268€2.24€0.000€0.0262026-08-04
gemini-3.5-flash-lite€0.296€2.47€0.000€0.0302026-08-08
qwen3.8-27b€0.300€2.20€0.000€0.1002026-08-18
codestral-2508€0.300€0.900€0.000€0.0302026-08-04
minimax-m2€0.313€1.26€0.000€0.0002026-08-04
minimax-m2.1€0.322€1.29€0.000€0.0002026-08-04
nova-2-lite€0.335€2.82€0.000€0.0002026-08-04
minimax-m3€0.355€1.77€0.000€0.0892026-08-04
gpt-4.1-mini€0.390€1.53€0.000€0.1202026-08-04
qwen3.6-27b€0.400€2.70€0.000€0.0002026-08-04
devstral-2512€0.429€2.15€0.000€0.0002026-09-03
mixtral-8x7B-instruct-v0.1€0.438€0.680€0.000€0.0002026-08-04
qwen3.5-122b-a10b€0.444€3.11€0.000€0.1112026-08-04
kimi-k2.5€0.444€2.48€0.000€0.1112026-08-04
mistral-large-2512€0.500€1.50€0.000€0.0502026-08-04
qwen3-vl-235b-a22b€0.554€2.80€0.000€0.0002026-08-04
minicpm-v-4.5€0.584€0.985€0.000€0.0002026-08-04
deepseek-r1-0528€0.585€2.31€0.000€0.1462026-08-04
minimax-m2.7€0.600€2.40€0.000€0.0002026-08-04
qwen3.5-397b-a17b€0.600€3.60€0.000€0.0002026-08-04
gemini-3.7-flash€0.673€3.37€0.000€0.0672026-08-16
gemini-3.6-flash€0.673€3.37€0.000€0.0672026-08-16
kimi-k2.7-code€0.673€3.14€0.000€0.1802026-08-04
kimi-k2.6€0.694€3.03€0.000€0.1732026-08-04
nova-pro-v1€0.824€3.29€0.000€0.0002026-08-04
glm-5€0.887€2.84€0.000€0.2222026-08-04
claude-haiku-4-5€0.894€4.47€0.000€0.0892026-08-04
hermes-4-405b€0.894€2.68€0.000€0.0002026-08-04
qwen2.5-vl-72b-instruct€0.910€0.910€0.000€0.0002026-09-06
glm-5.3€1.00€3.50€0.000€0.2502026-09-08
glm-5v-turbo€1.06€3.55€0.000€0.2662026-08-04
glm-5-turbo€1.06€3.55€0.000€0.2662026-08-04
glm-5.2€1.08€3.77€0.000€0.2332026-08-04
gpt-5.1€1.23€9.84€0.000€0.1402026-08-04
gpt-5€1.23€9.84€0.000€0.1402026-08-04
glm-5.1€1.24€3.90€0.000€0.3112026-08-04
apertus-70b€1.25€2.00€0.000€0.0002026-08-04
mistral-medium-3.5€1.25€6.40€0.000€0.1252026-08-27
gemini-2.5-pro€1.34€8.94€0.000€0.2172026-08-04
gemini-3.5-flash€1.48€8.89€0.000€0.1482026-08-16
deepseek-v4-pro€1.55€3.11€0.000€0.3882026-08-04
llama-3.1-405b-instruct€1.75€1.75€0.000€0.0002026-08-04
pixtral-large-2502€1.79€5.37€0.000€0.0002026-08-04
deepseek-v4-pro-0813€1.79€3.59€0.000€0.4492026-09-01
gpt-4.1€1.97€7.87€0.000€0.4902026-08-04
gpt-5.6-terra€1.98€11.85€0.000€0.1972026-08-21
claude-sonnet-5€1.98€9.87€0.000€0.1972026-08-04
qwen3.8-2.4t-a95b€2.24€5.39€0.000€0.5612026-08-16
gpt-4o€2.39€9.55€0.000€1.192026-08-04
gpt-5.4€2.60€13.87€0.000€0.2172026-08-04
claude-sonnet-4€2.60€13.01€0.000€0.2602026-08-04
claude-4-5-sonnet€2.68€13.42€0.000€0.2932026-08-04
kimi-k3€2.69€13.46€0.000€0.0002026-08-04
claude-4-6-sonnet€2.87€14.31€0.000€0.2872026-08-04
mistral-large-2402€3.85€11.63€0.000€0.0002026-08-04
claude-opus4-6€4.77€23.84€0.000€0.4772026-08-04
claude-opus4-5€4.77€23.85€0.000€0.4772026-08-04
claude-opus4-8€4.88€24.40€0.000€0.4882026-08-04
claude-opus4-7€4.88€24.40€0.000€0.4882026-08-04
claude-opus-5€4.94€24.68€0.000€0.4942026-08-04
gpt-5.6-sol€4.94€29.62€0.000€0.4942026-08-04

Azure OpenAI

API pricing ↗
ModelInputOutputCache writeCache readSince
gpt-5-nanoglobal$0.050$0.400$0.000$0.0102026-08-03
gpt-4.1-nano-2025-04-14globalbatch$0.050$0.200$0.000$0.0002026-08-03
gpt-5-nanodata zone$0.060$0.440$0.000$0.0102026-08-03
gpt-oss-20bregional$0.070$0.300$0.000$0.0002026-08-03
gpt-4o-mini-2024-07-18globalbatch$0.075$0.300$0.000$0.0002026-08-03
gpt-4.1-nano-2025-04-14global$0.100$0.400$0.000$0.0002026-08-11
gpt-4.1-nano-2025-04-14data zone$0.110$0.440$0.000$0.0302026-08-03
gpt-4.1-nano-2025-04-14regional$0.110$0.440$0.000$0.0302026-08-03
gpt-4o-mini-2024-07-18global$0.150$0.600$0.000$0.0752026-08-03
gpt-oss-120bglobal$0.150$0.600$0.000$0.0002026-08-03
gpt-4o-mini-2024-07-18data zone$0.165$0.660$0.000$0.0832026-08-03
gpt-4o-mini-2024-07-18regional$0.165$0.660$0.000$0.0832026-08-03
gpt-5.4-nanoglobal$0.200$1.25$0.000$0.0202026-08-03
gpt-4.1-mini-2025-04-14globalbatch$0.200$0.800$0.000$0.0002026-08-03
gpt-5.1-codex-miniglobal$0.250$2.00$0.000$0.0302026-08-03
gpt-5-miniglobal$0.250$2.00$0.000$0.0302026-08-03
gpt-5-minidata zone$0.280$2.20$0.000$0.0302026-08-03
gpt-5.4-miniglobalbatch$0.380$2.25$0.000$0.0402026-08-03
gpt-4.1-mini-2025-04-14global$0.400$1.60$0.000$0.0002026-08-11
gpt-4.1-mini-2025-04-14data zone$0.440$1.76$0.000$0.1102026-08-03
gpt-4.1-mini-2025-04-14regional$0.440$1.76$0.000$0.1102026-08-03
gpt-5-miniglobalpriority$0.450$3.60$0.000$0.0502026-08-03
gpt-3.5-turbo-0125global$0.550$1.65$0.000$0.0002026-08-03
o4-mini-2025-04-16globalbatch$0.550$2.20$0.000$0.0002026-08-03
o3-mini-2025-01-31globalbatch$0.550$2.20$0.000$0.0002026-08-03
gpt-5-2025-08-07globalbatch$0.630$5.00$0.000$0.0702026-08-03
gpt-4.1-mini-2025-04-14globalpriority$0.700$2.80$0.000$0.1802026-08-03
gpt-5.4-miniglobal$0.750$4.50$0.000$0.0802026-08-03
gpt-5.4-minidata zone$0.830$4.95$0.000$0.0902026-08-03
gpt-5.6-luna≤272K ctxglobal$1.00$6.00$1.25$0.1002026-08-03
o3-2025-04-16globalbatch$1.00$4.00$0.000$0.0002026-08-03
gpt-4.1-2025-04-14globalbatch$1.00$4.00$0.000$0.0002026-08-03
o4-mini-2025-04-16global$1.10$4.40$0.000$0.2802026-08-03
o3-mini-2025-01-31global$1.10$4.40$0.000$0.5502026-08-03
o1-mini-2024-09-12global$1.10$4.40$0.000$0.5502026-08-03
o4-mini-2025-04-16data zone$1.21$4.84$0.000$0.3102026-08-03
o3-mini-2025-01-31data zone$1.21$4.84$0.000$0.6052026-08-03
o4-mini-2025-04-16regional$1.21$4.84$0.000$0.3102026-08-03
o3-mini-2025-01-31regional$1.21$4.84$0.000$0.6052026-08-03
gpt-5.1global$1.25$10.00$0.000$0.1302026-08-03
gpt-5.1-chatglobal$1.25$10.00$0.000$0.1302026-08-03
gpt-5.1-codexglobal$1.25$10.00$0.000$0.1302026-08-03
gpt-5.1-codex-maxglobal$1.25$10.00$0.000$0.1302026-08-03
gpt-5-2025-08-07global$1.25$10.00$0.000$0.1302026-08-03
gpt-5-codexglobal$1.25$10.00$0.000$0.1302026-08-03
gpt-5-chatglobal$1.25$10.00$0.000$0.1302026-08-03
gpt-5.4globalbatch$1.25$7.50$0.000$0.1302026-08-03
gpt-4o-2024-08-06globalbatch$1.25$5.00$0.000$0.0002026-08-03
gpt-5.1data zone$1.38$11.00$0.000$0.1402026-08-03
gpt-5-2025-08-07data zone$1.38$11.00$0.000$0.1402026-08-03
gpt-5.4-miniglobalpriority$1.50$9.00$0.000$0.1502026-08-03
gpt-5.3-codexglobal$1.75$14.00$0.000$0.1802026-08-03
gpt-5.3-chatglobal$1.75$14.00$0.000$0.1802026-08-03
gpt-5.2global$1.75$14.00$0.000$0.1802026-08-03
gpt-5.2-codexglobal$1.75$14.00$0.000$0.1802026-08-03
gpt-5.2-chat-latestglobal$1.75$14.00$0.000$0.1802026-08-03
gpt-5.2data zone$1.93$15.40$0.000$0.2002026-08-03
gpt-5.2-chatdata zone$1.93$15.40$0.000$0.2002026-08-03
gpt-5.6-luna>272K ctxglobal$2.00$9.00$2.50$0.2002026-08-03
gpt-4.1-2025-04-14global$2.00$8.00$0.000$0.0002026-08-11
o3-2025-04-16global$2.00$8.00$0.000$0.0002026-08-11
gpt-4.1-2025-04-14data zone$2.20$8.80$0.000$0.0002026-08-11
gpt-4.1-2025-04-14regional$2.20$8.80$0.000$0.0002026-08-11
o3-2025-04-16data zone$2.20$8.80$0.000$0.0002026-08-11
o3-2025-04-16regional$2.20$8.80$0.000$0.0002026-08-11
gpt-5.6-terra≤272K ctxglobal$2.50$15.00$3.13$0.2502026-08-03
gpt-5.4≤272K ctxglobal$2.50$15.00$0.000$0.2502026-08-03
gpt-4o-2024-11-20global$2.50$10.00$0.000$1.252026-08-03
gpt-4o-2024-08-06global$2.50$10.00$0.000$1.252026-08-03
gpt-5.1globalpriority$2.50$20.00$0.000$0.2502026-08-03
gpt-5-2025-08-07globalpriority$2.50$20.00$0.000$0.2502026-08-03
gpt-5.4data zone$2.75$16.50$0.000$0.2802026-08-03
gpt-4o-2024-08-06regional$2.75$11.00$0.000$1.382026-08-03
gpt-4o-2024-08-06data zone$2.75$11.00$0.000$0.0002026-08-11
computer-use-previewglobal$3.00$12.00$0.000$0.0002026-08-03
gpt-5.3-codexglobalpriority$3.50$28.00$0.000$0.3502026-08-03
gpt-5.2globalpriority$3.50$28.00$0.000$0.3502026-08-03
gpt-4.1-2025-04-14globalpriority$3.50$14.00$0.000$0.8802026-08-03
gpt-chat-latest-05052026global$5.00$30.00$0.000$0.5002026-08-03
gpt-5.6-sol≤272K ctxglobal$5.00$30.00$6.25$0.5002026-08-03
gpt-5.6-terra>272K ctxglobal$5.00$22.50$6.25$0.5002026-08-03
gpt-5.5global$5.00$30.00$0.000$0.5002026-08-03
gpt-5.4>272K ctxglobal$5.00$22.50$0.000$0.5002026-08-03
gpt-4o-2024-05-13global$5.00$15.00$0.000$0.0002026-08-03
gpt-5.6-terraglobalpriority$5.00$30.00$0.000$0.5002026-08-03
gpt-5.4globalpriority$5.00$30.00$0.000$0.5002026-08-03
gpt-5.5data zone$5.50$33.00$0.000$0.5502026-08-03
gpt-5.6-sol>272K ctxglobal$10.00$45.00$12.50$1.002026-08-03
gpt-5.5-long-context>272K ctxglobal$10.00$45.00$0.000$1.002026-08-03
o3-deep-researchglobal$10.00$40.00$0.000$2.502026-08-03
gpt-5.6-solglobalpriority$10.00$60.00$0.000$1.002026-08-03
gpt-4-turboglobal$11.00$33.00$0.000$0.0002026-08-03
gpt-5.5globalpriority$12.50$75.00$0.000$1.252026-08-03
gpt-5-proglobal$15.00$120.00$0.000$0.0002026-08-03
o1-2024-12-17global$15.00$60.00$0.000$7.502026-08-03
o1-2024-12-17data zone$16.50$66.00$0.000$8.252026-08-03
o1-2024-12-17regional$16.50$66.00$0.000$8.252026-08-03
gpt-5.4-pro≤272K ctxglobal$30.00$180.00$0.000$0.0002026-08-03
gpt-4-8kglobal$30.00$60.00$0.000$0.0002026-08-03
gpt-5.4-pro>272K ctxglobal$60.00$270.00$0.000$0.0002026-08-03
gpt-4-32kglobal$60.00$120.00$0.000$0.0002026-08-03

OpenCode

API pricing ↗Plans ↗

Subscription plans

  • OpenCode

    $0 / mo

    The agent is 100% free and ships with a set of free models. Bring your own provider (75+ via Models.dev), or sign in with GitHub Copilot / ChatGPT Plus/Pro to spend those subscriptions.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
big-pickle$0.000$0.000$0.000$0.0002026-08-03
deepseek-v4-flash-free$0.000$0.000$0.000$0.0002026-08-03
laguna-s-2.1-free$0.000$0.000$0.000$0.0002026-08-03
ling-3.0-flash-free$0.000$0.000$0.000$0.0002026-08-03
north-mini-code-free$0.000$0.000$0.000$0.0002026-08-03
Read Cached Write Big Pickle$0.000$0.000$0.000$0.0002026-08-04
mimo-v2.5-free$0.000$0.000$0.000$0.0002026-08-03
Ling 3.0 Flash Fin Free$0.000$0.000$0.000$0.0002026-08-29
nemotron-3-ultra-free$0.000$0.000$0.000$0.0002026-08-03
Nemotron 3.5 Lightning Free$0.000$0.000$0.000$0.0002026-08-12
Spark 1.3 Contributor Free$0.000$0.000$0.000$0.0002026-09-03
gpt-5-nano$0.050$0.400$0.000$0.0052026-08-03
deepseek-v4-flash$0.140$0.280$0.000$0.0282026-08-03
DeepSeek V4 Flash Vision Exp$0.140$0.280$0.000$0.0282026-09-05
GLM 5.3 Flash$0.150$0.500$0.000$0.0302026-09-05
qwen3.5-plus$0.200$1.20$0.250$0.0202026-08-03
gpt-5.6-luna≤272K ctx$0.200$1.20$0.250$0.0202026-08-03
gpt-5.4-nano$0.200$1.25$0.000$0.0202026-08-03
gpt-5.1-codex-mini$0.250$2.00$0.000$0.0252026-08-03
minimax-m3$0.300$1.20$0.000$0.0602026-08-03
minimax-m2.7$0.300$1.20$0.000$0.0602026-08-03
minimax-m2.5$0.300$1.20$0.000$0.0602026-08-03
gemini-3.5-flash-lite$0.300$2.50$0.000$0.0302026-08-03
qwen3.7-plus$0.400$1.60$0.500$0.0402026-08-03
gpt-5.6-luna>272K ctx$0.400$1.80$0.500$0.0402026-08-03
qwen3.6-plus$0.500$3.00$0.625$0.0502026-08-03
gemini-3-flash$0.500$3.00$0.000$0.0502026-08-03
kimi-k2.5$0.600$3.00$0.000$0.1002026-08-03
gpt-5.4-mini$0.750$4.50$0.000$0.0752026-08-03
kimi-k2.7-code$0.950$4.00$0.000$0.1902026-08-03
kimi-k2.6$0.950$4.00$0.000$0.1602026-08-03
glm-5$1.00$3.20$0.000$0.2002026-08-03
claude-haiku-4-5$1.00$5.00$1.25$0.1002026-08-03
grok-build-0.1$1.00$2.00$0.000$0.2002026-08-03
gpt-5.1$1.07$8.50$0.000$0.1072026-08-03
gpt-5.1-codex$1.07$8.50$0.000$0.1072026-08-03
gpt-5$1.07$8.50$0.000$0.1072026-08-03
gpt-5-codex$1.07$8.50$0.000$0.1072026-08-03
Muse Spark 1.3$1.25$4.25$0.000$0.1502026-09-05
Muse Spark 1.2$1.25$4.25$0.000$0.1502026-08-16
gpt-5.1-codex-max$1.25$10.00$0.000$0.1252026-08-03
GLM 5.3$1.40$4.40$0.000$0.2602026-09-05
glm-5.2$1.40$4.40$0.000$0.2602026-08-03
glm-5.1$1.40$4.40$0.000$0.2602026-08-03
Gemini 3.8 Flash$1.50$7.50$0.000$0.1502026-09-03
Gemini 3.7 Flash$1.50$7.50$0.000$0.1502026-08-14
gemini-3.6-flash$1.50$7.50$0.000$0.1502026-08-03
gemini-3.5-flash$1.50$9.00$0.000$0.1502026-08-03
deepseek-v4-pro$1.74$3.48$0.000$0.1452026-08-03
gpt-5.3-codex-spark$1.75$14.00$0.000$0.1752026-08-03
gpt-5.3-codex$1.75$14.00$0.000$0.1752026-08-03
gpt-5.2$1.75$14.00$0.000$0.1752026-08-03
gpt-5.2-codex$1.75$14.00$0.000$0.1752026-08-03
claude-sonnet-5$2.00$10.00$2.50$0.2002026-08-03
gemini-3.1-pro≤200K ctx$2.00$12.00$0.000$0.2002026-08-03
Grok 4.6≤200K ctx$2.00$6.00$0.000$0.5002026-08-13
grok-4.5≤200K ctx$2.00$6.00$0.000$0.3002026-08-03
gpt-5.6-sol≤272K ctx$2.00$10.00$2.50$0.2002026-08-22
gpt-5.6-terra≤272K ctx$2.00$12.00$2.50$0.2002026-08-03
qwen3.7-max$2.50$7.50$3.13$0.5002026-08-03
gpt-5.4≤272K ctx$2.50$15.00$0.000$0.2502026-08-03
kimi-k3$3.00$15.00$0.000$0.3002026-08-03
claude-sonnet-4-6$3.00$15.00$3.75$0.3002026-08-03
claude-sonnet-4-5≤200K ctx$3.00$15.00$3.75$0.3002026-08-03
gemini-3.1-pro>200K ctx$4.00$18.00$0.000$0.4002026-08-03
Grok 4.6>200K ctx$4.00$12.00$0.000$1.002026-08-13
grok-4.5>200K ctx$4.00$12.00$0.000$0.6002026-08-03
gpt-5.6-sol>272K ctx$4.00$15.00$5.00$0.4002026-08-22
gpt-5.6-terra>272K ctx$4.00$18.00$5.00$0.4002026-08-03
claude-opus-5$5.00$25.00$6.25$0.5002026-08-03
claude-opus-4-8$5.00$25.00$6.25$0.5002026-08-03
claude-opus-4-7$5.00$25.00$6.25$0.5002026-08-03
claude-opus-4-6$5.00$25.00$6.25$0.5002026-08-03
claude-opus-4-5$5.00$25.00$6.25$0.5002026-08-03
gpt-5.5≤272K ctx$5.00$30.00$0.000$0.5002026-08-03
gpt-5.4>272K ctx$5.00$22.50$0.000$0.5002026-08-03
claude-sonnet-4-5>200K ctx$6.00$22.50$7.50$0.6002026-08-03
Claude Fable 5.1$10.00$50.00$12.50$0.2502026-09-03
claude-fable-5$10.00$50.00$12.50$1.002026-08-03
GPT 6 Astra≤272K ctx$10.00$50.00$12.50$1.002026-09-05
gpt-5.5>272K ctx$10.00$45.00$0.000$1.002026-08-03
GPT 6 Astra>272K ctx$20.00$75.00$25.00$2.002026-09-05
gpt-5.5-pro$30.00$180.00$0.000$30.002026-08-03
gpt-5.4-pro$30.00$180.00$0.000$30.002026-08-03

DeepInfra

API pricing ↗
ModelInputOutputCache writeCache readSince
mistralai/Mistral-Nemo-Instruct-2407$0.019$0.030$0.000$0.0002026-08-03
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo$0.020$0.040$0.000$0.0002026-08-03
google/gemma-4-E4B-it$0.020$0.100$0.000$0.0002026-08-13
google/gemma-3-12b-it$0.050$0.150$0.000$0.0002026-08-03
google/gemma-3-4b-it$0.050$0.100$0.000$0.0002026-08-03
nvidia/Nemotron-3-Nano-30B-A3B$0.050$0.200$0.000$0.0252026-08-03
mistralai/Mistral-Small-24B-Instruct-2501$0.050$0.080$0.000$0.0002026-08-03
deepseek-ai/DeepSeek-V4-Flash-0731$0.060$0.180$0.000$0.0152026-09-07
google/gemma-4-26B-A4B-it$0.070$0.340$0.000$0.0002026-08-03
microsoft/phi-4$0.070$0.140$0.000$0.0002026-08-03
mistralai/Mistral-Small-3.2-24B-Instruct-2506$0.075$0.200$0.000$0.0002026-08-03
Qwen/Qwen3-32B$0.080$0.280$0.000$0.0002026-08-03
google/gemma-3-27b-it$0.080$0.160$0.000$0.0002026-08-03
nvidia/NVIDIA-Nemotron-3.5-Lightning$0.080$0.200$0.000$0.0402026-08-14
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B$0.085$0.400$0.000$0.0002026-08-03
deepseek-ai/DeepSeek-V4-Flash$0.090$0.180$0.000$0.0182026-08-03
Qwen/Qwen3-Next-80B-A3B-Instruct$0.090$1.10$0.000$0.0002026-08-03
Qwen/Qwen3-235B-A22B-Instruct-2507$0.090$0.550$0.000$0.0002026-08-03
google/gemma-4-31B-it-turbo$0.090$0.340$0.000$0.0502026-08-03
Qwen/Qwen3.6-35B-A3B$0.100$0.950$0.000$0.0002026-08-13
Qwen/Qwen3.5-9B$0.100$0.150$0.000$0.0002026-08-13
meta-llama/Llama-4-Scout-17B-16E$0.100$0.300$0.000$0.0002026-08-03
meta-llama/Llama-3.3-70B-Instruct-Turbo$0.100$0.320$0.000$0.0002026-08-03
Qwen/Qwen3-30B-A3B$0.120$0.500$0.000$0.0002026-08-03
Qwen/Qwen3-14B$0.120$0.240$0.000$0.0002026-08-03
google/gemma-4-31B-it$0.130$0.380$0.000$0.0002026-08-03
Qwen/Qwen3.5-35B-A3B$0.140$1.00$0.000$0.0502026-08-13
Qwen/Qwen3-VL-30B-A3B-Instruct$0.150$0.600$0.000$0.0002026-08-03
meta-llama/Llama-Guard-4-12B$0.180$0.180$0.000$0.0002026-08-03
Qwen/Qwen3-VL-235B-A22B-Instruct$0.200$0.880$0.000$0.1102026-08-03
meta-llama/Llama-4-Maverick-17B-128E$0.200$0.800$0.000$0.0002026-08-03
nvidia/Nemotron-Content-Safety-3.5$0.200$0.200$0.000$0.0002026-08-13
Qwen/Qwen3-235B-A22B-Thinking-2507$0.230$2.30$0.000$0.2002026-08-03
deepseek-ai/DeepSeek-V3-0324$0.240$0.900$0.000$0.1352026-08-03
deepseek-ai/DeepSeek-V3.1$0.250$0.950$0.000$0.1302026-08-03
google/gemini-3.1-flash-lite$0.250$1.50$0.000$0.0002026-08-03
deepseek-ai/DeepSeek-V3.2$0.260$0.380$0.000$0.1302026-08-03
Qwen/Qwen3.5-27B$0.260$2.60$0.000$0.0002026-08-13
deepseek-ai/DeepSeek-V3.1-Terminus$0.270$0.950$0.000$0.1302026-08-03
google/gemma-4-31B-it-Ultra$0.270$0.760$0.000$0.0002026-08-13
Qwen/Qwen3.5-122B-A10B$0.290$2.40$0.000$0.0002026-08-13
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo$0.300$1.00$0.000$0.1002026-08-03
google/gemini-2.5-flash$0.300$2.50$0.000$0.0002026-08-03
deepseek-ai/DeepSeek-V3$0.320$0.890$0.000$0.0002026-08-03
Qwen/Qwen3.6-27B$0.320$3.20$0.000$0.0002026-08-13
Qwen/Qwen2.5-72B-Instruct$0.360$0.400$0.000$0.0002026-08-03
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo$0.400$0.400$0.000$0.0002026-08-03
Gryphe/MythoMax-L2-13b$0.400$0.400$0.000$0.0002026-08-03
Qwen/Qwen3.5-397B-A17B$0.450$3.00$0.000$0.2202026-08-13
deepseek-ai/DeepSeek-R1-0528$0.500$2.15$0.000$0.3502026-08-03
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B$0.500$2.20$0.000$0.1002026-08-13
Kimi-K2.7-Code$0.680$3.40$0.000$0.1362026-08-13
Kimi-K2.6$0.750$3.50$0.000$0.1502026-08-13
anthropic/claude-haiku-4-5$1.00$5.00$0.000$0.0002026-08-03
deepseek-ai/DeepSeek-V4-Proflex$1.04$2.08$0.000$0.0802026-08-03
Qwen/Qwen3-Max-Thinking$1.20$6.00$0.000$0.2402026-08-03
Qwen/Qwen3-Max$1.20$6.00$0.000$0.2402026-08-03
google/gemini-2.5-pro$1.25$10.00$0.000$0.0002026-08-03
deepseek-ai/DeepSeek-V4-Pro$1.30$2.60$0.000$0.1002026-08-03
google/gemini-3.5-flash$1.50$9.00$0.000$0.0002026-08-03
Qwen/Qwen3.8-Max$1.65$4.95$0.000$0.2062026-08-13
deepseek-ai/DeepSeek-V4-Propriority$1.95$3.90$0.000$0.1502026-08-03
google/gemini-3.1-pro$2.00$12.00$0.000$0.0002026-08-03
Qwen/Qwen3.7-Max$2.50$7.50$0.000$0.5002026-08-03
Kimi-K3$2.85$14.25$0.000$0.2852026-08-13
anthropic/claude-sonnet-5$3.00$15.00$0.000$0.0002026-09-03
anthropic/claude-sonnet-4-6$3.00$15.00$0.000$0.0002026-08-03
anthropic/claude-opus-5$5.00$25.00$0.000$0.0002026-08-13
anthropic/claude-opus-4-7$5.00$25.00$0.000$0.0002026-08-03
anthropic/claude-opus-4-8$5.00$25.00$0.000$0.0002026-08-03
anthropic/claude-fable-5$10.00$50.00$0.000$0.0002026-08-03

Together AI

API pricing ↗
ModelInputOutputCache writeCache readSince
Ternary Bonsai 27B$0.000$0.000$0.000$0.0002026-08-18
LFM2.5-8B-A1B$0.030$0.120$0.000$0.0002026-08-03
gpt-oss-20B$0.050$0.200$0.000$0.0002026-08-03
Gemma 3n E4B Instruct$0.060$0.120$0.000$0.0002026-08-03
DeepSeek V4 Flash 0731$0.140$0.280$0.000$0.0302026-08-11
Llama 3 8B Instruct Lite$0.140$0.140$0.000$0.0002026-08-03
GLM-5.3-Flash$0.150$0.500$0.000$0.0302026-08-28
Qwen3.8 Flash$0.150$0.470$0.000$0.0002026-09-01
gpt-oss-120B$0.150$0.600$0.000$0.0002026-08-03
Rnj-1 Instruct$0.150$0.150$0.000$0.0002026-08-03
Qwen3.5 9B$0.170$0.250$0.000$0.0002026-08-03
Qwen3 235B A22B Instruct 2507 FP8$0.200$0.600$0.000$0.0002026-08-03
A22B Instruct 2507 FP8 Throughput$0.200$0.600$0.000$0.0002026-08-11
Gemma-4-31B-it-Pearl$0.280$0.860$0.000$0.0002026-08-03
MiniMax M3$0.300$1.20$0.000$0.0602026-08-03
price Model Input output MiniMax M3$0.300$1.20$0.000$0.0602026-08-18
MiniMax M2.7$0.300$1.20$0.000$0.0602026-08-03
Qwen2.5 7B Instruct Turbo$0.300$0.300$0.000$0.0002026-08-03
Model Input output MiniMax M3$0.300$1.20$0.000$0.0002026-08-11
Qwen3.7-Plus$0.320$1.28$0.000$0.0002026-08-03
Muse Glimmer 30B$0.350$1.50$0.000$0.0402026-08-13
Gemma 4 31B$0.390$0.970$0.000$0.0002026-08-03
LoRA Full Fine-Tuning Up to 16B$0.480$0.540$0.000$0.0002026-08-11
Inkling Small$0.500$1.20$0.000$0.1002026-08-03
Qwen3.6-Plus$0.500$3.00$0.000$0.0002026-08-03
NVIDIA Nemotron 3 Ultra$0.600$3.60$0.000$0.2002026-08-03
Qwen3.5-397B-A17B$0.600$3.60$0.000$0.3502026-08-03
Kimi K2.7 Code$0.950$4.00$0.000$0.1902026-08-03
Inkling$1.00$4.05$0.000$0.1702026-08-03
Llama 3.3 70B$1.04$1.04$0.000$0.0002026-08-03
Kimi K2.6$1.20$4.50$0.000$0.2002026-08-03
Qwen3.7-Max$1.25$3.75$0.000$0.1302026-08-03
Cogito v2.1 671B$1.25$1.25$0.000$0.0002026-08-03
DeepSeek V4 Pro 0813$1.32$3.96$0.000$0.1302026-08-18
GLM-5.1$1.40$4.40$0.000$0.2602026-08-03
GLM-5.3$1.40$4.40$0.000$0.2602026-08-29
GLM-5.2$1.40$4.40$0.000$0.2602026-08-03
DeepSeek V4 Pro$1.74$3.48$0.000$0.2002026-08-03
days NVIDIA HGX H100$1.99$3.99$0.000$0.0002026-09-03
Qwen3.8-2.4T-A95B$2.00$6.00$0.000$0.2502026-08-29
Contact us NVIDIA HGX H200$2.99$5.99$0.000$0.0002026-09-03
Kimi K3$3.00$15.00$0.000$0.3002026-08-03
Llama 4 Scout Instruct$3.00$7.50$0.000$0.0002026-08-19
Contact us NVIDIA HGX B200$4.09$8.19$0.000$0.0002026-09-03
V4 Flash 0731 DeepSeek-V4 Flash$6.00$15.00$0.000$0.0002026-08-19
Qwen3.5-122B-A10B$6.00$15.00$0.000$0.0002026-08-19
Llama 4 Maverick Instruct$8.00$20.00$0.000$0.0002026-08-19
DeepSeek-V3.1$10.00$25.00$0.000$0.0002026-08-19
Kimi K2.6 Kimi K2.7-Code$15.00$37.50$0.000$0.0002026-08-19
GLM-5.2 GLM-5.1 GLM-5$40.00$100.00$0.000$0.0002026-08-19

Fireworks AI

API pricing ↗
ModelInputOutputCache writeCache readSince
IDIA Nemotron 3.5 Lightning 30B A3B$0.050$0.200$0.000$0.0102026-08-14
OpenAI GPT OSS 20B$0.070$0.300$0.000$0.0352026-08-03
DeepSeek V4 Flash$0.140$0.280$0.000$0.0282026-08-03
GLM 5.3 Flash$0.150$0.500$0.000$0.0302026-09-01
OpenAI GPT OSS 120B$0.150$0.600$0.000$0.0152026-08-03
OpenAI GPT OSS 120Bpriority$0.180$0.720$0.000$0.0182026-08-03
DeepSeek V4 Flashpriority$0.210$0.420$0.000$0.0422026-08-03
DeepSeek V4 Flash (0731)$0.220$0.660$0.000$0.0072026-08-22
DeepSeek V4 Flash Vision Exp$0.220$0.660$0.000$0.0072026-09-03
DeepSeek V4 Flash (0731)priority$0.275$0.825$0.000$0.0092026-08-22
DeepSeek V4 Flash Vision Exppriority$0.275$0.825$0.000$0.0092026-09-03
MiniMax M2.7$0.300$1.20$0.000$0.0602026-08-03
MiniMax M3$0.300$1.20$0.000$0.0602026-08-03
Muse Glimmer 30B$0.350$1.50$0.000$0.0402026-08-14
Qwen 3.7 Plus$0.400$1.60$0.000$0.0802026-08-03
MiniMax M2.7priority$0.450$1.80$0.000$0.0902026-08-03
MiniMax M3priority$0.450$1.80$0.000$0.0902026-08-03
Muse Glimmer 30Bpriority$0.525$2.25$0.000$0.0602026-08-14
NVIDIA Nemotron 3 Ultra$0.600$2.40$0.000$0.1202026-08-03
NVIDIA Nemotron 3 Ultra (Preview)$0.600$2.40$0.000$0.1202026-08-11
Kimi K2.7 Code$0.950$4.00$0.000$0.1902026-08-03
Kimi K2.6$0.950$4.00$0.000$0.1602026-08-03
DeepSeek V4 Pro (0813)$1.32$3.96$0.000$0.0442026-08-27
GLM 5.1$1.40$4.40$0.000$0.2602026-08-03
GLM 5.3$1.40$4.40$0.000$0.2602026-08-29
GLM 5.2$1.40$4.40$0.000$0.1402026-08-03
Kimi K2.7 Codepriority$1.43$6.00$0.000$0.2852026-08-03
Kimi K2.6priority$1.50$6.00$0.000$0.2202026-08-03
DeepSeek V4 Pro (0813)priority$1.65$4.95$0.000$0.0552026-08-27
DeepSeek V4 Pro$1.74$3.48$0.000$0.1452026-08-03
GLM 5.3priority$1.75$5.50$0.000$0.3252026-08-29
GLM 5.2priority$1.75$5.50$0.000$0.1802026-08-03
Kimi K2.7 Code Fast$1.90$8.00$0.000$0.3802026-08-03
Kimi K2.6 Fast$2.00$8.00$0.000$0.3002026-08-03
Qwen 3.8 Max$2.00$6.00$0.000$0.2502026-08-19
GLM 5.1priority$2.10$6.60$0.000$0.3902026-08-03
GLM 5.2 Fast$2.10$6.60$0.000$0.2102026-08-03
GLM 5.2 Fast US$2.10$6.60$0.000$0.2102026-08-03
DeepSeek V4 Propriority$2.61$5.22$0.000$0.2182026-08-03
GLM 5.1 Fast$2.80$8.80$0.000$0.5202026-08-03
Kimi K3$3.00$15.00$0.000$0.3002026-08-03
Reserved Throughput Kimi K3$3.00$15.00$0.000$0.3002026-09-03
Qwen 3.8 Maxpriority$3.00$9.00$0.000$0.3752026-08-27
Kimi K3 US$3.30$16.50$0.000$0.3302026-08-03
Kimi K3priority$3.75$18.75$0.000$0.3752026-08-03
Reserved Throughput Kimi K3priority$3.75$18.75$0.000$0.3752026-09-03
Kimi K3 USpriority$4.13$20.63$0.000$0.4122026-08-03
Kimi K3 Fast$4.50$22.50$0.000$0.4502026-08-03

Z.AI

API pricing ↗

Subscription plans

  • GLM Coding Lite

    $18 / mo

    $18/mo list, shown at $12.6/mo with the current promotion. 10,000 credits/week. 5-hour and weekly usage caps. Works with ZCode, Claude Code and 20+ agent tools.

  • GLM Coding Pro

    $80 / mo

    $80/mo list, shown at $56/mo promotional. 6x Lite usage. Priority access to flagship models, curated MCP tools, faster generation.

  • GLM Coding Max

    $168 / mo

    $168/mo list, shown at $117.6/mo promotional. 14x Lite usage. First access to new flagship models, dedicated resources at peak times.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
glm-4.7-flash$0.000$0.000$0.000$0.0002026-08-03
glm-4.5-flash$0.000$0.000$0.000$0.0002026-08-03
GLM-4.7-Flash$0.000$0.000$0.000$0.0002026-08-04
GLM-4.5-Flash$0.000$0.000$0.000$0.0002026-08-04
GLM-4.6V-Flash$0.000$0.000$0.000$0.0002026-08-04
GLM-4.6V-FlashX$0.040$0.400$0.000$0.0042026-08-04
glm-4.7-flashx$0.070$0.400$0.000$0.0102026-08-03
GLM-4.7-FlashX$0.070$0.400$0.000$0.0102026-08-04
GLM-5.3-Flash$0.150$0.015$0.000$0.0752026-08-27
glm-4.5-air$0.200$1.10$0.000$0.0302026-08-03
GLM-4.5-Air$0.200$1.10$0.000$0.0302026-08-04
GLM-4.6V$0.300$0.900$0.000$0.0502026-08-04
glm-4.7$0.600$2.20$0.000$0.1102026-08-03
glm-4.6$0.600$2.20$0.000$0.1102026-08-03
glm-4.5$0.600$2.20$0.000$0.1102026-08-03
GLM-4.7$0.600$2.20$0.000$0.1102026-08-04
GLM-4.6$0.600$2.20$0.000$0.1102026-08-04
GLM-4.5$0.600$2.20$0.000$0.1102026-08-04
GLM-4.5V$0.600$1.80$0.000$0.1102026-08-04
glm-5$1.00$3.20$0.000$0.2002026-08-03
GLM-5$1.00$3.20$0.000$0.2002026-08-04
glm-4.5-airx$1.10$4.50$0.000$0.2202026-08-03
GLM-4.5-AirX$1.10$4.50$0.000$0.2202026-08-04
glm-5-turbo$1.20$4.00$0.000$0.2402026-08-03
glm-5.2$1.40$4.40$0.000$0.2602026-08-03
glm-5.1$1.40$4.40$0.000$0.2602026-08-03
GLM-5.3$1.40$4.40$0.000$0.2602026-08-19
GLM-5.2$1.40$4.40$0.000$0.2602026-08-04
GLM-5.1$1.40$4.40$0.000$0.2602026-08-04
glm-4.5-x$2.20$8.90$0.000$0.4502026-08-03
GLM-4.5-X$2.20$8.90$0.000$0.4502026-08-04

302.AI

API pricing ↗
ModelInputOutputCache writeCache readSince
gpt-5-nano$0.050$0.400$0.000$0.0002026-08-03
gpt-5-mini$0.250$2.00$0.000$0.0002026-08-03
gpt-5.4-mini$0.750$4.50$0.000$0.0002026-08-03
gpt-5.4-mini-2026-03-17$0.750$4.50$0.000$0.0002026-08-03
gpt-5$1.25$10.00$0.000$0.0002026-08-03
gpt-5-chat-latest$1.25$10.00$0.000$0.0002026-08-03
gpt-5-codex$1.25$10.00$0.000$0.0002026-08-03
gpt-5-codex-low$1.25$10.00$0.000$0.0002026-08-03
gpt-5-codex-medium$1.25$10.00$0.000$0.0002026-08-03
gpt-5-codex-high$1.25$10.00$0.000$0.0002026-08-03
gpt-5.2-codex$1.75$14.00$0.000$0.0002026-08-03
gpt-5.3-codex$1.75$14.00$0.000$0.0002026-08-03
gpt-5.3-chat-latest$1.75$14.00$0.000$0.0002026-08-03
claude-opus-4-6-thinking≤200K ctx$5.00$25.00$6.25$0.5002026-08-03
claude-opus-4-6≤200K ctx$5.00$25.00$6.25$0.5002026-08-03
claude-opus-4-5-20251101≤200K ctx$5.00$25.00$6.25$0.5002026-08-03
claude-opus-4-6-thinking>200K ctx$10.00$37.50$12.50$1.002026-08-03
claude-opus-4-6>200K ctx$10.00$37.50$12.50$1.002026-08-03

Baseten

API pricing ↗
ModelInputOutputCache writeCache readSince
GPT OSS 120B$0.100$0.500$0.000$0.0002026-08-03
DeepSeek-V4-Flash-0731$0.130$0.260$0.000$0.0282026-08-11
GLM-5.3-Flash$0.150$0.500$0.000$0.0302026-08-27
Inkling-Small$0.500$1.20$0.000$0.1002026-08-11
GLM 4.7$0.600$2.20$0.000$0.1202026-08-11
NVIDIA Nemotron 3 Ultra$0.600$2.40$0.000$0.1202026-08-11
Kimi K2.6$0.950$4.00$0.000$0.1602026-08-11
Kimi K2.7 Code$0.950$4.00$0.000$0.1602026-08-11
Inkling$1.00$4.05$0.000$0.1702026-08-11
DeepSeek V4 Pro 0813$1.32$3.96$0.000$0.1322026-08-27
GLM-5.3$1.40$4.40$0.000$0.1402026-08-29
GLM-5.2$1.40$4.40$0.000$0.1402026-08-11
DeepSeek V4 Pro$1.74$3.48$0.000$0.1452026-08-11
GLM-5.2 Fast$2.10$6.60$0.000$0.2102026-08-11
Kimi K3$3.00$15.00$0.000$0.3002026-08-11

Scaleway

API pricing ↗
ModelInputOutputCache writeCache readSince
qwen3-embedding-8b€0.100€0.000€0.000€0.0002026-08-03
bge-multilingual-gemma2€0.100€0.000€0.000€0.0002026-08-03
mistral-small-3.2-24b-instruct-2506€0.150€0.350€0.000€0.0002026-08-03
gpt-oss-120b€0.150€0.600€0.000€0.0002026-08-03
qwen3-coder-30b-a3b-instruct€0.200€0.800€0.000€0.0002026-08-03
pixtral-12b-2409€0.200€0.200€0.000€0.0002026-08-03
qwen3.6-35b-a3b€0.250€1.50€0.000€0.0002026-08-03
gemma-4-26b-a4b-it€0.250€0.500€0.000€0.0002026-08-03
holo2-30b-a3b€0.300€0.700€0.000€0.0002026-08-03
deepseek-v4-flash-0731€0.400€0.080€0.000€0.0002026-08-14
qwen3.5-397b-a17b€0.600€3.60€0.000€0.0002026-08-03
qwen3-235b-a22b-instruct-2507€0.750€2.25€0.000€0.0002026-08-03
llama-3.3-70b-instruct€0.900€0.900€0.000€0.0002026-08-03
mistral-medium-3.5-128b€1.50€7.50€0.000€0.0002026-08-03
glm-5.2€1.80€5.50€0.000€0.0002026-08-03

Chutes

API pricing ↗Plans ↗

Subscription plans

  • Plus

    $10 / mo

    Bundled daily quota plus 6% discount on pay-as-you-go token rates.

  • Pro

    $20 / mo

    Larger daily quota plus 10% discount on pay-as-you-go token rates.

  • Enterprise

    price on request

    Contact sales.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
unsloth/Mistral-Nemo-Instruct-2407-TEE$0.025$0.098$0.000$0.0002026-08-04
Nemotron-3-Nano-Omni-30B-TEE$0.025$0.098$0.000$0.0002026-08-04
Qwen/Qwen3-32B-TEE$0.104$0.416$0.000$0.0002026-08-04
google/gemma-4-31B-turbo-TEE$0.120$0.370$0.000$0.0002026-08-04
Qwen/Qwen3-235B-A22B-Thinking-2507-TEE$0.299$1.20$0.000$0.0002026-08-04
Qwen/Qwen3.6-27B-TEE$0.300$2.00$0.000$0.0002026-08-04
Qwen/Qwen3.8-27B-TEE$0.320$2.50$0.000$0.0002026-09-03
deepseek-ai/DeepSeek-V4-Flash-0731-TEE$0.440$1.32$0.000$0.0002026-08-26
Qwen/Qwen3.5-397B-A17B-TEE$0.450$3.00$0.000$0.0002026-08-04
moonshotai/Kimi-K2.6-TEE$0.580$3.40$0.000$0.0002026-08-05
zai-org/GLM-5.1-TEE$0.980$3.08$0.000$0.0002026-08-04
deepseek-ai/DeepSeek-V3.2-TEE$1.00$1.00$0.000$0.0002026-08-04
zai-org/GLM-5.2-TEE$1.25$3.95$0.000$0.0002026-08-04
moonshotai/Kimi-K3-TEE$3.00$15.00$0.000$0.0002026-08-04

Anthropic

API pricing ↗Plans ↗

Subscription plans

  • Free

    $0 / mo

    Chat on web/iOS/Android/desktop, code generation, web search, memory across conversations, extended thinking.

  • Pro

    $20 / mo

    $17/mo billed annually

    $17/mo on annual ($200 billed up front), $20 billed monthly. Includes Claude Code, Cowork, Design and Science.

  • Team (standard seat)

    $20 / mo / seat

    Teams of 2 to 150. $20/seat/month billed annually. SSO, central billing, enterprise search, no model training by default.

  • Max

    from $100 / mo

    'From $100' per month. Choose 5x or 20x more usage than Pro, higher output limits, priority access at busy times.

  • Team (premium seat)

    $100 / mo / seat

    5x more usage than a standard seat. $100/seat/month billed annually. Seat types can be mixed within a team.

  • Enterprise

    price on request

    Seat price PLUS usage at API rates. SCIM, audit logs, compliance API, 500k context on the default model.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
claude-haiku-3-5$0.800$4.00$1.00$0.0802026-08-02
claude-haiku-4-5$1.00$5.00$1.25$0.1002026-08-02
claude-sonnet-4-6$3.00$15.00$3.75$0.3002026-08-02
claude-sonnet-4-5$3.00$15.00$3.75$0.3002026-08-02
claude-opus-5$5.00$25.00$6.25$0.5002026-08-02
claude-opus-4-8$5.00$25.00$6.25$0.5002026-08-02
claude-opus-4-7$5.00$25.00$6.25$0.5002026-08-02
claude-opus-4-6$5.00$25.00$6.25$0.5002026-08-02
claude-opus-4-5$5.00$25.00$6.25$0.5002026-08-02
claude-fable-5$10.00$50.00$12.50$1.002026-08-02
claude-mythos-5$10.00$50.00$12.50$1.002026-08-02
claude-opus-4-1$15.00$75.00$18.75$1.502026-08-02

Google Gemini

API pricing ↗

Subscription plans

  • Google AI Plus (2 TB)

    $9.99 / mo

    2 TB storage. Gemini app at 2x the no-plan usage limits, plus the Flash Thinking model. Gemini in Gmail, Google Flow, Notebook.

  • Google AI Pro (5 TB)

    $19.99 / mo

    5 TB storage, shareable with 5 others. Gemini app at 4x the no-plan limits, Pro model, Deep Research. Includes YouTube Premium Lite. 1-month trial at $0.

  • Google AI Pro (10 TB)

    $49.99 / mo

    Same AI entitlement as the 5 TB Pro plan; 10 TB of storage.

  • Google AI Ultra (20 TB)

    $99.99 / mo

    20 TB storage. Gemini app at 5x the AI Pro limits plus Deep Think. YouTube Premium Individual, Google Home Premium Advanced.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
gemini-2.5-flash-lite$0.100$0.400$0.000$0.0102026-08-02
gemini-embedding-001$0.150$0.000$0.000$0.0002026-08-02
gemini-embedding-2$0.200$0.000$0.000$0.0002026-08-02
gemini-3.1-flash-lite$0.250$1.50$0.000$0.0252026-08-02
gemini-3.5-flash-lite$0.300$2.50$0.000$0.0302026-08-02
gemini-2.5-flash$0.300$2.50$0.000$0.0302026-08-02
gemini-3-flash-preview$0.500$3.00$0.000$0.0502026-08-02
gemini-3.6-flash$0.750$3.75$0.000$0.0752026-08-14
gemini-2.5-pro$1.25$10.00$0.000$0.1252026-08-02
gemini-3.5-flash$1.50$9.00$0.000$0.1502026-08-02

Groq

API pricing ↗
ModelInputOutputCache writeCache readSince
meta-llama/llama-prompt-guard-2-22m$0.030$0.030$0.000$0.0002026-08-10
meta-llama/llama-prompt-guard-2-86m$0.040$0.040$0.000$0.0002026-08-10
llama-3.1-8b-instant$0.050$0.080$0.000$0.0002026-08-03
openai/gpt-oss-20b$0.075$0.300$0.000$0.0002026-08-10
openai/gpt-oss-safeguard-20b$0.075$0.300$0.000$0.0002026-08-10
openai/gpt-oss-120b$0.150$0.600$0.000$0.0002026-08-10
llama-3.3-70b-versatile$0.590$0.790$0.000$0.0002026-08-03
qwen/qwen3.6-27b$0.600$3.00$0.000$0.0002026-08-10
qwen/qwen3.8-27b$0.800$4.00$0.000$0.0002026-08-27
moonshotai/kimi-k2-instruct-0905$1.00$3.00$0.000$0.5002026-08-03

Mistral AI

API pricing ↗

Subscription plans

  • Free

    $0 / mo

  • Pro

    $14.99 / mo

    Excluding taxes.

  • Team

    $24.99 / mo / seat

    Excluding taxes. Minimum 2 users.

  • Enterprise

    price on request

    Contact sales — no price published.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
ministral-3b-latest$0.100$0.100$0.000$0.0002026-08-02
mistral-small-latest$0.150$0.600$0.000$0.0002026-08-02
ministral-8b-latest$0.150$0.150$0.000$0.0002026-08-02
ministral-14b-latest$0.200$0.200$0.000$0.0002026-08-02
codestral-latest$0.300$0.900$0.000$0.0002026-08-02
mistral-large-latest$0.500$1.50$0.000$0.0002026-08-02
mistral-medium-latest$1.50$7.50$0.000$0.0002026-08-02

MiniMax

API pricing ↗Plans ↗
ModelInputOutputCache writeCache readSince
MiniMax-M2.7$0.300$1.20$0.375$0.0602026-08-03
MiniMax-M3≤512K ctx$0.300$1.20$0.000$0.0602026-08-03
MiniMax-M3≤512K ctxpriority$0.450$1.80$0.000$0.0902026-08-11
MiniMax-M3>512K ctx$0.600$2.40$0.000$0.1202026-08-03
MiniMax-M2.7-highspeed$0.600$2.40$0.375$0.0602026-08-03

Cerebras

API pricing ↗Plans ↗

Subscription plans

  • Free Trial

    $0 / mo

    $5 in free credits on sign-up. Access to all Cerebras-powered models.

  • Developer

    from $10 / mo

    Self-serve payment 'starting at just $10'; 10x higher rate limits than free.

  • Cerebras Code Pro

    $50 / mo

    Up to 24M tokens/day. SOLD OUT as of 2026-08-03 — not purchasable.

  • Cerebras Code Max

    $200 / mo

    Up to 120M tokens/day. SOLD OUT as of 2026-08-03 — not purchasable.

  • Enterprise

    price on request

    Highest rate limits, custom weights, dedicated queue priority. Contact sales.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
gpt-oss-120b$0.350$0.750$0.000$0.0002026-08-03
gemma-4-31b$0.990$1.49$0.000$0.0002026-08-03
Qwen 3.8 27B$0.990$1.49$0.000$0.0002026-09-04
zai-glm-4.7$2.25$2.75$0.000$0.0002026-08-03

AWS Bedrock

API pricing ↗
ModelInputOutputCache writeCache readSince
anthropic.claude-3-5-sonnetbatch$3.00$15.00$0.000$0.0002026-08-03
anthropic.claude-3-5-sonnet-v2batch$3.00$15.00$0.000$0.0002026-08-03
anthropic.claude-3-5-sonnet$6.00$30.00$0.000$0.0002026-08-03
anthropic.claude-3-5-sonnet-v2$6.00$30.00$0.000$0.0002026-08-03

Moonshot AI

API pricing ↗
ModelInputOutputCache writeCache readSince
kimi-k2.7-code$0.950$4.00$0.000$0.1902026-08-03
kimi-k2.6$0.950$4.00$0.000$0.1602026-08-03
kimi-k2.7-code-highspeed$1.90$8.00$0.000$0.3802026-08-03
kimi-k3$3.00$15.00$0.000$0.3002026-08-03

Perplexity

API pricing ↗
ModelInputOutputCache writeCache readSince
sonar$1.00$1.00$0.000$0.0002026-08-03
sonar-reasoning-pro$2.00$8.00$0.000$0.0002026-08-03
sonar-deep-research$2.00$8.00$0.000$0.0002026-08-03
sonar-pro$3.00$15.00$0.000$0.0002026-08-03

OpenAI

API pricing ↗Plans ↗

Subscription plans

  • Free

    $0 / mo

  • Go

    $8 / mo

    This plan may include ads.

  • Plus

    $20 / mo

  • Business

    $25 / mo / seat

    $20/mo billed annually

    2+ users. $20/user/mo billed annually, $25 billed monthly.

  • Pro

    from $100 / mo

    5x or 20x more usage. The page prints a floor, not a rate.

  • Enterprise

    price on request

    Contact sales — no price published.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
gpt-5.6-luna$0.200$1.20$0.250$0.0202026-08-02
gpt-5.6-terra$2.00$12.00$2.50$0.2002026-08-02
gpt-5.6-sol$4.00$20.00$5.00$0.4002026-08-22

STACKIT

API pricing ↗
ModelInputOutputCache writeCache readSince
Model Serving-llm-standard-EU01€0.150€0.250€0.000€0.0002026-08-04
Model Serving-llm-plus-EU01€0.450€0.650€0.000€0.0002026-08-04
Model Serving-llm-premium-EU01€1.50€1.75€0.000€0.0002026-08-04

DeepSeek

API pricing ↗
ModelInputOutputCache writeCache readSince
deepseek-v4-flash$0.140$0.280$0.000$0.0032026-08-02
deepseek-v4-pro$0.435$0.870$0.000$0.0042026-08-02

xAI

API pricing ↗

Subscription plans

  • SuperGrok

    $30 / mo

  • SuperGrok Heavy

    $300 / mo

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

ModelInputOutputCache writeCache readSince
grok-4.5$2.00$6.00$0.000$0.3002026-08-02

Cursor

API pricing ↗Plans ↗

Subscription plans

  • Hobby

    $0 / mo

    Limited Agent requests; access to Composer.

  • Pro

    $20 / mo

    Extended Agent limits, frontier models, cloud agents, Bugbot.

  • Teams Standard

    $40 / mo / seat

    Per user/month. Centralised billing, SAML/OIDC SSO, usage analytics, team privacy mode.

  • Pro+

    price on request

    3x Pro limits on Agent. NO PRICE PRINTED on the pricing page.

  • Ultra

    price on request

    20x Pro limits on Agent. NO PRICE PRINTED.

  • Teams Premium

    price on request

    5x Standard limits on Agent. NO PRICE PRINTED.

  • Enterprise

    price on request

    Pooled usage, invoice/PO billing, SCIM, audit logs. Contact sales.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

This provider sells access by subscription. Any per-token rates it publishes separately are not yet ingested, so metered turns are reported as UNPRICED rather than billed at zero.

GitHub Copilot

API pricing ↗Plans ↗

Subscription plans

  • Free

    $0 / mo / seat

    Limited chat and agent usage. Additional credits cannot be purchased.

  • Pro

    $10 / mo / seat

    Includes $15/mo of GitHub AI Credits. Additional credits purchasable.

  • Pro+

    $39 / mo / seat

    Includes $70/mo of GitHub AI Credits.

  • Max

    $100 / mo / seat

    Includes $200/mo of GitHub AI Credits.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

This provider sells access by subscription. Any per-token rates it publishes separately are not yet ingested, so metered turns are reported as UNPRICED rather than billed at zero.

Hugging Face

API pricing ↗Plans ↗

Subscription plans

  • Free

    $0 / mo

    $0.10/mo of inference credits ('subject to change'). Pay-as-you-go beyond that requires purchasing credits.

  • PRO Account

    $9 / mo

    $2.00/mo of included inference credits; 20x included inference credits, 8x ZeroGPU quota, 10x private storage.

  • Team

    $20 / mo / seat

    $20/month per user. $2.00/mo of inference credits PER SEAT, pooled across the org. SSO (SAML & OIDC), audit logs, resource groups.

  • Enterprise

    $50 / mo / seat

    $50/month per user. All Team benefits plus SCIM provisioning, managed billing with annual commitments, dedicated support.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

This provider sells access by subscription. Any per-token rates it publishes separately are not yet ingested, so metered turns are reported as UNPRICED rather than billed at zero.

Antigravity

API pricing ↗Plans ↗

Subscription plans

  • Individual (Free)

    $0 / mo

    Gemini 3.5 Flash / 3.1 Pro / 3 Flash, Claude Sonnet & Opus 4.6, gpt-oss-120b. Unlimited tab completions; basic weekly rate limits.

  • Google AI Pro

    price on request

    More generous rate limits, flexible AI credit pool. NO PRICE on the Antigravity pricing page.

  • Google AI Ultra

    price on request

    Highest rate limits. NO PRICE on the Antigravity pricing page.

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

This provider sells access by subscription. Any per-token rates it publishes separately are not yet ingested, so metered turns are reported as UNPRICED rather than billed at zero.

Ollama

runs locally — no per-token fee
API pricing ↗Plans ↗

Subscription plans

  • Free

    $0 / mo

    Unlimited on your own hardware; light cloud usage.

  • Pro

    $20 / mo

    $16.67/mo billed annually

  • Max

    $20 / mo

    $16.67/mo billed annually

A subscription is a flat recurring fee, not a rate per token — it is never folded into the per-token figures below.

Models run on your own hardware, so there is no per-token cost to publish.

LM Studio

runs locally — no per-token fee
API pricing ↗

Models run on your own hardware, so there is no per-token cost to publish.

Nebius

no verified prices yet
API pricing ↗

Anvil can route to this provider, but we have not ingested verified prices for it yet. Turns on these models are reported as UNPRICED rather than billed at zero.

NVIDIA NIM

no verified prices yet
API pricing ↗

Anvil can route to this provider, but we have not ingested verified prices for it yet. Turns on these models are reported as UNPRICED rather than billed at zero.

OpenCode Go

no verified prices yet
API pricing ↗

Anvil can route to this provider, but we have not ingested verified prices for it yet. Turns on these models are reported as UNPRICED rather than billed at zero.

How the estimate is built

Tokens are measured, not guessed

Every provider returns exact input, output, cache-write and cache-read token counts with each response. Anvil records those verbatim in a per-session ledger. Nothing here is sampled or extrapolated — the token counts are ground truth.

The rate is keyed on the provider that served the turn

Not on the model's name. Azure, Bedrock and OpenRouter all serve models called gpt-* and claude-*, at their own prices. Pricing by name alone silently applied the origin vendor's rate to a reseller's traffic, so the key is (provider, model, timestamp).

A turn is priced at the rate in force when it ran

Rows carry an effective-from date and are appended, never edited. A turn from three months ago keeps pricing at the rate that applied then, even after a change. That is also what makes the chart above a real history rather than today's number repeated backwards.

Multipliers are applied, not averaged

Cache writes cost 1.25x base input for a 5-minute TTL and 2x for a 1-hour TTL; cache reads cost 0.1x. Batch is 50% off. Anvil requests a 1-hour cache, so its writes are the 2x kind — pricing them at 1.25x under-counts every cached turn.

Unknown is reported as unknown

Anvil supports 35 providers. Where we have no verified price, the turn is marked UNPRICED and the report says its totals are an under-count, naming the models involved. It is never quietly billed at zero — a zero that means 'we did not know' is indistinguishable from a zero that means 'this was free'.

A subscription is not a per-token rate

A Claude Max or ChatGPT Pro seat costs the same whether you run one turn or ten thousand. For those turns the figure shown is what the same tokens WOULD have cost on the metered API — useful for comparison, but not what you paid.

What this page does not cover

Provider pricing is more structured than one number per model. These are the axes the table above deliberately does not fold in, because averaging them would produce a figure that is wrong for every real request:

  • Context tiers: Gemini, xAI and OpenAI charge roughly 2x above a 200k-token prompt. Anthropic is flat to 1M. Where a model has tiers, the standard tier is shown.
  • Service tiers: Batch (50% off), Flex, and Fast/Priority (up to 2x) are published separately by most providers. The standard tier is shown here.
  • Non-token units: video is billed per second, music per song, transcription per minute, search grounding per 1,000 requests, and Managed Agents per session-hour. Those are outside a per-million-token table.
  • Regional endpoints and data-residency routing carry a ~10% premium at several providers.
  • Anthropic's Claude 4.7 and later use a newer tokenizer that produces roughly 30% more tokens for the same text — same price per token, more tokens.

Where these numbers come from

Rates are pulled daily from each provider's own published pricing page and folded into an append-only history — a change closes the previous row and opens a new one, so nothing is overwritten. Anvil reads the same data from /api/pricing, and carries a vendored snapshot so an offline or air-gapped host still prices correctly. Every provider links to its source above.

Model pricing | AnvilHub