LLM Model Prices (per million tokens)

Thanks to the LiteLLM project, the model provider websites and APIs and random sources online for the source data. Most benchmark data is from the Epoch AI benchmarking dashboard, provided under a Creative Commons license by Epoch AI, but some data is from other sources. The Aider Polyglot data is from the Aider website. Always check the original source for the most up-to-date information as there may be errors in the data (some sources are a bit rough) and benchmark score matching is a bit fuzzy.

$
Showing 1819 models (875 rows displayed)
Provider ⬍Model ⬍Max Input Tokens ⬍Input Token Price ⬍Output Token Price ⬍GPQA (Diamond) ⬍MATH (Level 5) ⬍OTIS Mock AIME 24-25 ⬍Aider Polyglot ⬍
vertex_ai-language-models, vertex_ai, gemini, openrouter ▶gemini-3-pro-preview (4 endpoints)1048k$2.00
>200k: $4.00
$12.00
>200k: $18.00
92.6%–91.4%–
openrouter, azure, openai ▶gpt-5.1 (8 endpoints)272k–400k$1.25–$1.38$10.00–$11.0087.6%–88.6%–
vercel_ai_gateway, xai, openrouter, azure_ai, oci ▶grok-4 (7 endpoints)128k–256k$3.00–$5.50
>128k: $6.00
$0.15–$27.50
>128k: $30.00
87%–84%79.6%
openrouter, azure, openai ▶gpt-5 (7 endpoints)272k–400k$1.25–$1.375$10.00–$11.0086.2%98.1%91.4%88%
vertex_ai-language-models, gemini, openrouter, vercel_ai_gateway, deepinfra ▶gemini-2.5-pro (5 endpoints)1000k–1048k$1.25–$2.50
>200k: $2.50
$10.00
>200k: $15.00
85.3%–84.2%–
openrouter, vertex_ai-language-models, gemini ▶gemini-2.5-pro-preview (7 endpoints)1048k$1.25
>200k: $2.50
$10.00
>200k: $15.00
84.8%95.9%–83.1%
moonshotmoonshot/​kimi-​k2-​thinking-​turboℹ️
kimi-​k2-​thinking-​turbo
262k$1.15$8.0084.2%–83.1%–
vertex_ai-language-models, gemini ▶gemini-2.5-pro-exp-03-25 (3 endpoints)1048k$0.00–$1.25
>200k: $0.00–$2.50
$0.00–$10.00
>200k: $0.00–$15.00
83.8%–––
azure, openai, vercel_ai_gateway, openrouter ▶o3 (7 endpoints)200k$2.00–$2.20$8.00–$8.8081.8%97.8%83.9%81.3%
vertex_ai-anthropic_models, openrouter, anthropic, bedrock_converse ▶claude-opus-4-5 (7 endpoints)200k$5.00$25.0080.7%–48.1%–
azure, openai, vercel_ai_gateway, openrouter ▶o4-mini (8 endpoints)200k$1.10–$1.21$4.40–$4.8479.6%97.8%81.7%72%
azure, openai, vercel_ai_gateway, openrouter ▶o3-mini (9 endpoints)200k$1.10–$1.21$4.40–$4.8477%96.5%76.9%60.4%
azure, openai, vercel_ai_gateway, openrouter ▶o1 (8 endpoints)200k$15.00–$16.50$60.00–$66.0076.8%94.7%73.3%61.7%
lambda, openrouter, deepinfra, wandb, fireworks_ai, lambda_ai, hyperbolic, vercel_ai_gateway, azure_ai, bedrock_converse, together_ai, deepseek, sambanova ▶deepseek-r1 (18 endpoints)32k–164k$0.20–$135,000.00$0.25–$540,000.0076.3%96.6%66.4%71.4%
xai, openrouter ▶grok-3-mini-beta (3 endpoints)131k$0.30$0.5076.3%90.9%77.8%49.3%
openrouter, azure, openai ▶gpt-5-mini (7 endpoints)272k–400k$0.25–$0.275$2.00–$2.2075%97.8%86.7%–
openrouter, azure_ai, vertex_ai-anthropic_models, anthropic, bedrock_converse, bedrock ▶claude-sonnet-4.5 (14 endpoints)200k–1000k$3.00–$3.30
>200k: $6.00–$6.60
$15.00–$16.50
>200k: $22.50–$24.75
73.7%–35.6%–
azure_ai, vertex_ai-anthropic_models, openrouter, anthropic, bedrock_converse ▶claude-opus-4-1 (8 endpoints)200k$15.00$75.0073.2%–40%–
openrouter, deepinfra, fireworks_ai, groq, cerebras, sambanova, wandb, ovhcloud, together_ai, watsonx ▶gpt-oss-120b (11 endpoints)8k–131k$0.00–$15,000.00$0.00–$60,000.0070.8%–71%41.8%
openrouter, bedrock_converse, fireworks_ai, hyperbolic, deepinfra ▶qwen3-235b-a22b (7 endpoints)40k–262k$0.00–$2.00$0.00–$2.0070.7%68.9%––
openrouter, azure, openai ▶gpt-5-nano (7 endpoints)272k–400k$0.05–$0.055$0.40–$0.4469.4%95.2%81.1%–
vertex_ai-anthropic_models, openrouter, anthropic, bedrock_converse ▶claude-opus-4 (7 endpoints)200k$15.00$75.0069.2%85%42.2%72%
openrouter, deepinfra, fireworks_ai, wandb, lambda_ai, vercel_ai_gateway, azure_ai, deepseek, together_ai, hyperbolic, sambanova ▶deepseek-v3 (17 endpoints)32k–163k$0.20–$114,000.00$0.20–$275,000.0067.6%75.5%37.8%55.1%
xai, openrouter ▶grok-3-beta (3 endpoints)131k$3.00$15.0067.6%88.7%55.6%53.3%
openrouter, lambda, vercel_ai_gateway ▶llama-4-maverick (3 endpoints)131k–1048k$0.15–$0.20$0.6067%73%20.6%15.6%
azure, openai, vercel_ai_gateway, openrouter ▶gpt-4.1 (7 endpoints)1047k$2.00–$2.20$8.00–$8.8066.9%83%38.3%52.4%
vertex_ai-anthropic_models, openrouter, anthropic, bedrock_converse ▶claude-sonnet-4 (9 endpoints)1000k$3.00
>200k: $6.00
$15.00
>200k: $22.50
66.7%84.4%28.9%61.3%
vercel_ai_gateway, openrouter, anthropic, vertex_ai-anthropic_models, bedrock_converse, bedrock, deepinfra ▶claude-3.7-sonnet (12 endpoints)200k$3.00–$3.60$15.00–$18.0066%68.2%21.9%64.9%
azure, openai, vercel_ai_gateway, openrouter ▶gpt-4.1-mini (7 endpoints)1047k$0.40–$0.44$1.60–$1.7665.8%87.3%44.7%32.4%
dashscopedashscope/​qwq-​plusℹ️
qwq-​plus
98k$0.80$2.4065.4%–––
gemini, openrouter, vertex_ai-language-models, deepinfra ▶gemini-2.0-flash-001 (4 endpoints)1000k–1048k$0.10–$0.15$0.40–$0.6064.1%82.2%31.1%–
azure ▶o1-mini (4 endpoints)128k$1.10–$1.21$4.40–$4.8462.4%89.2%46.9%32.9%
azure_ai, openrouter, bedrock_converse, anthropic, vertex_ai-anthropic_models ▶claude-haiku-4-5 (12 endpoints)200k$1.00–$1.10$5.00–$5.5060.5%86.9%35.8%–
azure_ai, mistral, watsonx ▶mistral-medium-latest (6 endpoints)32k–131k$0.40–$3.00$2.00–$10.0059.5%81.6%32.2%–
vertex_ai-language-models, gemini ▶gemini-1.5-pro-002 (2 endpoints)2097k$1.25–$3.50
>128k: $2.50–$7.00
$5.00–$10.50
>128k: $10.00–$21.00
57.2%70.4%23.1%–
vertex_ai-language-models, gemini ▶gemini-2.0-flash-thinking-exp (4 endpoints)1048k$0.00
>128k: $0.00
$0.00
>128k: $0.00
57.1%–57.8%18.2%
openrouter, deepinfra, azure_ai ▶phi-4 (3 endpoints)16k$0.06–$0.125$0.14–$0.5056.1%64.9%13.8%–
openrouter, deepinfra, sambanova, vercel_ai_gateway, fireworks_ai, ovhcloud, groq, nscale, gradient_ai ▶deepseek-r1-distill-llama-70b (9 endpoints)128k–131k$0.03–$0.99$0.13–$1.4055.7%89.9%51.4%–
vercel_ai_gateway, vertex_ai-anthropic_models, bedrock, anthropic, openrouter ▶claude-3.5-sonnet (12 endpoints)200k$3.00–$6.00$15.00–$30.0054%51.7%6.53%–
vercel_ai_gateway, xai ▶grok-2 (4 endpoints)131k$2.00$10.0053.8%63.5%11.5%–
lambda, openrouter, vercel_ai_gateway ▶llama-4-scout (3 endpoints)131k–1000k$0.08–$0.10$0.3051.8%62.3%7.78%–
azure ▶o1-preview (4 endpoints)128k$15.00–$16.50$60.00–$66.0050.3%81.6%31.1%–
azure, openai, vercel_ai_gateway, openrouter ▶gpt-4o (21 endpoints)128k$2.50–$5.00$10.00–$15.0049.2%53.3%6.39%23.1%
hyperbolic, openrouter, deepinfra ▶qwen2.5-72b-instruct (3 endpoints)32k–131k$0.07–$0.12$0.26–$0.3949.1%63.2%8.06%–
azure, openai, vercel_ai_gateway, openrouter ▶gpt-4.1-nano (7 endpoints)1047k$0.10–$0.11$0.40–$0.4448.9%70%28.9%8.9%
gemini, openrouter, deepinfra, fireworks_ai, bedrock_converse ▶gemma-3-27b-it (6 endpoints)96k–131k$0.00–$0.90
>128k: $0.00
$0.00–$0.90
>128k: $0.00
48.9%74%19.7%4.9%
vercel_ai_gateway, bedrock_converse, mistral ▶magistral-small (4 endpoints)40k–128k$0.50$1.5048.4%–30%–
openrouter, dashscope ▶qwen-plus (6 endpoints)129k–1000k$0.40$1.2048.1%65.3%17.8%–
azure_ai, vertex_ai-mistral_models, mistral, vercel_ai_gateway, watsonx, bedrock ▶mistral-small (8 endpoints)32k–128k$0.10–$1.00$0.30–$3.0047.5%46.8%5.83%–
fireworks_ai, openrouter, nscale ▶deepseek-r1-distill-qwen-14b (3 endpoints)32k–131k$0.07–$0.20$0.07–$0.2044.7%87.1%––
azure, openai, vercel_ai_gateway, openrouter ▶gpt-4o-mini (10 endpoints)128k$0.15–$0.165$0.60–$0.6637.7%52.6%6.94%3.6%
openai, openrouter ▶chatgpt-4o-latest (2 endpoints)128k$5.00$15.00–––45.3%
vercel_ai_gateway, mistral, openrouter, vertex_ai-mistral_models, codestral ▶codestral (9 endpoints)32k–256k$0.00–$1.00$0.00–$3.00–––11.1%
openrouter deepseek/​deepseek-​v3.2-​exp
deepseek-​v3.2-​exp
163k$0.21$0.32–––74.2%
vertex_ai-language-models, gemini, vercel_ai_gateway ▶gemini-2.0-flash (3 endpoints)1048k$0.10–$0.15$0.40–$0.60––––
vertex_ai-language-models, gemini, vercel_ai_gateway ▶gemini-2.0-flash-lite (3 endpoints)1048k$0.075$0.30––––
vertex_ai-language-models, gemini, openrouter ▶gemini-2.5-flash-preview-04-17 (7 endpoints)1048k$0.15–$0.30$0.60–$2.50––73.1%55.1%
azure azure/​gpt-​4.5-​preview
gpt-​4.5-​preview
128k$75.00$150.00–––44.9%
openrouter, vercel_ai_gateway ▶kimi-k2 (4 endpoints)32k–262k$0.00–$0.55$0.00–$2.20–––59.1%
openrouter openai/​o1-​pro
o1-​pro
200k$150.00$600.00––––
openrouter openai/​o3-​pro
o3-​pro
200k$20.00$80.00–––84.9%
openrouter, watsonx, mistral, vertex_ai-mistral_models, azure_ai, bedrock, vercel_ai_gateway, azure ▶mistral-large (22 endpoints)32k–262k$0.50–$10.40$1.50–$31.2051.3%50.3%8.47%–
openrouter, bedrock, oci ▶llama-3.1-405b-instruct (4 endpoints)128k–130k$3.50–$10.68$3.50–$16.0050.9%49.8%9.72%–
openrouter, hyperbolic, deepinfra, azure_ai, watsonx, oci, bedrock_converse, wandb, nscale, gradient_ai ▶llama-3.3-70b-instruct (12 endpoints)128k–131k$0.00–$71,000.00$0.00–$71,000.0047.4%41.6%5.14%–
vertex_ai-language-models, gemini ▶gemini-1.5-flash-002 (2 endpoints)1048k$0.075
>128k: $0.15–$1.00
$0.30
>128k: $0.60
47.3%61.9%16.3%–
vercel_ai_gateway, vertex_ai-anthropic_models, openrouter, anthropic, bedrock ▶claude-3-opus (9 endpoints)200k$15.00$75.0047.2%37.5%4.72%–
azure, openai, vercel_ai_gateway, openrouter ▶gpt-4-turbo (6 endpoints)128k$10.00$30.0046.6%46.7%6.67%–
gemini, vertex_ai-language-models ▶gemini-1.5-pro-001 (2 endpoints)1000k–2097k$1.25–$3.50
>128k: $2.50–$7.00
$5.00–$10.50
>128k: $10.00–$21.00
45.9%40.7%6.81%–
openrouter, perplexity, bedrock ▶llama-3.1-70b-instruct (4 endpoints)128k–131k$0.40–$1.00$0.40–$1.0044.2%36.7%3.61%–
deepinfra, openrouter ▶wizardlm-2-8x22b (2 endpoints)65k$0.48$0.4843.4%25.7%––
azure, openai, openrouter ▶gpt-4-1106-preview (3 endpoints)128k$10.00$30.0042.4%40%––
azure, openai ▶gpt-4-0125-preview (2 endpoints)128k$10.00$30.0042.3%35.4%––
openrouter, dashscope ▶qwen-turbo (5 endpoints)129k–1000k$0.05$0.2041.8%56.2%6.11%–
oci, watsonx, azure_ai, openrouter ▶llama-3.2-90b-vision-instruct (4 endpoints)32k–128k$0.35–$2.04$0.40–$2.0441%39.4%2.64%–
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2-​72b-​instructℹ️
qwen2-​72b-​instruct
32k$0.90$0.9040.8%39.1%––
vertex_ai-anthropic_models, bedrock ▶claude-3-sonnet (6 endpoints)200k$3.00$15.0040.6%18.2%2.5%–
hyperbolic, anyscale, azure_ai ▶meta-llama-3-70b-instruct (3 endpoints)8k–131k$0.12–$1.10$0.30–$1.0040.6%22.6%4.31%–
gemini, vertex_ai-language-models ▶gemini-1.5-flash-001 (2 endpoints)1000k–1048k$0.075
>128k: $0.15–$1.00
$0.30
>128k: $0.60
40.4%25.1%3.89%–
bedrock, vercel_ai_gateway, openrouter, anthropic, vertex_ai-anthropic_models ▶claude-3.5-haiku (11 endpoints)200k$0.25–$1.00$1.25–$5.0038.1%46.4%4.31%28%
openrouter google/​gemma-​2-​27b-​it
gemma-​2-​27b-​it
8k$0.65$0.6536.5%27.9%1.39%–
vercel_ai_gateway, vertex_ai-anthropic_models, openrouter, anthropic, bedrock ▶claude-3-haiku (11 endpoints)200k$0.25–$0.30$1.25–$1.5036.3%14.9%1.81%–
azure, openai, openrouter ▶gpt-4 (6 endpoints)8k–8k$30.00$60.0035.7%23%1.11%–
mistral mistral/​open-​mixtral-​8x22b
open-​mixtral-​8x22b
65k$2.00$6.0034.1%24.2%––
vertex_ai-language-models gemini-​1.0-​pro-​001ℹ️32k$0.50$1.5034%11.2%1.11%–
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​dbrx-​instruct
dbrx-​instruct
32k$1.20$1.2032.9%11.7%––
deepinfra, bedrock, ovhcloud, anyscale, replicate, together_ai ▶mixtral-8x7b-instruct-v0.1 (9 endpoints)4k–32k$0.15–$0.63$0.15–$1.0030.6%9.29%––
mistral ▶open-mistral-nemo (2 endpoints)128k$0.30$0.3029.9%10.8%––
mistral mistral/​open-​mixtral-​8x7b
open-​mixtral-​8x7b
32k$0.70$0.7029.8%9.95%––
openai, vercel_ai_gateway, openrouter, azure ▶gpt-3.5-turbo (13 endpoints)4k–16k$0.20–$1.50$1.50–$2.0028%15.9%––
azure_ai, openrouter ▶phi-3-medium-128k-instruct (2 endpoints)128k$0.17–$1.00$0.68–$1.0027.6%17.6%––
openrouter, groq, fireworks_ai ▶gemma-2-9b-it (3 endpoints)8k$0.03–$0.20$0.09–$0.2027.5%21%0.556%–
replicate, perplexity, anyscale ▶llama-2-70b-chat (3 endpoints)4k$0.65–$1.00$1.00–$2.8026.3%3.29%0%–
deepinfra, anyscale ▶meta-llama-3-8b-instruct (2 endpoints)8k$0.03–$0.15$0.06–$0.1526.1%6.13%0.833%–
openrouter, lambda_ai, perplexity, lambda, ovhcloud, bedrock, wandb, nscale ▶llama-3.1-8b-instruct (9 endpoints)128k–131k$0.02–$22,000.00$0.03–$22,000.0025.9%22.9%2.5%–
deepinfra, azure_ai, hyperbolic, sambanova, friendliai ▶meta-llama-3.1-8b-instruct (5 endpoints)8k–131k$0.03–$0.30$0.05–$0.6125.9%22.9%2.5%–
ovhcloud, openrouter ▶mistral-7b-instruct-v0.3 (2 endpoints)32k–127k$0.10–$0.20$0.10–$0.2015.2%3.6%––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​yi-​34b-​chat
yi-​34b-​chat
4k$0.90$0.9014.7%5.15%––
mistral mistral/​open-​mistral-​7b
open-​mistral-​7b
32k$0.25$0.2513.2%3.68%––
openrouter aion-​labs/​aion-​1.0
aion-​1.0
131k$4.00$8.00––––
openrouter aion-​labs/​aion-​1.0-​mini
aion-​1.0-​mini
131k$0.70$1.40––––
openrouter aion-​labs/​aion-​rp-​llama-​3.1-​8b
aion-​rp-​llama-​3.1-​8b
32k$0.20$0.20––––
publicaipublicai/​BSC-​LT/​ALIA-​40b-​instruct_Q8_0ℹ️
alia-​40b-​instruct_q8_0
8k$0.00$0.00––––
watsonx watsonx/​sdaia/​allam-​1-​13b-​instruct
allam-​1-​13b-​instruct
8k$1.80$1.80––––
gradient_aigradient_ai/​anthropic-​claude-​3.5-​haiku
anthropic-​claude-​3.5-​haiku
–$0.80$4.00––––
gradient_aigradient_ai/​anthropic-​claude-​3.5-​sonnet
anthropic-​claude-​3.5-​sonnet
–$3.00$15.00––––
gradient_aigradient_ai/​anthropic-​claude-​3.7-​sonnet
anthropic-​claude-​3.7-​sonnet
–$3.00$15.00––––
gradient_aigradient_ai/​anthropic-​claude-​3-​opus
anthropic-​claude-​3-​opus
–$15.00$75.00––––
openrouter thedrummer/​anubis-​70b-​v1.1
anubis-​70b-​v1.1
131k$0.75$1.00––––
publicaipublicai/​swiss-​ai/​apertus-​70b-​instructℹ️
apertus-​70b-​instruct
8k$0.00$0.00––––
publicaipublicai/​swiss-​ai/​apertus-​8b-​instructℹ️
apertus-​8b-​instruct
8k$0.00$0.00––––
vertex_ai-chat-models, palm ▶chat-bison (2 endpoints)8k$0.125$0.125––––
vertex_ai-chat-models, palm ▶chat-bison@001 (2 endpoints)8k$0.125$0.125––––
vertex_ai-chat-models chat-​bison@002ℹ️8k$0.125$0.125––––
vertex_ai-chat-models chat-​bison-​32kℹ️32k$0.125$0.125––––
vertex_ai-chat-models chat-​bison-​32k@002ℹ️32k$0.125$0.125––––
nlp_cloud chatdolphin16k$0.50$0.50––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​chronos-​hermes-​13b-​v2
chronos-​hermes-​13b-​v2
4k$0.20$0.20––––
bedrock ▶claude-3-5-sonnet-20241022-v2.0 (4 endpoints)200k$3.00$15.00––––
vertex_ai-anthropic_models ▶claude-3-5-sonnet-v2 (2 endpoints)200k$3.00$15.00––––
vercel_ai_gateway, deepinfra ▶claude-4-opus (2 endpoints)200k$15.00–$16.50$75.00–$82.50––––
vercel_ai_gateway, deepinfra ▶claude-4-sonnet (2 endpoints)200k$3.00–$3.30$15.00–$16.50––––
bedrock ▶claude-instant-v1 (5 endpoints)100k$0.80–$2.48$2.40–$8.38––––
bedrock ▶claude-v1 (5 endpoints)100k$8.00$24.00––––
bedrock ▶claude-v2.1 (5 endpoints)100k$8.00$24.00––––
vertex_ai-code-text-models code-​bisonℹ️6k$0.125$0.125––––
vertex_ai-code-chat-models codechat-​bisonℹ️6k$0.125$0.125––––
vertex_ai-code-chat-models codechat-​bison@001ℹ️6k$0.125$0.125––––
vertex_ai-code-chat-models codechat-​bison@002ℹ️6k$0.125$0.125––––
vertex_ai-code-chat-models codechat-​bison-​32kℹ️32k$0.125$0.125––––
vertex_ai-code-chat-models codechat-​bison-​32k@002ℹ️32k$0.125$0.125––––
vertex_ai-code-chat-models codechat-​bison@latestℹ️6k$0.125$0.125––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​codegemma-​2b
codegemma-​2b
8k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​codegemma-​7b
codegemma-​7b
8k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​13b
code-​llama-​13b
16k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​13b-​instruct
code-​llama-​13b-​instruct
16k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​13b-​python
code-​llama-​13b-​python
16k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​34b
code-​llama-​34b
16k$0.90$0.90––––
perplexity, fireworks_ai, anyscale ▶codellama-34b-instruct (3 endpoints)4k–16k$0.35–$1.00$0.90–$1.40––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​34b-​python
code-​llama-​34b-​python
16k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​70b
code-​llama-​70b
4k$0.90$0.90––––
perplexity, fireworks_ai, anyscale ▶codellama-70b-instruct (3 endpoints)4k–16k$0.70–$1.00$0.90–$2.80––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​70b-​python
code-​llama-​70b-​python
4k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​7b
code-​llama-​7b
16k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​7b-​instruct
code-​llama-​7b-​instruct
16k$0.20$0.20––––
cloudflare cloudflare/​@hf/​thebloke/​codellama-​7b-​instruct-​awq
codellama-​7b-​instruct-​awq
4k$1.923$1.923––––
openrouter alfredpros/​codellama-​7b-​instruct-​solidity
codellama-​7b-​instruct-​solidity
4k$0.80$1.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​llama-​7b-​python
code-​llama-​7b-​python
16k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​code-​qwen-​1p5-​7b
code-​qwen-​1p5-​7b
65k$0.20$0.20––––
openrouter arcee-​ai/​coder-​large
coder-​large
32k$0.50$0.80––––
vertex_ai-mistral_models ▶codestral-2 (2 endpoints)128k$0.30$0.90––––
vertex_ai-mistral_models ▶codestral-2@001 (2 endpoints)128k$0.30$0.90––––
vercel_ai_gatewayvercel_ai_gateway/​mistral/​codestral-​embed
codestral-​embed
0$0.15$0.00––––
vertex_ai-mistral_models vertex_ai/​codestral@latest
codestral@latest
128k$0.20$0.60––––
mistral mistral/​codestral-​mamba-​latestℹ️
codestral-​mamba-​latest
256k$0.25$0.25––––
openrouter openai/​codex-​mini
codex-​mini
200k$1.50$6.00––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​cogito-​671b-​v2-​p1
cogito-​671b-​v2-​p1
163k$1.20$1.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​cogito-​v1-​preview-​llama-​3b
cogito-​v1-​preview-​llama-​3b
131k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​cogito-​v1-​preview-​llama-​70b
cogito-​v1-​preview-​llama-​70b
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​cogito-​v1-​preview-​llama-​8b
cogito-​v1-​preview-​llama-​8b
131k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​cogito-​v1-​preview-​qwen-​14b
cogito-​v1-​preview-​qwen-​14b
131k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​cogito-​v1-​preview-​qwen-​32b
cogito-​v1-​preview-​qwen-​32b
131k$0.90$0.90––––
openrouter deepcogito/​cogito-​v2.1-​671b
cogito-​v2.1-​671b
128k$1.25$1.25––––
openrouter deepcogito/​cogito-​v2-​preview-​llama-​109b-​moe
cogito-​v2-​preview-​llama-​109b-​moe
32k$0.18$0.59––––
openrouter deepcogito/​cogito-​v2-​preview-​llama-​405b
cogito-​v2-​preview-​llama-​405b
32k$3.50$3.50––––
openrouter deepcogito/​cogito-​v2-​preview-​llama-​70b
cogito-​v2-​preview-​llama-​70b
32k$0.88$0.88––––
ocioci/​cohere.​command-​latestℹ️
cohere.​command-​latest
128k$1.56$1.56––––
ocioci/​cohere.​command-​plus-​latestℹ️
cohere.​command-​plus-​latest
128k$1.56$1.56––––
oci, vercel_ai_gateway, openrouter, cohere_chat ▶command-a (4 endpoints)256k$1.56–$2.50$1.56–$10.00––––
cohere_chat command-​light4k$0.30$0.60––––
bedrock cohere.​command-​light-​text-​v14
command-​light-​text-​v14
4k$0.30$0.60––––
cohere_chat, vercel_ai_gateway, openrouter, bedrock ▶command-r (5 endpoints)128k$0.15–$0.50$0.60–$1.50––––
openrouter, cohere_chat ▶command-r7b-12-2024 (2 endpoints)128k$0.0375–$0.15$0.0375–$0.15––––
cohere_chat, vercel_ai_gateway, openrouter, azure, bedrock ▶command-r-plus (6 endpoints)128k$2.50–$3.00$10.00–$15.00––––
bedrock cohere.​command-​text-​v14
command-​text-​v14
4k$1.50$2.00––––
azure ▶computer-use-preview (2 endpoints)8k$3.00$12.00––––
openrouter thedrummer/​cydonia-​24b-​v4.1
cydonia-​24b-​v4.1
131k$0.30$0.50––––
databricks databricks/​databricks-​claude-​3-​7-​sonnetℹ️
databricks-​claude-​3-​7-​sonnet
200k$3.00$15.00––––
databricks databricks/​databricks-​claude-​haiku-​4-​5ℹ️
databricks-​claude-​haiku-​4-​5
200k$1.00$5.00––––
databricks databricks/​databricks-​claude-​opus-​4ℹ️
databricks-​claude-​opus-​4
200k$15.00$75.00––––
databricks databricks/​databricks-​claude-​opus-​4-​1ℹ️
databricks-​claude-​opus-​4-​1
200k$15.00$75.00––––
databricks databricks/​databricks-​claude-​opus-​4-​5ℹ️
databricks-​claude-​opus-​4-​5
200k$5.00$25.00––––
databricks databricks/​databricks-​claude-​sonnet-​4ℹ️
databricks-​claude-​sonnet-​4
200k$3.00$15.00––––
databricks databricks/​databricks-​claude-​sonnet-​4-​1ℹ️
databricks-​claude-​sonnet-​4-​1
200k$3.00$15.00––––
databricks databricks/​databricks-​claude-​sonnet-​4-​5ℹ️
databricks-​claude-​sonnet-​4-​5
200k$3.00$15.00––––
databricks databricks/​databricks-​gemini-​2-​5-​flashℹ️
databricks-​gemini-​2-​5-​flash
1048k$0.30$2.50––––
databricks databricks/​databricks-​gemini-​2-​5-​proℹ️
databricks-​gemini-​2-​5-​pro
1048k$1.25$10.00––––
databricks databricks/​databricks-​gemma-​3-​12bℹ️
databricks-​gemma-​3-​12b
128k$0.15$0.50––––
databricks databricks/​databricks-​gpt-​5ℹ️
databricks-​gpt-​5
400k$1.25$10.00––––
databricks databricks/​databricks-​gpt-​5-​1ℹ️
databricks-​gpt-​5-​1
400k$1.25$10.00––––
databricks databricks/​databricks-​gpt-​5-​miniℹ️
databricks-​gpt-​5-​mini
400k$0.25$2.00––––
databricks databricks/​databricks-​gpt-​5-​nanoℹ️
databricks-​gpt-​5-​nano
400k$0.05$0.40––––
databricks databricks/​databricks-​gpt-​oss-​120bℹ️
databricks-​gpt-​oss-​120b
131k$0.15$0.60––––
databricks databricks/​databricks-​gpt-​oss-​20bℹ️
databricks-​gpt-​oss-​20b
131k$0.07$0.30––––
databricks databricks/​databricks-​llama-​2-​70b-​chatℹ️
databricks-​llama-​2-​70b-​chat
4k$0.50$1.50––––
databricks databricks/​databricks-​llama-​4-​maverickℹ️
databricks-​llama-​4-​maverick
128k$0.50$1.50––––
databricks databricks/​databricks-​meta-​llama-​3-​1-​405b-​instructℹ️
databricks-​meta-​llama-​3-​1-​405b-​instruct
128k$5.00$15.00––––
databricks databricks/​databricks-​meta-​llama-​3-​1-​8b-​instructℹ️
databricks-​meta-​llama-​3-​1-​8b-​instruct
200k$0.15$0.45––––
databricks databricks/​databricks-​meta-​llama-​3-​3-​70b-​instructℹ️
databricks-​meta-​llama-​3-​3-​70b-​instruct
128k$0.50$1.50––––
databricks databricks/​databricks-​meta-​llama-​3-​70b-​instructℹ️
databricks-​meta-​llama-​3-​70b-​instruct
128k$1.00$3.00––––
databricks databricks/​databricks-​mixtral-​8x7b-​instructℹ️
databricks-​mixtral-​8x7b-​instruct
4k$0.50$1.00––––
databricks databricks/​databricks-​mpt-​30b-​instructℹ️
databricks-​mpt-​30b-​instruct
8k$1.00$1.00––––
databricks databricks/​databricks-​mpt-​7b-​instructℹ️
databricks-​mpt-​7b-​instruct
8k$0.50$0.00––––
openrouter nousresearch/​deephermes-​3-​mistral-​24b-​preview
deephermes-​3-​mistral-​24b-​preview
32k$0.05$0.20––––
deepseek deepseek-​chatℹ️131k$0.60$1.70––––
openrouter deepseek/​deepseek-​chat-​v3.1
deepseek-​chat-​v3.1
8k$0.15$0.75––––
deepseek deepseek/​deepseek-​coder
deepseek-​coder
128k$0.14$0.28––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​coder-​1b-​base
deepseek-​coder-​1b-​base
16k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​coder-​33b-​instruct
deepseek-​coder-​33b-​instruct
16k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​coder-​7b-​base
deepseek-​coder-​7b-​base
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​coder-​7b-​base-​v1p5
deepseek-​coder-​7b-​base-​v1p5
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​coder-​7b-​instruct-​v1p5
deepseek-​coder-​7b-​instruct-​v1p5
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​coder-​v2-​instructℹ️
deepseek-​coder-​v2-​instruct
65k$1.20$1.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​coder-​v2-​lite-​base
deepseek-​coder-​v2-​lite-​base
163k$0.50$0.50––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​coder-​v2-​lite-​instruct
deepseek-​coder-​v2-​lite-​instruct
163k$0.50$0.50––––
lambda_ai, lambda ▶deepseek-llama3.3-70b (2 endpoints)131k–131k$0.20$0.60––––
openrouter, fireworks_ai ▶deepseek-prover-v2 (2 endpoints)163k$0.50–$1.20$1.20–$2.18––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​r1-​0528-​distill-​qwen3-​8b
deepseek-​r1-​0528-​distill-​qwen3-​8b
131k$0.20$0.20––––
vertex_ai-deepseek_modelsvertex_ai/​deepseek-​ai/​deepseek-​r1-​0528-​maasℹ️
deepseek-​r1-​0528-​maas
65k$1.35$5.40––––
openrouter deepseek/​deepseek-​r1-​0528-​qwen3-​8b
deepseek-​r1-​0528-​qwen3-​8b
32k$0.02$0.10––––
together_ai together_ai/​deepseek-​ai/​DeepSeek-​R1-​0528-​tputℹ️
deepseek-​r1-​0528-​tput
128k$0.55$2.19––––
deepinfra deepinfra/​deepseek-​ai/​DeepSeek-​R1-​0528-​Turbo
deepseek-​r1-​0528-​turbo
32k$1.00$3.00––––
lambda_ailambda_ai/​deepseek-​r1-​671b
deepseek-​r1-​671b
131k$0.80$0.80––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​r1-​basicℹ️
deepseek-​r1-​basic
128k$0.55$2.19––––
fireworks_ai, nscale ▶deepseek-r1-distill-llama-8b (2 endpoints)131k$0.025–$0.20$0.025–$0.20––––
nscalenscale/​deepseek-​ai/​DeepSeek-​R1-​Distill-​Qwen-​1.5Bℹ️
deepseek-​r1-​distill-​qwen-​1.5b
–$0.09$0.09––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​r1-​distill-​qwen-​1p5b
deepseek-​r1-​distill-​qwen-​1p5b
131k$0.10$0.10––––
deepinfra, fireworks_ai, openrouter, nscale ▶deepseek-r1-distill-qwen-32b (4 endpoints)64k–131k$0.15–$0.90$0.15–$0.90––––
fireworks_ai, nscale ▶deepseek-r1-distill-qwen-7b (2 endpoints)131k$0.20$0.20––––
openrouter ▶deepseek-r1t2-chimera (2 endpoints)163k$0.00–$0.30$0.00–$1.20––––
openrouter ▶deepseek-r1t-chimera (2 endpoints)163k$0.00–$0.30$0.00–$1.20––––
deepinfra deepinfra/​deepseek-​ai/​DeepSeek-​R1-​Turbo
deepseek-​r1-​turbo
40k$1.00$3.00––––
deepseek deepseek-​reasonerℹ️131k$0.60$1.70––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​v2-​lite-​chat
deepseek-​v2-​lite-​chat
163k$0.50$0.50––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​v2p5
deepseek-​v2p5
32k$1.20$1.20––––
deepinfra, wandb, sambanova, together_ai ▶deepseek-v3.1 (4 endpoints)32k–163k$0.27–$55,000.00$1.00–$165,000.00––––
vertex_ai-deepseek_modelsvertex_ai/​deepseek-​ai/​deepseek-​v3.1-​maasℹ️
deepseek-​v3.1-​maas
163k$1.35$5.40––––
openrouter nex-​agi/​deepseek-​v3.1-​nex-​n1:free
deepseek-​v3.1-​nex-​n1
131k$0.00$0.00––––
openrouter, deepinfra ▶deepseek-v3.1-terminus (2 endpoints)163k$0.21–$0.27$0.79–$1.00––––
openrouter deepseek/​deepseek-​v3.1-​terminus:exacto
deepseek-​v3.1-​terminus:exacto
163k$0.21$0.79––––
openrouter, deepseek ▶deepseek-v3.2 (2 endpoints)163k$0.25–$0.28$0.38–$0.40––––
vertex_ai-deepseek_modelsvertex_ai/​deepseek-​ai/​deepseek-​v3.2-​maasℹ️
deepseek-​v3.2-​maas
163k$0.56$1.68––––
openrouter deepseek/​deepseek-​v3.2-​speciale
deepseek-​v3.2-​speciale
163k$0.27$0.41––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​v3p1ℹ️
deepseek-​v3p1
128k$0.56$1.68––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​v3p1-​terminusℹ️
deepseek-​v3p1-​terminus
128k$0.56$1.68––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​deepseek-​v3p2ℹ️
deepseek-​v3p2
163k$1.20$1.20––––
openrouter, mistral ▶devstral-medium (5 endpoints)128k–262k$0.00–$0.40$0.00–$2.00––––
fireworks_ai, openrouter, vercel_ai_gateway, mistral ▶devstral-small (6 endpoints)128k–131k$0.06–$0.90$0.12–$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​dobby-​mini-​unhinged-​plus-​llama-​3-​1-​8b
dobby-​mini-​unhinged-​plus-​llama-​3-​1-​8b
131k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​dobby-​unhinged-​llama-​3-​3-​70b-​new
dobby-​unhinged-​llama-​3-​3-​70b-​new
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​dolphin-​2-​9-​2-​qwen2-​72b
dolphin-​2-​9-​2-​qwen2-​72b
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​dolphin-​2p6-​mixtral-​8x7b
dolphin-​2p6-​mixtral-​8x7b
32k$0.50$0.50––––
openrouter cognitivecomputations/​dolphin-​mistral-​24b-​venice-​edition:free
dolphin-​mistral-​24b-​venice-​edition
32k$0.00$0.00––––
vercel_ai_gatewayvercel_ai_gateway/​cohere/​embed-​v4.0
embed-​v4.0
0$0.12$0.00––––
openrouter baidu/​ernie-​4.5-​21b-​a3b
ernie-​4.5-​21b-​a3b
120k$0.056$0.224––––
openrouter baidu/​ernie-​4.5-​21b-​a3b-​thinking
ernie-​4.5-​21b-​a3b-​thinking
131k$0.056$0.224––––
openrouter baidu/​ernie-​4.5-​300b-​a47b
ernie-​4.5-​300b-​a47b
123k$0.224$0.88––––
openrouter baidu/​ernie-​4.5-​vl-​28b-​a3b
ernie-​4.5-​vl-​28b-​a3b
30k$0.112$0.448––––
openrouter baidu/​ernie-​4.5-​vl-​424b-​a47b
ernie-​4.5-​vl-​424b-​a47b
123k$0.336$1.00––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​ernie-​4p5-​21b-​a3b-​pt
ernie-​4p5-​21b-​a3b-​pt
4k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​ernie-​4p5-​300b-​a47b-​pt
ernie-​4p5-​300b-​a47b-​pt
4k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​fare-​20b
fare-​20b
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​firefunction-​v1
firefunction-​v1
32k$0.50$0.50––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​firefunction-​v2ℹ️
firefunction-​v2
8k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​firellava-​13b
firellava-​13b
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​firesearch-​ocr-​v6
firesearch-​ocr-​v6
8k$0.20$0.20––––
watsonx watsonx/​google/​flan-​t5-​xl-​3b
flan-​t5-​xl-​3b
8k$0.60$0.60––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​flux-​1-​dev
flux-​1-​dev
4k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​flux-​1-​dev-​controlnet-​union
flux-​1-​dev-​controlnet-​union
4k$0.001$0.001––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​flux-​1-​schnell
flux-​1-​schnell
4k$0.10$0.10––––
vertex_ai-language-models gemini-​1.0-​proℹ️32k$0.50$1.50––––
vertex_ai-language-models gemini-​1.0-​pro-​002ℹ️32k$0.50$1.50––––
vertex_ai-vision-models gemini-​1.0-​pro-​visionℹ️16k$0.50$1.50––––
vertex_ai-vision-models gemini-​1.0-​pro-​vision-​001ℹ️16k$0.50$1.50––––
vertex_ai-language-models gemini-​1.0-​ultraℹ️8k$0.50$1.50––––
vertex_ai-language-models gemini-​1.0-​ultra-​001ℹ️8k$0.50$1.50––––
gemini, vertex_ai-language-models ▶gemini-1.5-flash (3 endpoints)1000k–1048k$0.075
>128k: $0.15–$1.00
$0.30
>128k: $0.60
––––
gemini gemini/​gemini-​1.5-​flash-​8bℹ️
gemini-​1.5-​flash-​8b
1048k$0.00
>128k: $0.00
$0.00
>128k: $0.00
––––
gemini, vertex_ai-language-models ▶gemini-1.5-flash-exp-0827 (2 endpoints)1000k–1048k$0.00–$0.0047
>128k: $0.00–$1.00
$0.00–$0.0047
>128k: $0.00–$0.0094
––––
vertex_ai-language-models gemini-​1.5-​flash-​preview-​0514ℹ️1000k$0.075
>128k: $1.00
$0.0047
>128k: $0.0094
––––
vertex_ai-language-models, gemini ▶gemini-1.5-pro (3 endpoints)1048k–2097k$1.25–$3.50
>128k: $2.50–$7.00
$1.05–$10.50
>128k: $10.00–$21.00
––––
vertex_ai-language-models ▶gemini-1.5-pro-preview-0215 (3 endpoints)1000k$0.0781
>128k: $0.1563
$0.3125
>128k: $0.625
––––
openrouter google/​gemini-​2.0-​flash-​exp:free
gemini-​2.0-​flash-​exp
1048k$0.00$0.00–––22.2%
vertex_ai-language-models, openrouter ▶gemini-2.0-flash-lite-001 (2 endpoints)1048k$0.075$0.30––––
gemini gemini/​gemini-​2.0-​flash-​lite-​preview-​02-​05ℹ️
gemini-​2.0-​flash-​lite-​preview-​02-​05
1048k$0.075$0.30––––
gemini gemini/​gemini-​2.0-​flash-​live-​001ℹ️
gemini-​2.0-​flash-​live-​001
1048k$0.35$1.50––––
vertex_ai-language-models gemini-​2.0-​flash-​live-​preview-​04-​09ℹ️1048k$0.50$2.00––––
vertex_ai-language-models, gemini ▶gemini-2.0-flash-preview-image-generation (2 endpoints)1048k$0.10$0.40––––
gemini gemini/​gemini-​2.5-​computer-​use-​preview-​10-​2025ℹ️
gemini-​2.5-​computer-​use-​preview-​10-​2025
128k$1.25
>200k: $2.50
$10.00
>200k: $15.00
––––
vertex_ai-language-models, gemini, openrouter, deepinfra, vercel_ai_gateway ▶gemini-2.5-flash (5 endpoints)1000k–1048k$0.30$2.50––––
openrouter google/​gemini-​2.5-​flash-​image
gemini-​2.5-​flash-​image
32k$0.30$2.50––––
openrouter google/​gemini-​2.5-​flash-​image-​preview
gemini-​2.5-​flash-​image-​preview
32k$0.30$2.50––––
vertex_ai-language-models, gemini, openrouter ▶gemini-2.5-flash-lite (3 endpoints)1048k$0.10$0.40––––
vertex_ai-language-models, gemini, openrouter ▶gemini-2.5-flash-lite-preview-06-17 (5 endpoints)1048k$0.10$0.40––––
gemini gemini/​gemini-​2.5-​flash-​preview-​ttsℹ️
gemini-​2.5-​flash-​preview-​tts
1048k$0.15$0.60––––
vertex_ai-language-models, gemini ▶gemini-2.5-pro-preview-tts (2 endpoints)1048k$1.25
>200k: $2.50
$10.00
>200k: $15.00
––––
openrouter google/​gemini-​3-​pro-​image-​preview
gemini-​3-​pro-​image-​preview
65k$2.00$12.00––––
vertex_ai-language-models gemini-​flash-​experimentalℹ️1000k$0.00$0.00––––
gemini gemini/​gemini-​flash-​latestℹ️
gemini-​flash-​latest
1048k$0.30$2.50––––
gemini gemini/​gemini-​flash-​lite-​latestℹ️
gemini-​flash-​lite-​latest
1048k$0.10$0.40––––
gemini gemini/​gemini-​gemma-​2-​27b-​itℹ️
gemini-​gemma-​2-​27b-​it
–$0.35$1.05––––
gemini gemini/​gemini-​gemma-​2-​9b-​itℹ️
gemini-​gemma-​2-​9b-​it
–$0.35$1.05––––
vertex_ai-language-models, gemini ▶gemini-live-2.5-flash-preview-native-audio-09-2025 (2 endpoints)1048k$0.30$2.00––––
gemini, vertex_ai-language-models ▶gemini-pro (2 endpoints)32k$0.35–$0.50
>128k: $0.70
$1.05–$1.50
>128k: $2.10
––––
vertex_ai-language-models gemini-​pro-​experimentalℹ️1000k$0.00$0.00––––
gemini, vertex_ai-vision-models ▶gemini-pro-vision (2 endpoints)16k–30k$0.35–$0.50
>128k: $0.70
$1.05–$1.50
>128k: $2.10
––––
vercel_ai_gatewayvercel_ai_gateway/​google/​gemma-​2-​9b
gemma-​2-​9b
8k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​gemma-​2b-​it
gemma-​2b-​it
8k$0.10$0.10––––
openrouter, deepinfra, bedrock_converse ▶gemma-3-12b-it (4 endpoints)32k–131k$0.00–$0.09$0.00–$0.29––––
deepinfra, bedrock_converse, openrouter ▶gemma-3-4b-it (4 endpoints)32k–131k$0.00–$0.04$0.00–$0.08––––
lemonadelemonade/​Gemma-​3-​4b-​it-​GGUF
gemma-​3-​4b-​it-​gguf
128k$0.00$0.00––––
openrouter google/​gemma-​3n-​e2b-​it:free
gemma-​3n-​e2b-​it
8k$0.00$0.00––––
openrouter ▶gemma-3n-e4b-it (2 endpoints)8k–32k$0.00–$0.02$0.00–$0.04––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​gemma-​7b
gemma-​7b
8k$0.20$0.20––––
groq, anyscale, fireworks_ai ▶gemma-7b-it (3 endpoints)8k$0.07–$0.20$0.07–$0.20––––
publicaipublicai/​aisingapore/​Gemma-​SEA-​LION-​v4-​27B-​ITℹ️
gemma-​sea-​lion-​v4-​27b-​it
8k$0.00$0.00––––
openrouter thudm/​glm-​4.1v-​9b-​thinking
glm-​4.1v-​9b-​thinking
65k$0.028$0.1104––––
openrouter z-​ai/​glm-​4-​32b
glm-​4-​32b
128k$0.10$0.10––––
zaizai/​glm-​4-​32b-​0414-​128kℹ️
glm-​4-​32b-​0414-​128k
128k$0.10$0.10––––
openrouter, deepinfra, vercel_ai_gateway, wandb, zai ▶glm-4.5 (5 endpoints)128k–131k$0.35–$55,000.00$1.55–$200,000.00––––
openrouter, vercel_ai_gateway, zai ▶glm-4.5-air (4 endpoints)128k–131k$0.00–$0.20$0.00–$1.10––––
together_ai together_ai/​zai-​org/​GLM-​4.5-​Air-​FP8ℹ️
glm-​4.5-​air-​fp8
128k$0.20$1.10––––
zaizai/​glm-​4.5-​airxℹ️
glm-​4.5-​airx
128k$1.10$4.50––––
zaizai/​glm-​4.5-​flashℹ️
glm-​4.5-​flash
128k$0.00$0.00––––
zai, openrouter ▶glm-4.5v (2 endpoints)65k–128k$0.48–$0.60$1.44–$1.80––––
zaizai/​glm-​4.5-​xℹ️
glm-​4.5-​x
128k$2.20$8.90––––
openrouter, vercel_ai_gateway, together_ai, zai ▶glm-4.6 (4 endpoints)200k–202k$0.40–$0.60$1.75–$2.20––––
openrouter z-​ai/​glm-​4.6:exacto
glm-​4.6:exacto
204k$0.44$1.76––––
openrouter z-​ai/​glm-​4.6v
glm-​4.6v
131k$0.30$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​glm-​4p5ℹ️
glm-​4p5
128k$0.55$2.19––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​glm-​4p5-​airℹ️
glm-​4p5-​air
128k$0.22$0.88––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​glm-​4p5v
glm-​4p5v
131k$1.20$1.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​glm-​4p6ℹ️
glm-​4p6
202k$0.55$2.19––––
openrouter alpindale/​goliath-​120b
goliath-​120b
6k$6.00$8.00––––
azure, openai, openrouter ▶gpt-35-turbo-16k (4 endpoints)16k$3.00$4.00––––
vercel_ai_gateway, openrouter ▶gpt-3.5-turbo-instruct (2 endpoints)4k–8k$1.50$2.00––––
azure ▶gpt-4-32k (2 endpoints)32k$60.00$120.00––––
openai, openrouter, azure ▶gpt-4o-audio-preview (5 endpoints)128k$2.50$10.00––––
openrouter openai/​gpt-​4o:extended
gpt-​4o:extended
128k$6.00$18.00––––
openai, azure ▶gpt-4o-mini-audio-preview (3 endpoints)128k$0.15–$2.50$0.60–$10.00––––
openai, azure ▶gpt-4o-mini-realtime-preview (5 endpoints)128k$0.60–$0.66$2.40–$2.64––––
openai, openrouter ▶gpt-4o-mini-search-preview (3 endpoints)128k$0.15$0.60––––
openai, azure ▶gpt-4o-realtime-preview (9 endpoints)128k$5.00–$5.50$20.00–$22.00––––
openai, openrouter ▶gpt-4o-search-preview (3 endpoints)128k$2.50$10.00––––
openai, openrouter ▶gpt-4-turbo-preview (2 endpoints)128k$10.00$30.00––––
azure azure/​gpt-​4-​turbo-​vision-​preview
gpt-​4-​turbo-​vision-​preview
128k$10.00$30.00––––
azure, openrouter, openai ▶gpt-5.1-chat (7 endpoints)128k–272k$1.25–$1.38$10.00–$11.00––––
openrouter openai/​gpt-​5.1-​codex
gpt-​5.1-​codex
400k$1.25$10.00––––
openrouter openai/​gpt-​5.1-​codex-​max
gpt-​5.1-​codex-​max
400k$1.25$10.00––––
openrouter openai/​gpt-​5.1-​codex-​mini
gpt-​5.1-​codex-​mini
400k$0.25$2.00––––
openrouter openai/​gpt-​5.2
gpt-​5.2
400k$1.75$14.00––––
openrouter openai/​gpt-​5.2-​chat
gpt-​5.2-​chat
128k$1.75$14.00––––
openrouter openai/​gpt-​5.2-​pro
gpt-​5.2-​pro
400k$21.00$168.00––––
azure, openrouter, openai ▶gpt-5-chat (4 endpoints)128k–272k$1.25$10.00––––
openrouter openai/​gpt-​5-​codex
gpt-​5-​codex
400k$1.25$10.00––––
openrouter openai/​gpt-​5-​image
gpt-​5-​image
400k$10.00$10.00––––
openrouter openai/​gpt-​5-​image-​mini
gpt-​5-​image-​mini
400k$2.50$2.00––––
openrouter openai/​gpt-​5-​pro
gpt-​5-​pro
400k$15.00$120.00––––
azure azure/​gpt-​audio-​2025-​08-​28
gpt-​audio-​2025-​08-​28
128k$2.50$10.00––––
azure azure/​gpt-​audio-​mini-​2025-​10-​06
gpt-​audio-​mini-​2025-​10-​06
128k$0.60$2.40––––
bedrock_converse openai.​gpt-​oss-​120b-​1:0
gpt-​oss-​120b-​1:0
128k$0.15$0.60––––
openrouter openai/​gpt-​oss-​120b:exacto
gpt-​oss-​120b:exacto
131k$0.039$0.19––––
vertex_ai-openai_modelsvertex_ai/​openai/​gpt-​oss-​120b-​maasℹ️
gpt-​oss-​120b-​maas
131k$0.15$0.60––––
lemonadelemonade/​gpt-​oss-​120b-​mxfp-​GGUF
gpt-​oss-​120b-​mxfp-​gguf
131k$0.00$0.00––––
openrouter, deepinfra, fireworks_ai, groq, wandb, ovhcloud, together_ai ▶gpt-oss-20b (8 endpoints)128k–131k$0.00–$5,000.00$0.00–$20,000.00––––
bedrock_converse openai.​gpt-​oss-​20b-​1:0
gpt-​oss-​20b-​1:0
128k$0.07$0.30––––
vertex_ai-openai_modelsvertex_ai/​openai/​gpt-​oss-​20b-​maasℹ️
gpt-​oss-​20b-​maas
131k$0.075$0.30––––
lemonadelemonade/​gpt-​oss-​20b-​mxfp4-​GGUF
gpt-​oss-​20b-​mxfp4-​gguf
131k$0.00$0.00––––
fireworks_ai, bedrock_converse ▶gpt-oss-safeguard-120b (2 endpoints)128k–131k$0.15–$1.20$0.60–$1.20––––
openrouter, fireworks_ai, bedrock_converse ▶gpt-oss-safeguard-20b (3 endpoints)128k–131k$0.07–$0.50$0.20–$0.50––––
openai, azure ▶gpt-realtime (3 endpoints)32k$4.00$16.00––––
openai, azure ▶gpt-realtime-mini (2 endpoints)32k–128k$0.60$2.40––––
watsonx watsonx/​ibm/​granite-​13b-​chat-​v2
granite-​13b-​chat-​v2
8k$0.60$0.60––––
watsonx watsonx/​ibm/​granite-​13b-​instruct-​v2
granite-​13b-​instruct-​v2
8k$0.60$0.60––––
watsonx watsonx/​ibm/​granite-​3-​3-​8b-​instruct
granite-​3-​3-​8b-​instruct
8k$0.20$0.20––––
watsonx watsonx/​ibm/​granite-​3-​8b-​instruct
granite-​3-​8b-​instruct
8k$0.20$0.20––––
openrouter ibm-​granite/​granite-​4.0-​h-​micro
granite-​4.0-​h-​micro
131k$0.017$0.11––––
watsonx watsonx/​ibm/​granite-​4-​h-​small
granite-​4-​h-​small
20k$0.06$0.25––––
watsonx watsonx/​ibm/​granite-​guardian-​3-​2-​2b
granite-​guardian-​3-​2-​2b
8k$0.10$0.10––––
watsonx watsonx/​ibm/​granite-​guardian-​3-​3-​8b
granite-​guardian-​3-​3-​8b
8k$0.20$0.20––––
watsonx watsonx/​ibm/​granite-​ttm-​1024-​96-​r2
granite-​ttm-​1024-​96-​r2
512$0.38$0.38––––
watsonx watsonx/​ibm/​granite-​ttm-​1536-​96-​r2
granite-​ttm-​1536-​96-​r2
512$0.38$0.38––––
watsonx watsonx/​ibm/​granite-​ttm-​512-​96-​r2
granite-​ttm-​512-​96-​r2
512$0.38$0.38––––
watsonx watsonx/​ibm/​granite-​vision-​3-​2-​2b
granite-​vision-​3-​2-​2b
8k$0.10$0.10––––
vercel_ai_gateway, xai ▶grok-2-vision (4 endpoints)32k$2.00$10.00––––
oci, azure_ai, vercel_ai_gateway, xai, openrouter ▶grok-3 (7 endpoints)131k$3.00–$3.30$0.15–$16.50––––
oci, vercel_ai_gateway, xai ▶grok-3-fast (3 endpoints)131k$5.00$25.00––––
xai xai/​grok-​3-​fast-​betaℹ️
grok-​3-​fast-​beta
131k$5.00$25.00––––
azure_ai, oci, vercel_ai_gateway, xai, openrouter ▶grok-3-mini (7 endpoints)131k$0.25–$0.30$0.50–$1.38––––
oci, vercel_ai_gateway, xai ▶grok-3-mini-fast (4 endpoints)131k$0.60$4.00––––
xai xai/​grok-​3-​mini-​fast-​betaℹ️
grok-​3-​mini-​fast-​beta
131k$0.60$4.00––––
xai, openrouter ▶grok-4-1-fast (2 endpoints)2000k$0.20
>128k: $0.40
$0.50
>128k: $1.00
––––
xai ▶grok-4-1-fast-non-reasoning (2 endpoints)2000k$0.20
>128k: $0.40
$0.50
>128k: $1.00
––––
xai ▶grok-4-1-fast-reasoning (2 endpoints)2000k$0.20
>128k: $0.40
$0.50
>128k: $1.00
––––
openrouter x-​ai/​grok-​4-​fast
grok-​4-​fast
2000k$0.20$0.50––––
xai, azure_ai ▶grok-4-fast-non-reasoning (2 endpoints)131k–2000k$0.20–$0.43
>128k: $0.40
$0.50–$1.73
>128k: $1.00
––––
xai, azure_ai ▶grok-4-fast-reasoning (2 endpoints)131k–2000k$0.20–$0.43
>128k: $0.40
$0.50–$1.73
>128k: $1.00
––––
xai xai/​grok-​beta
grok-​beta
131k$5.00$15.00––––
xai xai/​grok-​code-​fastℹ️
grok-​code-​fast
256k$0.20$1.50––––
xai, openrouter, azure_ai ▶grok-code-fast-1 (4 endpoints)131k–256k$0.20–$3.50$1.50–$17.50––––
xai xai/​grok-​vision-​beta
grok-​vision-​beta
8k$5.00$15.00––––
openrouter nousresearch/​hermes-​2-​pro-​llama-​3-​8b
hermes-​2-​pro-​llama-​3-​8b
8k$0.025$0.08––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​hermes-​2-​pro-​mistral-​7b
hermes-​2-​pro-​mistral-​7b
32k$0.20$0.20––––
lambda_ai, lambda ▶hermes3-405b (2 endpoints)131k–131k$0.80$0.80––––
lambda_ai, lambda ▶hermes3-70b (2 endpoints)131k–131k$0.12$0.30––––
lambda_ai, lambda ▶hermes3-8b (2 endpoints)131k–131k$0.025$0.04––––
openrouter, deepinfra ▶hermes-3-llama-3.1-405b (3 endpoints)131k$0.00–$1.00$0.00–$1.00––––
deepinfra, openrouter, hyperbolic ▶hermes-3-llama-3.1-70b (3 endpoints)32k–131k$0.12–$0.30$0.30––––
openrouter nousresearch/​hermes-​4-​405b
hermes-​4-​405b
131k$0.30$1.20––––
openrouter nousresearch/​hermes-​4-​70b
hermes-​4-​70b
131k$0.11$0.38––––
openrouter tencent/​hunyuan-​a13b-​instruct
hunyuan-​a13b-​instruct
131k$0.14$0.57––––
openrouter inflection/​inflection-​3-​pi
inflection-​3-​pi
8k$2.50$10.00––––
openrouter inflection/​inflection-​3-​productivity
inflection-​3-​productivity
8k$2.50$10.00––––
openrouter prime-​intellect/​intellect-​3
intellect-​3
131k$0.20$1.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​internvl3-​38b
internvl3-​38b
16k$0.90$0.90––––
openrouter, fireworks_ai ▶internvl3-78b (2 endpoints)16k–32k$0.10–$0.90$0.39–$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​internvl3-​8b
internvl3-​8b
16k$0.20$0.20––––
bedrock ai21.​j2-​mid-​v1
j2-​mid-​v1
8k$12.50$12.50––––
bedrock ai21.​j2-​ultra-​v1
j2-​ultra-​v1
8k$18.80$18.80––––
watsonx watsonx/​core42/​jais-​13b-​chat
jais-​13b-​chat
8k$500.00$2,000.00––––
azure_ai azure_ai/​jais-​30b-​chatℹ️
jais-​30b-​chat
8k$3,200.00$9,710.00––––
ai21, vertex_ai-ai21_models ▶jamba-1.5 (2 endpoints)256k$0.20$0.40––––
ai21, vertex_ai-ai21_models, bedrock ▶jamba-1.5-large (3 endpoints)256k$2.00$8.00––––
ai21, vertex_ai-ai21_models ▶jamba-1.5-large@001 (2 endpoints)256k$2.00$8.00––––
ai21, vertex_ai-ai21_models, bedrock ▶jamba-1.5-mini (3 endpoints)256k$0.20$0.40––––
ai21, vertex_ai-ai21_models ▶jamba-1.5-mini@001 (2 endpoints)256k$0.20$0.40––––
azure_ai, bedrock ▶jamba-instruct (2 endpoints)70k$0.50$0.70––––
ai21 jamba-​large-​1.6256k$2.00$8.00––––
ai21, openrouter ▶jamba-large-1.7 (2 endpoints)256k$2.00$8.00––––
ai21 jamba-​mini-​1.6256k$0.20$0.40––––
ai21, openrouter ▶jamba-mini-1.7 (2 endpoints)256k$0.20$0.40––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​kat-​coder
kat-​coder
262k$0.90$0.90––––
openrouter kwaipilot/​kat-​coder-​pro:free
kat-​coder-​pro
256k$0.00$0.00––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​kat-​dev-​32b
kat-​dev-​32b
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​kat-​dev-​72b-​exp
kat-​dev-​72b-​exp
131k$0.90$0.90––––
openrouter moonshotai/​kimi-​dev-​72b
kimi-​dev-​72b
131k$0.29$1.15––––
moonshotmoonshot/​kimi-​k2-​0711-​previewℹ️
kimi-​k2-​0711-​preview
131k$0.60$2.50––––
openrouter moonshotai/​kimi-​k2-​0905:exacto
kimi-​k2-​0905:exacto
262k$0.60$2.50––––
moonshotmoonshot/​kimi-​k2-​0905-​previewℹ️
kimi-​k2-​0905-​preview
262k$0.60$2.50––––
deepinfra, fireworks_ai, groq, together_ai, hyperbolic, wandb ▶kimi-k2-instruct (10 endpoints)128k–262k$0.50–$2.00$2.00–$3.00––––
openrouter, fireworks_ai, moonshot, bedrock_converse ▶kimi-k2-thinking (4 endpoints)128k–262k$0.45–$0.60$2.35–$2.50––––
vertex_ai-moonshot_modelsvertex_ai/​moonshotai/​kimi-​k2-​thinking-​maasℹ️
kimi-​k2-​thinking-​maas
256k$0.60$2.50––––
moonshotmoonshot/​kimi-​k2-​turbo-​previewℹ️
kimi-​k2-​turbo-​preview
262k$1.15$8.00––––
moonshotmoonshot/​kimi-​latestℹ️
kimi-​latest
131k$2.00$5.00––––
moonshotmoonshot/​kimi-​latest-​128kℹ️
kimi-​latest-​128k
131k$2.00$5.00––––
moonshotmoonshot/​kimi-​latest-​32kℹ️
kimi-​latest-​32k
32k$1.00$3.00––––
moonshotmoonshot/​kimi-​latest-​8kℹ️
kimi-​latest-​8k
8k$0.20$2.00––––
openrouter moonshotai/​kimi-​linear-​48b-​a3b-​instruct
kimi-​linear-​48b-​a3b-​instruct
1048k$0.70$0.90––––
moonshotmoonshot/​kimi-​thinking-​previewℹ️
kimi-​thinking-​preview
131k$0.60$2.50––––
deepinfra deepinfra/​Sao10K/​L3.1-​70B-​Euryale-​v2.2
l3.1-​70b-​euryale-​v2.2
131k$0.65$0.75––––
openrouter sao10k/​l3.1-​70b-​hanami-​x1
l3.1-​70b-​hanami-​x1
16k$3.00$3.00––––
openrouter sao10k/​l3.1-​euryale-​70b
l3.1-​euryale-​70b
32k$0.65$0.75––––
deepinfra deepinfra/​Sao10K/​L3.3-​70B-​Euryale-​v2.3
l3.3-​70b-​euryale-​v2.3
131k$0.65$0.75––––
openrouter sao10k/​l3.3-​euryale-​70b
l3.3-​euryale-​70b
131k$0.65$0.75––––
deepinfra deepinfra/​Sao10K/​L3-​8B-​Lunaris-​v1-​Turbo
l3-​8b-​lunaris-​v1-​turbo
8k$0.04$0.05––––
openrouter sao10k/​l3-​euryale-​70b
l3-​euryale-​70b
8k$1.48$1.48––––
openrouter sao10k/​l3-​lunaris-​8b
l3-​lunaris-​8b
8k$0.04$0.05––––
mistral mistral/​labs-​devstral-​small-​2512ℹ️
labs-​devstral-​small-​2512
256k$0.10$0.30––––
gemini gemini/​learnlm-​1.5-​pro-​experimentalℹ️
learnlm-​1.5-​pro-​experimental
32k$0.00
>128k: $0.00
$0.00
>128k: $0.00
––––
openrouter liquid/​lfm-​2.2-​6b
lfm-​2.2-​6b
32k$0.05$0.10––––
openrouter liquid/​lfm2-​8b-​a1b
lfm2-​8b-​a1b
32k$0.05$0.10––––
lambda_ai, lambda ▶lfm-40b (2 endpoints)66k–131k$0.10–$0.15$0.15–$0.20––––
lambda_ailambda_ai/​lfm-​7b
lfm-​7b
131k$0.025$0.04––––
replicate replicate/​meta/​llama-​2-​13b
llama-​2-​13b
4k$0.10$0.50––––
replicate, anyscale ▶llama-2-13b-chat (2 endpoints)4k$0.10–$0.25$0.25–$0.50––––
bedrock meta.​llama2-​13b-​chat-​v1
llama2-​13b-​chat-​v1
4k$0.75$1.00––––
replicate, groq ▶llama-2-70b (2 endpoints)4k$0.65–$0.70$0.80–$2.75––––
bedrock meta.​llama2-​70b-​chat-​v1
llama2-​70b-​chat-​v1
4k$1.95$2.56––––
replicate replicate/​meta/​llama-​2-​7b
llama-​2-​7b
4k$0.05$0.25––––
replicate, anyscale ▶llama-2-7b-chat (2 endpoints)4k$0.05–$0.15$0.15–$0.25––––
cloudflare cloudflare/​@cf/​meta/​llama-​2-​7b-​chat-​fp16
llama-​2-​7b-​chat-​fp16
3k$1.923$1.923––––
cloudflare cloudflare/​@cf/​meta/​llama-​2-​7b-​chat-​int8
llama-​2-​7b-​chat-​int8
2k$1.923$1.923––––
openrouter meta-​llama/​llama-​3.1-​405b
llama-​3.1-​405b
32k$4.00$4.00––––
lambda_ai, lambda ▶llama3.1-405b-instruct-fp8 (2 endpoints)131k–131k$0.80$0.80––––
vertex_ai-llama_models vertex_ai/​meta/​llama-​3.1-​405b-​instruct-​maasℹ️
llama-​3.1-​405b-​instruct-​maas
128k$5.00$16.00––––
groq groq/​llama-​3.1-​405b-​reasoning
llama-​3.1-​405b-​reasoning
8k$0.59$0.79––––
cerebras, vercel_ai_gateway ▶llama3.1-70b (2 endpoints)128k$0.60–$0.72$0.60–$0.72––––
lambda_ai, lambda ▶llama3.1-70b-instruct-fp8 (2 endpoints)131k–131k$0.12$0.30––––
vertex_ai-llama_models vertex_ai/​meta/​llama-​3.1-​70b-​instruct-​maasℹ️
llama-​3.1-​70b-​instruct-​maas
128k$0.00$0.00––––
groq groq/​llama-​3.1-​70b-​versatile
llama-​3.1-​70b-​versatile
8k$0.59$0.79––––
vercel_ai_gateway, cerebras ▶llama-3.1-8b (2 endpoints)128k–131k$0.05–$0.10$0.08–$0.10––––
groq groq/​llama-​3.1-​8b-​instant
llama-​3.1-​8b-​instant
128k$0.05$0.08––––
vertex_ai-llama_models vertex_ai/​meta/​llama-​3.1-​8b-​instruct-​maasℹ️
llama-​3.1-​8b-​instruct-​maas
128k$0.00$0.00––––
openrouter neversleep/​llama-​3.1-​lumimaid-​8b
llama-​3.1-​lumimaid-​8b
32k$0.09$0.60––––
deepinfra, openrouter ▶llama-3.1-nemotron-70b-instruct (2 endpoints)131k$0.60–$1.20$0.60–$1.20––––
lambda_ai, lambda ▶llama3.1-nemotron-70b-instruct-fp8 (2 endpoints)131k–131k$0.12$0.30––––
openrouter nvidia/​llama-​3.1-​nemotron-​ultra-​253b-​v1
llama-​3.1-​nemotron-​ultra-​253b-​v1
131k$0.60$1.80––––
perplexity perplexity/​llama-​3.1-​sonar-​huge-​128k-​online
llama-​3.1-​sonar-​huge-​128k-​online
127k$5.00$5.00––––
perplexity perplexity/​llama-​3.1-​sonar-​large-​128k-​chat
llama-​3.1-​sonar-​large-​128k-​chat
131k$1.00$1.00––––
perplexity perplexity/​llama-​3.1-​sonar-​large-​128k-​online
llama-​3.1-​sonar-​large-​128k-​online
127k$1.00$1.00––––
perplexity perplexity/​llama-​3.1-​sonar-​small-​128k-​chat
llama-​3.1-​sonar-​small-​128k-​chat
131k$0.20$0.20––––
perplexity perplexity/​llama-​3.1-​sonar-​small-​128k-​online
llama-​3.1-​sonar-​small-​128k-​online
127k$0.20$0.20––––
vercel_ai_gatewayvercel_ai_gateway/​meta/​llama-​3.2-​11b
llama-​3.2-​11b
128k$0.16$0.16––––
bedrock ▶llama3-2-11b-instruct-v1.0 (2 endpoints)128k$0.35$0.35––––
groq groq/​llama-​3.2-​11b-​text-​preview
llama-​3.2-​11b-​text-​preview
8k$0.18$0.18––––
lambda_ai, deepinfra, openrouter, watsonx, azure_ai ▶llama3.2-11b-vision-instruct (5 endpoints)128k–131k$0.015–$0.37$0.025–$0.37––––
groq groq/​llama-​3.2-​11b-​vision-​preview
llama-​3.2-​11b-​vision-​preview
8k$0.18$0.18––––
vercel_ai_gatewayvercel_ai_gateway/​meta/​llama-​3.2-​1b
llama-​3.2-​1b
128k$0.10$0.10––––
watsonx, bedrock, openrouter ▶llama-3-2-1b-instruct (5 endpoints)60k–128k$0.027–$0.13$0.10–$0.20––––
groq groq/​llama-​3.2-​1b-​preview
llama-​3.2-​1b-​preview
8k$0.04$0.04––––
vercel_ai_gatewayvercel_ai_gateway/​meta/​llama-​3.2-​3b
llama-​3.2-​3b
128k$0.15$0.15––––
openrouter, lambda_ai, deepinfra, lambda, watsonx, bedrock, hyperbolic ▶llama-3.2-3b-instruct (10 endpoints)32k–131k$0.00–$0.19$0.00–$0.30––––
groq groq/​llama-​3.2-​3b-​preview
llama-​3.2-​3b-​preview
8k$0.06$0.06––––
vercel_ai_gatewayvercel_ai_gateway/​meta/​llama-​3.2-​90b
llama-​3.2-​90b
128k$0.72$0.72––––
bedrock ▶llama3-2-90b-instruct-v1.0 (2 endpoints)128k$2.00$2.00––––
groq groq/​llama-​3.2-​90b-​text-​preview
llama-​3.2-​90b-​text-​preview
8k$0.90$0.90––––
vertex_ai-llama_models vertex_ai/​meta/​llama-​3.2-​90b-​vision-​instruct-​maasℹ️
llama-​3.2-​90b-​vision-​instruct-​maas
128k$0.00$0.00––––
groq groq/​llama-​3.2-​90b-​vision-​preview
llama-​3.2-​90b-​vision-​preview
8k$0.90$0.90––––
vercel_ai_gateway, cerebras ▶llama-3.3-70b (2 endpoints)128k$0.72–$0.85$0.72–$1.20––––
lambda_ai, lambda ▶llama3.3-70b-instruct-fp8 (2 endpoints)131k–131k$0.12$0.30––––
deepinfra, together_ai ▶llama-3.3-70b-instruct-turbo (2 endpoints)131k$0.13–$0.88$0.39–$0.88––––
together_ai together_ai/​meta-​llama/​Llama-​3.3-​70B-​Instruct-​Turbo-​Free
llama-​3.3-​70b-​instruct-​turbo-​free
–$0.00$0.00––––
groq groq/​llama-​3.3-​70b-​specdec
llama-​3.3-​70b-​specdec
8k$0.59$0.99––––
groq groq/​llama-​3.3-​70b-​versatile
llama-​3.3-​70b-​versatile
128k$0.59$0.79––––
deepinfra, openrouter ▶llama-3.3-nemotron-super-49b-v1.5 (2 endpoints)131k$0.10$0.40––––
vertex_ai-llama_models vertex_ai/​meta/​llama3-​405b-​instruct-​maasℹ️
llama3-​405b-​instruct-​maas
32k$0.00$0.00––––
vercel_ai_gateway, replicate ▶llama-3-70b (2 endpoints)8k$0.59–$0.65$0.79–$2.75––––
openrouter, replicate, bedrock ▶llama-3-70b-instruct (12 endpoints)8k–8k$0.30–$4.45$0.40–$5.88––––
vertex_ai-llama_models vertex_ai/​meta/​llama3-​70b-​instruct-​maasℹ️
llama3-​70b-​instruct-​maas
32k$0.00$0.00––––
vercel_ai_gateway, replicate ▶llama-3-8b (2 endpoints)8k–8k$0.05$0.08–$0.25––––
openrouter, bedrock, replicate, gradient_ai ▶llama-3-8b-instruct (13 endpoints)8k–8k$0.03–$0.50$0.06–$2.65––––
vertex_ai-llama_models vertex_ai/​meta/​llama3-​8b-​instruct-​maasℹ️
llama3-​8b-​instruct-​maas
32k$0.00$0.00––––
groq groq/​llama3-​groq-​70b-​8192-​tool-​use-​preview
llama3-​groq-​70b-​8192-​tool-​use-​preview
8k$0.89$0.89––––
groq groq/​llama3-​groq-​8b-​8192-​tool-​use-​preview
llama3-​groq-​8b-​8192-​tool-​use-​preview
8k$0.19$0.19––––
watsonx watsonx/​meta-​llama/​llama-​4-​maverick-​17b
llama-​4-​maverick-​17b
128k$0.35$1.40––––
groq, sambanova ▶llama-4-maverick-17b-128e-instruct (2 endpoints)131k$0.20–$0.63$0.60–$1.80––––
deepinfra, azure_ai, oci, lambda_ai, together_ai ▶llama-4-maverick-17b-128e-instruct-fp8 (5 endpoints)131k–1048k$0.05–$1.41$0.10–$0.85––––
vertex_ai-llama_models vertex_ai/​meta/​llama-​4-​maverick-​17b-​128e-​instruct-​maasℹ️
llama-​4-​maverick-​17b-​128e-​instruct-​maas
1000k$0.35$1.15––––
vertex_ai-llama_models vertex_ai/​meta/​llama-​4-​maverick-​17b-​16e-​instruct-​maasℹ️
llama-​4-​maverick-​17b-​16e-​instruct-​maas
1000k$0.35$1.15––––
bedrock_converse ▶llama4-maverick-17b-instruct-v1.0 (2 endpoints)128k$0.24$0.97––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama4-​maverick-​instruct-​basicℹ️
llama4-​maverick-​instruct-​basic
131k$0.22$0.88––––
vertex_ai-llama_models vertex_ai/​meta/​llama-​4-​scout-​17b-​128e-​instruct-​maasℹ️
llama-​4-​scout-​17b-​128e-​instruct-​maas
10000k$0.25$0.70––––
azure_ai, deepinfra, oci, groq, wandb, lambda_ai, sambanova, nscale, together_ai ▶llama-4-scout-17b-16e-instruct (9 endpoints)8k–10000k$0.05–$17,000.00$0.10–$66,000.00––––
vertex_ai-llama_models vertex_ai/​meta/​llama-​4-​scout-​17b-​16e-​instruct-​maasℹ️
llama-​4-​scout-​17b-​16e-​instruct-​maas
10000k$0.25$0.70––––
bedrock_converse ▶llama4-scout-17b-instruct-v1.0 (2 endpoints)128k$0.17$0.66––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama4-​scout-​instruct-​basicℹ️
llama4-​scout-​instruct-​basic
131k$0.15$0.60––––
fireworks_ai, openrouter ▶llama-guard-2-8b (2 endpoints)8k$0.20$0.20––––
watsonx watsonx/​meta-​llama/​llama-​guard-​3-​11b-​vision
llama-​guard-​3-​11b-​vision
128k$0.35$0.35––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​guard-​3-​1b
llama-​guard-​3-​1b
131k$0.10$0.10––––
openrouter, deepinfra, fireworks_ai, groq ▶llama-guard-3-8b (4 endpoints)8k–131k$0.02–$0.20$0.055–$0.20––––
deepinfra, openrouter ▶llama-guard-4-12b (2 endpoints)163k$0.18$0.18––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llamaguard-​7b
llamaguard-​7b
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v2-​13b
llama-​v2-​13b
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v2-​13b-​chat
llama-​v2-​13b-​chat
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v2-​70b
llama-​v2-​70b
4k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v2-​70b-​chat
llama-​v2-​70b-​chat
2k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v2-​7b
llama-​v2-​7b
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v2-​7b-​chat
llama-​v2-​7b-​chat
4k$0.20$0.20––––
fireworks_ai ▶llama-v3-70b-instruct (2 endpoints)8k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3-​8b
llama-​v3-​8b
8k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3-​8b-​instruct-​hf
llama-​v3-​8b-​instruct
8k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p1-​405b-​instructℹ️
llama-​v3p1-​405b-​instruct
128k$3.00$3.00––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p1-​405b-​instruct-​long
llama-​v3p1-​405b-​instruct-​long
4k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p1-​70b-​instruct
llama-​v3p1-​70b-​instruct
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p1-​70b-​instruct-​1b
llama-​v3p1-​70b-​instruct-​1b
4k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p1-​8b-​instructℹ️
llama-​v3p1-​8b-​instruct
16k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p1-​nemotron-​70b-​instruct
llama-​v3p1-​nemotron-​70b-​instruct
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p2-​11b-​vision-​instructℹ️
llama-​v3p2-​11b-​vision-​instruct
16k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p2-​1b
llama-​v3p2-​1b
131k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p2-​1b-​instructℹ️
llama-​v3p2-​1b-​instruct
16k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p2-​3b
llama-​v3p2-​3b
131k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p2-​3b-​instructℹ️
llama-​v3p2-​3b-​instruct
16k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p2-​90b-​vision-​instructℹ️
llama-​v3p2-​90b-​vision-​instruct
16k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llama-​v3p3-​70b-​instruct
llama-​v3p3-​70b-​instruct
131k$0.90$0.90––––
ovhcloudovhcloud/​llava-​v1.6-​mistral-​7b-​hfℹ️
llava-​v1.6-​mistral-​7b
32k$0.29$0.29––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​llava-​yi-​34b
llava-​yi-​34b
4k$0.90$0.90––––
openrouter eleutherai/​llemma_7b
llemma_7b
4k$0.80$1.20––––
openrouter ▶longcat-flash-chat (2 endpoints)131k$0.00–$0.15$0.00–$0.75––––
aleph_alpha luminous-​base-​control–$37.50$41.25––––
aleph_alpha luminous-​extended-​control–$56.25$61.875––––
aleph_alpha luminous-​supreme-​control–$218.75$240.625––––
openrouter arcee-​ai/​maestro-​reasoning
maestro-​reasoning
131k$0.90$3.30––––
vercel_ai_gateway, mistral ▶magistral-medium (4 endpoints)40k–128k$2.00$5.00––––
openrouter anthracite-​org/​magnum-​v4-​72b
magnum-​v4-​72b
16k$3.00$5.00––––
openrouter, azure_ai ▶mai-ds-r1 (2 endpoints)128k–163k$0.30–$1.35$1.20–$5.40––––
ovhcloudovhcloud/​mamba-​codestral-​7B-​v0.1ℹ️
mamba-​codestral-​7b-​v0.1
256k$0.19$0.19––––
openrouter inception/​mercury
mercury
128k$0.25$1.00––––
openrouter inception/​mercury-​coder
mercury-​coder
128k$0.25$1.00––––
vercel_ai_gatewayvercel_ai_gateway/​inception/​mercury-​coder-​small
mercury-​coder-​small
32k$0.25$1.00––––
ovhcloudovhcloud/​Meta-​Llama-​3_1-​70B-​Instructℹ️
meta-​llama-​3_1-​70b-​instruct
131k$0.67$0.67––––
ovhcloudovhcloud/​Meta-​Llama-​3_3-​70B-​Instructℹ️
meta-​llama-​3_3-​70b-​instruct
131k$0.67$0.67––––
azure_ai, hyperbolic, sambanova ▶meta-llama-3.1-405b-instruct (3 endpoints)16k–128k$0.12–$5.33$0.30–$16.00––––
together_ai together_ai/​meta-​llama/​Meta-​Llama-​3.1-​405B-​Instruct-​Turbo
meta-​llama-​3.1-​405b-​instruct-​turbo
–$3.50$3.50––––
deepinfra, azure_ai, hyperbolic, friendliai ▶meta-llama-3.1-70b-instruct (4 endpoints)8k–131k$0.12–$2.68$0.30–$3.54––––
deepinfra, together_ai ▶meta-llama-3.1-70b-instruct-turbo (2 endpoints)131k$0.10–$0.88$0.28–$0.88––––
deepinfra, together_ai ▶meta-llama-3.1-8b-instruct-turbo (2 endpoints)131k$0.02–$0.18$0.03–$0.18––––
sambanova sambanova/​Meta-​Llama-​3.2-​1B-​Instructℹ️
meta-​llama-​3.2-​1b-​instruct
16k$0.04$0.08––––
sambanova sambanova/​Meta-​Llama-​3.2-​3B-​Instructℹ️
meta-​llama-​3.2-​3b-​instruct
4k$0.08$0.16––––
sambanova sambanova/​Meta-​Llama-​3.3-​70B-​Instructℹ️
meta-​llama-​3.3-​70b-​instruct
131k$0.60$1.20––––
sambanova sambanova/​Meta-​Llama-​Guard-​3-​8Bℹ️
meta-​llama-​guard-​3-​8b
16k$0.30$0.30––––
sagemakersagemaker/​meta-​textgeneration-​llama-​2-​13b-​f
meta-​textgeneration-​llama-​2-​13b-​f
4k$0.00$0.00––––
sagemakersagemaker/​meta-​textgeneration-​llama-​2-​70b-​b-​f
meta-​textgeneration-​llama-​2-​70b-​b-​f
4k$0.00$0.00––––
sagemakersagemaker/​meta-​textgeneration-​llama-​2-​7b-​f
meta-​textgeneration-​llama-​2-​7b-​f
4k$0.00$0.00––––
openrouter minimax/​minimax-​01
minimax-​01
1000k$0.20$1.10––––
openrouter minimax/​minimax-​m1
minimax-​m1
1000k$0.40$2.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​minimax-​m1-​80k
minimax-​m1-​80k
4k$0.10$0.10––––
openrouter, bedrock_converse, fireworks_ai ▶minimax-m2 (3 endpoints)4k–262k$0.254–$0.30$1.02–$1.20––––
vertex_ai-minimax_modelsvertex_ai/​minimaxai/​minimax-​m2-​maasℹ️
minimax-​m2-​maas
196k$0.30$1.20––––
openrouter mistralai/​ministral-​14b-​2512
ministral-​14b-​2512
262k$0.20$0.20––––
fireworks_ai, bedrock_converse ▶ministral-3-14b-instruct (2 endpoints)128k–256k$0.20$0.20––––
fireworks_ai, bedrock_converse ▶ministral-3-3b-instruct (2 endpoints)128k–256k$0.10$0.10––––
fireworks_ai, bedrock_converse ▶ministral-3-8b-instruct (2 endpoints)128k–256k$0.15–$0.20$0.15–$0.20––––
openrouter, azure_ai, vercel_ai_gateway ▶ministral-3b (4 endpoints)128k–131k$0.04–$0.10$0.04–$0.10––––
openrouter, vercel_ai_gateway ▶ministral-8b (3 endpoints)128k–262k$0.10–$0.15$0.10–$0.15––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​mistral-​7b
mistral-​7b
32k$0.20$0.20––––
openrouter, perplexity ▶mistral-7b-instruct (3 endpoints)4k–32k$0.00–$0.07$0.00–$0.28––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​mistral-​7b-​instruct-​4k
mistral-​7b-​instruct-​4k
32k$0.20$0.20––––
anyscale, cloudflare, openrouter ▶mistral-7b-instruct-v0.1 (3 endpoints)2k–16k$0.11–$1.923$0.15–$1.923––––
openrouter, bedrock, replicate ▶mistral-7b-instruct-v0.2 (6 endpoints)4k–32k$0.05–$0.20$0.20–$0.26––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​mistral-​7b-​instruct-​v0p2
mistral-​7b-​instruct-​v0p2
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​mistral-​7b-​instruct-​v3
mistral-​7b-​instruct-​v3
32k$0.20$0.20––––
replicate replicate/​mistralai/​mistral-​7b-​v0.1
mistral-​7b-​v0.1
4k$0.05$0.25––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​mistral-​7b-​v0p2
mistral-​7b-​v0p2
32k$0.20$0.20––––
vercel_ai_gatewayvercel_ai_gateway/​mistral/​mistral-​embed
mistral-​embed
0$0.10$0.00––––
vertex_ai-mistral_models vertex_ai/​mistral-​large@2411-​001
mistral-​large@2411-​001
128k$2.00$6.00––––
azure_ai, mistral ▶mistral-large-3 (2 endpoints)256k$0.50$1.50––––
bedrock_converse mistral.​mistral-​large-​3-​675b-​instruct
mistral-​large-​3-​675b-​instruct
128k$0.50$1.50––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​mistral-​large-​3-​fp8
mistral-​large-​3-​fp8
256k$1.20$1.20––––
vertex_ai-mistral_models vertex_ai/​mistral-​large@latest
mistral-​large@latest
128k$2.00$6.00––––
openrouter, vertex_ai-mistral_models ▶mistral-medium-3 (3 endpoints)128k–131k$0.40$2.00––––
vertex_ai-mistral_models ▶mistral-medium-3@001 (2 endpoints)128k$0.40$2.00––––
openrouter mistralai/​mistral-​medium-​3.1
mistral-​medium-​3.1
131k$0.40$2.00––––
openrouter, azure_ai, vertex_ai-mistral_models ▶mistral-nemo (3 endpoints)128k–131k$0.02–$3.00$0.04–$3.00––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​mistral-​nemo-​base-​2407
mistral-​nemo-​base-​2407
128k$0.20$0.20––––
deepinfra, fireworks_ai, ovhcloud, gradient_ai ▶mistral-nemo-instruct-2407 (4 endpoints)118k–131k$0.02–$0.30$0.04–$0.30––––
vertex_ai-mistral_models vertex_ai/​mistral-​nemo@latest
mistral-​nemo@latest
128k$0.15$0.15––––
openrouter mistralai/​mistral-​saba
mistral-​saba
32k$0.20$0.60––––
vercel_ai_gateway, groq ▶mistral-saba-24b (2 endpoints)32k–32k$0.79$0.79––––
openrouter, deepinfra, fireworks_ai ▶mistral-small-24b-instruct-2501 (3 endpoints)32k$0.03–$0.90$0.08–$0.90––––
vertex_ai-mistral_models vertex_ai/​mistral-​small-​2503@001
mistral-​small-​2503@001
32k$1.00$3.00––––
openrouter, watsonx ▶mistral-small-3.1-24b-instruct (3 endpoints)32k–131k$0.00–$0.10$0.00–$0.30––––
openrouter, deepinfra, ovhcloud ▶mistral-small-3.2-24b-instruct (3 endpoints)128k–131k$0.06–$0.09$0.18–$0.28––––
openrouter, mistral ▶mistral-tiny (2 endpoints)32k–32k$0.25$0.25––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​mixtral-​8x22b
mixtral-​8x22b
65k$1.20$1.20––––
fireworks_ai, vercel_ai_gateway, openrouter ▶mixtral-8x22b-instruct (4 endpoints)65k$1.20–$2.00$1.20–$6.00––––
anyscale, nscale ▶mixtral-8x22b-instruct-v0.1 (2 endpoints)65k$0.60–$0.90$0.60–$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​mixtral-​8x7b
mixtral-​8x7b
32k$0.50$0.50––––
groq groq/​mixtral-​8x7b-​32768
mixtral-​8x7b-​32768
32k$0.24$0.24––––
fireworks_ai, openrouter, perplexity ▶mixtral-8x7b-instruct (4 endpoints)4k–32k$0.07–$0.54$0.28–$0.54––––
moonshot ▶moonshot-v1-128k (2 endpoints)131k$2.00$5.00––––
moonshotmoonshot/​moonshot-​v1-​128k-​vision-​previewℹ️
moonshot-​v1-​128k-​vision-​preview
131k$2.00$5.00––––
moonshot ▶moonshot-v1-32k (2 endpoints)32k$1.00$3.00––––
moonshotmoonshot/​moonshot-​v1-​32k-​vision-​previewℹ️
moonshot-​v1-​32k-​vision-​preview
32k$1.00$3.00––––
moonshot ▶moonshot-v1-8k (2 endpoints)8k$0.20$2.00––––
moonshotmoonshot/​moonshot-​v1-​8k-​vision-​previewℹ️
moonshot-​v1-​8k-​vision-​preview
8k$0.20$2.00––––
moonshotmoonshot/​moonshot-​v1-​autoℹ️
moonshot-​v1-​auto
131k$2.00$5.00––––
openrouter, vercel_ai_gateway, morph ▶morph-v3-fast (3 endpoints)16k–81k$0.80$1.20––––
openrouter, vercel_ai_gateway, morph ▶morph-v3-large (3 endpoints)16k–262k$0.90$1.90––––
watsonx watsonx/​bigscience/​mt0-​xxl-​13b
mt0-​xxl-​13b
8k$500.00$2,000.00––––
openrouter, deepinfra, fireworks_ai ▶mythomax-l2-13b (3 endpoints)4k$0.06–$0.20$0.06–$0.20––––
bedrock_converse nvidia.​nemotron-​nano-​12b-​v2
nemotron-​nano-​12b-​v2
128k$0.20$0.60––––
openrouter ▶nemotron-nano-12b-v2-vl (2 endpoints)128k–131k$0.00–$0.20$0.00–$0.60––––
openrouter, bedrock_converse ▶nemotron-nano-9b-v2 (3 endpoints)128k–131k$0.00–$0.06$0.00–$0.23––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​nemotron-​nano-​v2-​12b-​vl
nemotron-​nano-​v2-​12b-​vl
4k$0.10$0.10––––
openrouter neversleep/​noromaid-​20b
noromaid-​20b
4k$1.00$1.75––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​nous-​capybara-​7b-​v1p9
nous-​capybara-​7b-​v1p9
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​nous-​hermes-​2-​mixtral-​8x7b-​dpo
nous-​hermes-​2-​mixtral-​8x7b-​dpo
32k$0.50$0.50––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​nous-​hermes-​2-​yi-​34b
nous-​hermes-​2-​yi-​34b
4k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​nous-​hermes-​llama2-​13b
nous-​hermes-​llama2-​13b
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​nous-​hermes-​llama2-​70b
nous-​hermes-​llama2-​70b
4k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​nous-​hermes-​llama2-​7b
nous-​hermes-​llama2-​7b
4k$0.20$0.20––––
openrouter ▶nova-2-lite-v1 (2 endpoints)1000k$0.00–$0.30$0.00–$2.50––––
bedrock_converse ▶nova-2-lite-v1.0 (5 endpoints)1000k$0.30–$0.33$2.50–$2.75––––
vercel_ai_gateway, bedrock_converse ▶nova-lite (5 endpoints)300k$0.06–$0.078$0.24–$0.312––––
amazon_nova, openrouter ▶nova-lite-v1 (2 endpoints)300k$0.06$0.24––––
vercel_ai_gateway, bedrock_converse ▶nova-micro (5 endpoints)128k$0.035–$0.046$0.14–$0.184––––
amazon_nova, openrouter ▶nova-micro-v1 (2 endpoints)128k$0.035$0.14––––
amazon_nova, openrouter ▶nova-premier-v1 (2 endpoints)1000k$2.50$12.50––––
bedrock_converse us.​amazon.​nova-​premier-​v1:0
nova-​premier-​v1.0
1000k$2.50$12.50––––
vercel_ai_gateway, bedrock_converse, bedrock ▶nova-pro (7 endpoints)300k$0.80–$1.05$3.20–$4.20––––
amazon_nova, openrouter ▶nova-pro-v1 (2 endpoints)300k$0.80$3.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​nvidia-​nemotron-​nano-​12b-​v2
nvidia-​nemotron-​nano-​12b-​v2
131k$0.20$0.20––––
deepinfra, fireworks_ai ▶nvidia-nemotron-nano-9b-v2 (2 endpoints)131k$0.04–$0.20$0.16–$0.20––––
openrouter openai/​o3-​deep-​research
o3-​deep-​research
200k$10.00$40.00––––
openrouter openai/​o4-​mini-​deep-​research
o4-​mini-​deep-​research
200k$2.00$8.00––––
openrouter allenai/​olmo-​2-​0325-​32b-​instruct
olmo-​2-​0325-​32b-​instruct
128k$0.05$0.20––––
openrouter, publicai ▶olmo-3-32b-think (2 endpoints)32k–65k$0.00$0.00––––
openrouter, publicai ▶olmo-3-7b-instruct (2 endpoints)32k–65k$0.00–$0.10$0.00–$0.20––––
openrouter, publicai ▶olmo-3-7b-think (2 endpoints)32k–65k$0.00–$0.12$0.00–$0.20––––
deepinfra deepinfra/​allenai/​olmOCR-​7B-​0725-​FP8
olmocr-​7b-​0725-​fp8
16k$0.27$1.50––––
gradient_aigradient_ai/​openai-​o3
openai-​o3
–$2.00$8.00––––
gradient_aigradient_ai/​openai-​o3-​mini
openai-​o3-​mini
–$1.10$4.40––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​openchat-​3p5-​0106-​7b
openchat-​3p5-​0106-​7b
8k$0.20$0.20––––
mistral mistral/​open-​codestral-​mambaℹ️
open-​codestral-​mamba
256k$0.25$0.25––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​openhermes-​2-​mistral-​7b
openhermes-​2-​mistral-​7b
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​openhermes-​2p5-​mistral-​7b
openhermes-​2p5-​mistral-​7b
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​openorca-​7b
openorca-​7b
32k$0.20$0.20––––
bedrock_converse ▶palmyra-x4-v1.0 (2 endpoints)128k$2.50$10.00––––
bedrock_converse ▶palmyra-x5-v1.0 (2 endpoints)1000k$0.60$6.00––––
bedrock ▶pegasus-1-2-v1.0 (3 endpoints)–N/A$7.50––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​phi-​2-​3b
phi-​2-​3b
2k$0.10$0.10––––
openrouter microsoft/​phi-​3.5-​mini-​128k-​instruct
phi-​3.5-​mini-​128k-​instruct
128k$0.10$0.10––––
azure_ai azure_ai/​Phi-​3.5-​mini-​instructℹ️
phi-​3.5-​mini-​instruct
128k$0.13$0.52––––
azure_ai azure_ai/​Phi-​3.5-​MoE-​instructℹ️
phi-​3.5-​moe-​instruct
128k$0.16$0.64––––
azure_ai azure_ai/​Phi-​3.5-​vision-​instructℹ️
phi-​3.5-​vision-​instruct
128k$0.13$0.52––––
azure_ai azure_ai/​Phi-​3-​medium-​4k-​instructℹ️
phi-​3-​medium-​4k-​instruct
4k$0.17$0.68––––
fireworks_ai, openrouter, azure_ai ▶phi-3-mini-128k-instruct (3 endpoints)128k–131k$0.10–$0.13$0.10–$0.52––––
azure_ai azure_ai/​Phi-​3-​mini-​4k-​instructℹ️
phi-​3-​mini-​4k-​instruct
4k$0.13$0.52––––
azure_ai azure_ai/​Phi-​3-​small-​128k-​instructℹ️
phi-​3-​small-​128k-​instruct
128k$0.15$0.60––––
azure_ai azure_ai/​Phi-​3-​small-​8k-​instructℹ️
phi-​3-​small-​8k-​instruct
8k$0.15$0.60––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​phi-​3-​vision-​128k-​instruct
phi-​3-​vision-​128k-​instruct
32k$0.20$0.20––––
azure_ai, wandb ▶phi-4-mini-instruct (2 endpoints)128k–131k$0.075–$8,000.00$0.30–$35,000.00––––
azure_ai azure_ai/​Phi-​4-​mini-​reasoningℹ️
phi-​4-​mini-​reasoning
131k$0.08$0.32––––
openrouter, azure_ai ▶phi-4-multimodal-instruct (2 endpoints)131k$0.05–$0.08$0.10–$0.32––––
azure_ai azure_ai/​Phi-​4-​reasoningℹ️
phi-​4-​reasoning
32k$0.125$0.50––––
openrouter microsoft/​phi-​4-​reasoning-​plus
phi-​4-​reasoning-​plus
32k$0.07$0.35––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​phind-​code-​llama-​34b-​python-​v1
phind-​code-​llama-​34b-​python-​v1
16k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​phind-​code-​llama-​34b-​v1
phind-​code-​llama-​34b-​v1
16k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​phind-​code-​llama-​34b-​v2
phind-​code-​llama-​34b-​v2
16k$0.90$0.90––––
vercel_ai_gateway, mistral, watsonx, openrouter ▶pixtral-12b (4 endpoints)32k–128k$0.10–$0.35$0.10–$0.35––––
openrouter, vercel_ai_gateway, mistral, bedrock_converse ▶pixtral-large (6 endpoints)128k–131k$2.00$6.00––––
perplexity perplexity/​pplx-​70b-​chat
pplx-​70b-​chat
4k$0.70$2.80––––
perplexity perplexity/​pplx-​70b-​online
pplx-​70b-​online
4k$0.00$2.80––––
perplexity perplexity/​pplx-​7b-​chat
pplx-​7b-​chat
8k$0.07$0.28––––
perplexity perplexity/​pplx-​7b-​online
pplx-​7b-​online
4k$0.00$0.28––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​pythia-​12b
pythia-​12b
2k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen1p5-​72b-​chat
qwen1p5-​72b-​chat
32k$0.90$0.90––––
deepinfra, openrouter ▶qwen2.5-7b-instruct (2 endpoints)32k$0.04$0.10––––
lambda_ai, lambda, openrouter, hyperbolic, ovhcloud, nscale ▶qwen25-coder-32b-instruct (6 endpoints)32k–131k$0.03–$0.87$0.10–$0.87–––16.4%
nscalenscale/​Qwen/​Qwen2.5-​Coder-​3B-​Instructℹ️
qwen2.5-​coder-​3b-​instruct
–$0.01$0.03––––
openrouter, nscale ▶qwen2.5-coder-7b-instruct (2 endpoints)32k$0.01–$0.03$0.03–$0.09––––
deepinfra, openrouter ▶qwen2.5-vl-32b-instruct (2 endpoints)16k–128k$0.05–$0.20$0.22–$0.60––––
openrouter, ovhcloud ▶qwen2.5-vl-72b-instruct (2 endpoints)32k–32k$0.03–$0.91$0.13–$0.91––––
openrouter qwen/​qwen-​2.5-​vl-​7b-​instruct
qwen-​2.5-​vl-​7b-​instruct
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2-​7b-​instruct
qwen2-​7b-​instruct
32k$0.20$0.20––––
sambanova sambanova/​Qwen2-​Audio-​7B-​Instructℹ️
qwen2-​audio-​7b-​instruct
4k$0.50$100.00––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​0p5b-​instruct
qwen2p5-​0p5b-​instruct
32k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​14b
qwen2p5-​14b
131k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​1p5b-​instruct
qwen2p5-​1p5b-​instruct
32k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​32b
qwen2p5-​32b
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​32b-​instruct
qwen2p5-​32b-​instruct
32k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​72b
qwen2p5-​72b
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​72b-​instruct
qwen2p5-​72b-​instruct
32k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​7b-​instruct
qwen2p5-​7b-​instruct
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​0p5b
qwen2p5-​coder-​0p5b
32k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​0p5b-​instruct
qwen2p5-​coder-​0p5b-​instruct
32k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​14b
qwen2p5-​coder-​14b
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​14b-​instruct
qwen2p5-​coder-​14b-​instruct
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​1p5b
qwen2p5-​coder-​1p5b
32k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​1p5b-​instruct
qwen2p5-​coder-​1p5b-​instruct
32k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​32b
qwen2p5-​coder-​32b
32k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​32b-​instructℹ️
qwen2p5-​coder-​32b-​instruct
4k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​32b-​instruct-​128k
qwen2p5-​coder-​32b-​instruct-​128k
131k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​32b-​instruct-​32k-​rope
qwen2p5-​coder-​32b-​instruct-​32k-​rope
32k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​32b-​instruct-​64k
qwen2p5-​coder-​32b-​instruct-​64k
65k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​3b
qwen2p5-​coder-​3b
32k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​3b-​instruct
qwen2p5-​coder-​3b-​instruct
32k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​7b
qwen2p5-​coder-​7b
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​coder-​7b-​instruct
qwen2p5-​coder-​7b-​instruct
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​math-​72b-​instruct
qwen2p5-​math-​72b-​instruct
4k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​vl-​32b-​instruct
qwen2p5-​vl-​32b-​instruct
128k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​vl-​3b-​instruct
qwen2p5-​vl-​3b-​instruct
128k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​vl-​72b-​instruct
qwen2p5-​vl-​72b-​instruct
128k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2p5-​vl-​7b-​instruct
qwen2p5-​vl-​7b-​instruct
128k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2-​vl-​2b-​instruct
qwen2-​vl-​2b-​instruct
32k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2-​vl-​72b-​instruct
qwen2-​vl-​72b-​instruct
32k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen2-​vl-​7b-​instruct
qwen2-​vl-​7b-​instruct
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen3-​0p6b
qwen3-​0p6b
40k$0.10$0.10––––
openrouter, deepinfra, vercel_ai_gateway, fireworks_ai ▶qwen3-14b (4 endpoints)40k$0.05–$0.20$0.20–$0.24––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen3-​1p7b
qwen3-​1p7b
131k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen3-​1p7b-​fp8-​draft
qwen3-​1p7b-​fp8-​draft
262k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen3-​1p7b-​fp8-​draft-​131072
qwen3-​1p7b-​fp8-​draft-​131072
131k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen3-​1p7b-​fp8-​draft-​40960
qwen3-​1p7b-​fp8-​draft-​40960
40k$0.10$0.10––––
vercel_ai_gatewayvercel_ai_gateway/​alibaba/​qwen-​3-​235b
qwen-​3-​235b
40k$0.20$0.60––––
together_ai together_ai/​Qwen/​Qwen3-​235B-​A22B-​fp8-​tputℹ️
qwen3-​235b-​a22b-​fp8-​tput
40k$0.20$0.60––––
deepinfra, fireworks_ai, wandb ▶qwen3-235b-a22b-instruct-2507 (3 endpoints)262k$0.09–$10,000.00$0.60–$10,000.00––––
vertex_ai-qwen_modelsvertex_ai/​qwen/​qwen3-​235b-​a22b-​instruct-​2507-​maasℹ️
qwen3-​235b-​a22b-​instruct-​2507-​maas
262k$0.25$1.00––––
together_ai together_ai/​Qwen/​Qwen3-​235B-​A22B-​Instruct-​2507-​tputℹ️
qwen3-​235b-​a22b-​instruct-​2507-​tput
262k$0.20$6.00––––
openrouter, fireworks_ai, deepinfra, wandb, together_ai ▶qwen3-235b-a22b-thinking-2507 (5 endpoints)256k–262k$0.11–$10,000.00$0.60–$10,000.00––––
vercel_ai_gatewayvercel_ai_gateway/​alibaba/​qwen-​3-​30b
qwen-​3-​30b
40k$0.10$0.30––––
fireworks_ai, openrouter, deepinfra ▶qwen3-30b-a3b (3 endpoints)40k–131k$0.06–$0.15$0.22–$0.60––––
openrouter, fireworks_ai ▶qwen3-30b-a3b-instruct-2507 (2 endpoints)262k$0.08–$0.50$0.33–$0.50––––
fireworks_ai, openrouter ▶qwen3-30b-a3b-thinking-2507 (2 endpoints)32k–262k$0.051–$0.90$0.34–$0.90––––
bedrock_converse, fireworks_ai, groq, cerebras, openrouter, deepinfra, vercel_ai_gateway, ovhcloud, sambanova ▶qwen3-32b (9 endpoints)8k–131k$0.08–$0.90$0.23–$0.90–––40%
lambda_ailambda_ai/​qwen3-​32b-​fp8
qwen3-​32b-​fp8
131k$0.05$0.10––––
openrouter, fireworks_ai ▶qwen3-4b (2 endpoints)40k$0.00–$0.20$0.00–$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen3-​4b-​instruct-​2507
qwen3-​4b-​instruct-​2507
262k$0.20$0.20––––
lemonadelemonade/​Qwen3-​4B-​Instruct-​2507-​GGUF
qwen3-​4b-​instruct-​2507-​gguf
262k$0.00$0.00––––
openrouter, fireworks_ai ▶qwen3-8b (2 endpoints)40k–128k$0.028–$0.20$0.1104–$0.20––––
openrouter, vercel_ai_gateway ▶qwen3-coder (3 endpoints)262k–262k$0.00–$0.40$0.00–$1.60––––
openrouter, fireworks_ai ▶qwen3-coder-30b-a3b-instruct (2 endpoints)262k$0.06–$0.15$0.25–$0.60––––
lemonadelemonade/​Qwen3-​Coder-​30B-​A3B-​Instruct-​GGUF
qwen3-​coder-​30b-​a3b-​instruct-​gguf
262k$0.00$0.00––––
bedrock_converse qwen.​qwen3-​coder-​30b-​a3b-​v1:0
qwen3-​coder-​30b-​a3b-​v1.0
262k$0.15$0.60––––
deepinfra, fireworks_ai, wandb ▶qwen3-coder-480b-a35b-instruct (3 endpoints)262k$0.40–$100,000.00$1.60–$150,000.00––––
together_ai together_ai/​Qwen/​Qwen3-​Coder-​480B-​A35B-​Instruct-​FP8ℹ️
qwen3-​coder-​480b-​a35b-​instruct-​fp8
256k$2.00$2.00––––
vertex_ai-qwen_modelsvertex_ai/​qwen/​qwen3-​coder-​480b-​a35b-​instruct-​maasℹ️
qwen3-​coder-​480b-​a35b-​instruct-​maas
262k$1.00$4.00––––
deepinfra deepinfra/​Qwen/​Qwen3-​Coder-​480B-​A35B-​Instruct-​Turbo
qwen3-​coder-​480b-​a35b-​instruct-​turbo
262k$0.29$1.20––––
bedrock_converse qwen.​qwen3-​coder-​480b-​a35b-​v1:0
qwen3-​coder-​480b-​a35b-​v1.0
262k$0.22$1.80––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen3-​coder-​480b-​instruct-​bf16
qwen3-​coder-​480b-​instruct-​bf16
4k$0.90$0.90––––
openrouter qwen/​qwen3-​coder:exacto
qwen3-​coder:exacto
262k$0.38$1.53––––
openrouter qwen/​qwen3-​coder-​flash
qwen3-​coder-​flash
128k$0.30$1.50––––
openrouter qwen/​qwen3-​coder-​plus
qwen3-​coder-​plus
128k$1.00$5.00––––
openrouter qwen/​qwen3-​max
qwen3-​max
256k$1.20$6.00––––
bedrock_converse qwen.​qwen3-​next-​80b-​a3b
qwen3-​next-​80b-​a3b
128k$0.15$1.20––––
openrouter, deepinfra, together_ai, fireworks_ai ▶qwen3-next-80b-a3b-instruct (4 endpoints)4k–262k$0.09–$0.90$0.90–$1.50––––
vertex_ai-qwen_modelsvertex_ai/​qwen/​qwen3-​next-​80b-​a3b-​instruct-​maasℹ️
qwen3-​next-​80b-​a3b-​instruct-​maas
262k$0.15$1.20––––
deepinfra, together_ai, openrouter, fireworks_ai ▶qwen3-next-80b-a3b-thinking (4 endpoints)4k–262k$0.12–$0.90$0.90–$1.50––––
vertex_ai-qwen_modelsvertex_ai/​qwen/​qwen3-​next-​80b-​a3b-​thinking-​maasℹ️
qwen3-​next-​80b-​a3b-​thinking-​maas
262k$0.15$1.20––––
bedrock_converse qwen.​qwen3-​vl-​235b-​a22b
qwen3-​vl-​235b-​a22b
128k$0.53$2.66––––
openrouter, fireworks_ai ▶qwen3-vl-235b-a22b-instruct (2 endpoints)262k$0.20–$0.22$0.88–$1.20––––
fireworks_ai, openrouter ▶qwen3-vl-235b-a22b-thinking (2 endpoints)262k$0.22–$0.30$0.88–$1.20––––
fireworks_ai, openrouter ▶qwen3-vl-30b-a3b-instruct (2 endpoints)131k–262k$0.14–$0.15$0.60–$1.00––––
fireworks_ai, openrouter ▶qwen3-vl-30b-a3b-thinking (2 endpoints)131k–262k$0.15–$0.16$0.60–$0.80––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen3-​vl-​32b-​instruct
qwen3-​vl-​32b-​instruct
4k$0.90$0.90––––
openrouter, fireworks_ai ▶qwen3-vl-8b-instruct (2 endpoints)4k–131k$0.064–$0.20$0.20–$0.40––––
openrouter qwen/​qwen3-​vl-​8b-​thinking
qwen3-​vl-​8b-​thinking
256k$0.18$2.10––––
dashscopedashscope/​qwen-​coderℹ️
qwen-​coder
1000k$0.30$1.50––––
openrouter, dashscope ▶qwen-max (2 endpoints)30k–32k$1.60$6.40––––
openrouter qwen/​qwen-​plus-​2025-​07-​28:thinking
qwen-​plus-​2025-​07-​28:thinking
1000k$0.40$4.00––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen-​qwq-​32b-​preview
qwen-​qwq-​32b-​preview
32k$0.90$0.90––––
publicaipublicai/​aisingapore/​Qwen-​SEA-​LION-​v4-​32B-​ITℹ️
qwen-​sea-​lion-​v4-​32b-​it
32k$0.00$0.00––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen-​v2p5-​14b-​instruct
qwen-​v2p5-​14b-​instruct
32k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​qwen-​v2p5-​7b
qwen-​v2p5-​7b
131k$0.20$0.20––––
openrouter qwen/​qwen-​vl-​max
qwen-​vl-​max
131k$0.80$3.20––––
openrouter qwen/​qwen-​vl-​plus
qwen-​vl-​plus
7k$0.21$0.63––––
deepinfra, hyperbolic, fireworks_ai, openrouter, sambanova, nscale ▶qwq-32b (6 endpoints)16k–131k$0.15–$0.90$0.20–$1.00–––20.9%
openrouter arliai/​qwq-​32b-​arliai-​rpr-​v1
qwq-​32b-​arliai-​rpr-​v1
32k$0.03$0.11––––
openrouter relace/​relace-​apply-​3
relace-​apply-​3
256k$0.85$1.25––––
openrouter relace/​relace-​search
relace-​search
256k$1.00$3.00––––
openrouter undi95/​remm-​slerp-​l2-​13b
remm-​slerp-​l2-​13b
6k$0.45$0.65––––
openrouter essentialai/​rnj-​1-​instruct
rnj-​1-​instruct
32k$0.15$0.15––––
openrouter thedrummer/​rocinante-​12b
rocinante-​12b
32k$0.17$0.43––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​rolm-​ocr
rolm-​ocr
128k$0.20$0.20––––
openrouter switchpoint/​router
router
131k$0.85$3.40––––
publicaipublicai/​BSC-​LT/​salamandra-​7b-​instruct-​tools-​16kℹ️
salamandra-​7b-​instruct-​tools-​16k
16k$0.00$0.00––––
openrouter thedrummer/​skyfall-​36b-​v2
skyfall-​36b-​v2
32k$0.55$0.80––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​snorkel-​mistral-​7b-​pairrm-​dpo
snorkel-​mistral-​7b-​pairrm-​dpo
32k$0.20$0.20––––
perplexity, openrouter, vercel_ai_gateway ▶sonar (3 endpoints)127k–128k$1.00$1.00––––
perplexity, openrouter ▶sonar-deep-research (2 endpoints)128k$2.00$8.00––––
perplexity perplexity/​sonar-​medium-​chat
sonar-​medium-​chat
16k$0.60$1.80––––
perplexity perplexity/​sonar-​medium-​online
sonar-​medium-​online
12k$0.00$1.80––––
perplexity, vercel_ai_gateway, openrouter ▶sonar-pro (3 endpoints)200k$3.00$15.00––––
openrouter perplexity/​sonar-​pro-​search
sonar-​pro-​search
200k$3.00$15.00––––
perplexity, vercel_ai_gateway, openrouter ▶sonar-reasoning (3 endpoints)127k–128k$1.00$5.00––––
perplexity, openrouter, vercel_ai_gateway ▶sonar-reasoning-pro (3 endpoints)127k–128k$2.00$8.00––––
perplexity perplexity/​sonar-​small-​chat
sonar-​small-​chat
16k$0.07$0.28––––
perplexity perplexity/​sonar-​small-​online
sonar-​small-​online
12k$0.00$0.28––––
openrouter raifle/​sorcererlm-​8x22b
sorcererlm-​8x22b
16k$4.50$4.50––––
openrouter arcee-​ai/​spotlight
spotlight
131k$0.18$0.18––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​stablecode-​3b
stablecode-​3b
4k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​starcoder-​16b
starcoder-​16b
8k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​starcoder2-​15b
starcoder2-​15b
16k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​starcoder2-​3b
starcoder2-​3b
16k$0.10$0.10––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​starcoder2-​7b
starcoder2-​7b
16k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​starcoder-​7b
starcoder-​7b
8k$0.20$0.20––––
openrouter stepfun-​ai/​step3
step3
65k$0.57$1.42––––
vercel_ai_gatewayvercel_ai_gateway/​amazon/​titan-​embed-​text-​v2
titan-​embed-​text-​v2
0$0.02$0.00––––
bedrock ▶titan-text-express-v1 (3 endpoints)42k$1.30$1.70––––
bedrock ▶titan-text-lite-v1 (3 endpoints)42k$0.30$0.40––––
bedrock ▶titan-text-premier-v1.0 (3 endpoints)42k$0.50$1.50––––
openrouter ▶tng-r1t-chimera (2 endpoints)163k$0.00–$0.30$0.00–$1.20––––
together_ai together-​ai-​21.1b-​41b–$0.80$0.80––––
together_ai together-​ai-​41.1b-​80b–$0.90$0.90––––
together_ai together-​ai-​4.1b-​8b–$0.20$0.20––––
together_ai together-​ai-​81.1b-​110b–$1.80$1.80––––
together_ai together-​ai-​8.1b-​21b–$0.30$0.30––––
together_ai together-​ai-​up-​to-​4b–$0.10$0.10––––
openrouter ▶tongyi-deepresearch-30b-a3b (2 endpoints)131k$0.00–$0.09$0.00–$0.40––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​toppy-​m-​7b
toppy-​m-​7b
32k$0.20$0.20––––
openrouter ▶trinity-mini (2 endpoints)131k$0.00–$0.045$0.00–$0.15––––
openrouter bytedance/​ui-​tars-​1.5-​7b
ui-​tars-​1.5-​7b
128k$0.10$0.20––––
openrouter thedrummer/​unslopnemo-​12b
unslopnemo-​12b
32k$0.40$0.40––––
v0, vercel_ai_gateway ▶v0-1.0-md (2 endpoints)128k$3.00$15.00––––
v0v0/​v0-​1.5-​lg
v0-​1.5-​lg
512k$15.00$75.00––––
v0, vercel_ai_gateway ▶v0-1.5-md (2 endpoints)128k$3.00$15.00––––
bedrock_converse deepseek.​v3-​v1:0
v3-​v1.0
163k$0.58$1.68––––
openrouter arcee-​ai/​virtuoso-​large
virtuoso-​large
131k$0.75$1.20––––
bedrock_converse mistral.​voxtral-​mini-​3b-​2507
voxtral-​mini-​3b-​2507
128k$0.04$0.04––––
bedrock_converse, openrouter ▶voxtral-small-24b-2507 (2 endpoints)32k–128k$0.10$0.30––––
openrouter mancer/​weaver
weaver
8k$1.125$1.125––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​yi-​34b
yi-​34b
4k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​yi-​34b-​200k-​capybara
yi-​34b-​200k-​capybara
200k$0.90$0.90––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​yi-​6b
yi-​6b
4k$0.20$0.20––––
fireworks_ai fireworks_ai/​accounts/​fireworks/​models/​yi-​largeℹ️
yi-​large
32k$3.00$3.00––––
cerebras cerebras/​zai-​glm-​4.6ℹ️
zai-​glm-​4.6
128k$2.25$2.75––––
fireworks_ai, anyscale ▶zephyr-7b-beta (2 endpoints)16k–32k$0.15–$0.20$0.15–$0.20––––