Changes

New models, price changes and deprecations found each time the data is rebuilt. Follow along with the Atom feed.

History is young: 4 days shown, last built 2026-10-20 03:37 UTC. Large counts on the earliest days can reflect catalogue changes in the sources, not real launches. Price changes are only detected between two consecutive builds.

Possible data errors (70)

Price moves of more than +300%, falls to under a quarter of the old price (including to $0), and prices the price-sanity check flags. These usually come from a unit or source error, so they are kept out of the day lists below and out of the Atom feed until the next builds confirm them.

Day	Model	Provider	Price	Was	Now	Change	Why flagged
2026-10-16	GLM-5.2	OpenRouter	input	$0.02	$0.62	+3000%	price rose 31x (more than +300%)
2026-10-16	DeepSeek V4 Flash	Merge Gateway	output	$0.07	$1.20	+1614.3%	price rose 17.1x (more than +300%)
2026-10-17	GLM-5.3	Relace	input	$0.0608	$0.75	+1133.5%	price rose 12.3x (more than +300%)
2026-10-17	DeepSeek V4 Flash Latest	OpenRouter	input	$0.0058	$0.07	+1106.9%	price rose 12.1x (more than +300%)
2026-10-17	DeepSeek V4 Flash Latest	Relace	input	$0.0058	$0.07	+1106.9%	price rose 12.1x (more than +300%)
2026-10-17	GLM-5.2	Relace	input	$0.0351	$0.40	+1039.6%	price rose 11.4x (more than +300%)
2026-10-16	DeepSeek V4 Flash	Merge Gateway	input	$0.035	$0.30	+757.1%	price rose 8.6x (more than +300%)
2026-10-16	deepseek/deepseek-v4-1-flash-batch	Relace	input	$0.0264	$0.20	+657.6%	price rose 7.6x (more than +300%)
2026-10-16	DeepSeek V4.1 Flash	Relace	input	$0.0264	$0.20	+657.6%	price rose 7.6x (more than +300%)
2026-10-17	DeepSeek V4 Flash Latest	Sail Research	input	$0.019	$0.10	+426.3%	price rose 5.3x (more than +300%)
2026-10-16	DeepSeek V4 Pro 0813	NanoGPT	output	$0.99	$2.50	+152.5%	price-sanity check: outside the 0.2x-5x band: input 0.11x the median of 38 direct rows, output 0.11x the median of 38 direct rows
2026-10-19	GLM-5.3	AIHubMix	input	$0.06	$0	−100%	price fell to $0
2026-10-19	GLM-5.3	AIHubMix	output	$0.22	$0	−100%	price fell to $0
2026-10-17	Beam 1.0	Vercel AI Gateway	input	$1.30	$0	−100%	price fell to $0
2026-10-17	Beam 1.0	Vercel AI Gateway	output	$4.30	$0	−100%	price fell to $0
2026-10-16	Qwen3.8-27B	IteraCompute	input	$0.30	$0	−100%	price fell to $0
2026-10-16	Qwen3.8-27B	IteraCompute	output	$2.50	$0	−100%	price fell to $0
2026-10-17	DeepSeek V4 Flash	OpenInference	output	$1.15	$0.0363	−96.8%	price fell to 0.03x (more than a 4x drop)
2026-10-16	GLM-5.3-Flash	OpenRouter	input	$0.15	$0.0113	−92.5%	price fell to 0.07x (more than a 4x drop)
2026-10-19	GPT-OSS 120B	NanoGPT	input	$0.35	$0.03	−91.4%	price fell to 0.09x (more than a 4x drop)
2026-10-19	DeepSeek V4 Flash Latest	Relace	input	$0.07	$0.0065	−90.7%	price fell to 0.09x (more than a 4x drop)
2026-10-19	GPT OSS 20B	NanoGPT	input	$0.20	$0.02	−90%	price fell to 0.1x (more than a 4x drop)
2026-10-17	DeepSeek V4 Flash Latest	OpenRouter	output	$1.28	$0.14	−89.1%	price fell to 0.11x (more than a 4x drop)
2026-10-17	DeepSeek V4 Flash Latest	Relace	output	$1.28	$0.14	−89.1%	price fell to 0.11x (more than a 4x drop)
2026-10-19	DeepSeek V4 Pro 0813	NanoGPT	input	$1.10	$0.145	−86.8%	price fell to 0.13x (more than a 4x drop)
2026-10-19	DeepSeek Latest	NanoGPT	input	$1.10	$0.145	−86.8%	price fell to 0.13x (more than a 4x drop)
2026-10-16	DeepSeek V4 Flash Latest	Baidu	input	$0.44	$0.0598	−86.4%	price fell to 0.14x (more than a 4x drop)
2026-10-16	DeepSeek V4 Flash Latest	Baidu	output	$1.32	$0.18	−86.4%	price fell to 0.14x (more than a 4x drop)
2026-10-19	MiniMax-M2.7	AIHubMix	output	$1.20	$0.20	−83.3%	price fell to 0.17x (more than a 4x drop)
2026-10-19	DeepSeek V4.1 Flash	Relace	output	$0.60	$0.10	−83.3%	price fell to 0.17x (more than a 4x drop)
2026-10-16	Llama 3.3 70b Instruct	OpenRouter	input	$0.59	$0.10	−83%	price fell to 0.17x (more than a 4x drop)
2026-10-17	DeepSeek V4 Flash Latest	OpenInference	output	$1.15	$0.20	−82.6%	price fell to 0.17x (more than a 4x drop)
2026-10-19	DeepSeek V4 Pro 0813	NanoGPT	output	$2.50	$0.436	−82.6%	price fell to 0.17x (more than a 4x drop)
2026-10-19	DeepSeek Latest	NanoGPT	output	$2.50	$0.436	−82.6%	price fell to 0.17x (more than a 4x drop)
2026-10-16	DeepSeek V4 Pro 0813	Baidu	input	$1.32	$0.249	−81.1%	price fell to 0.19x (more than a 4x drop)
2026-10-16	DeepSeek V4 Pro 0813	Baidu	output	$3.96	$0.748	−81.1%	price fell to 0.19x (more than a 4x drop)
2026-10-19	Qwen3.8-27B	Wafer	input	$0.20	$0.04	−80%	price fell to 0.2x (more than a 4x drop)
2026-10-19	GPT-OSS 120B	NanoGPT	output	$0.75	$0.15	−80%	price fell to 0.2x (more than a 4x drop)
2026-10-16	DeepSeek V4 Pro	Baidu	input	$1.69	$0.346	−79.5%	price fell to 0.2x (more than a 4x drop)
2026-10-16	DeepSeek V4 Pro	Baidu	output	$3.38	$0.693	−79.5%	price fell to 0.2x (more than a 4x drop)
2026-10-19	moonshotai/kimi-k3-batch	Relace	output	$14	$3.00	−78.6%	price fell to 0.21x (more than a 4x drop)
2026-10-19	Kimi K3	Relace	output	$14	$3.00	−78.6%	price fell to 0.21x (more than a 4x drop)
2026-10-19	DeepSeek V4 Pro 0813	Relace	input	$0.60	$0.131	−78.2%	price fell to 0.22x (more than a 4x drop)
2026-10-17	zhipuai/glm-5-3-flash-batch	OpenInference	output	$0.90	$0.20	−77.8%	price fell to 0.22x (more than a 4x drop)
2026-10-17	GLM-5.3-Flash	OpenInference	output	$0.90	$0.20	−77.8%	price fell to 0.22x (more than a 4x drop)
2026-10-17	GLM-5.3-Flash	OpenRouter	output	$0.90	$0.20	−77.8%	price fell to 0.22x (more than a 4x drop)
2026-10-19	GLM-5.3	OpenRouter	output	$4.80	$1.40	−70.8%	price-sanity check: outside the 0.2x-5x band: input 0.06x the median of 71 direct rows
2026-10-17	DeepSeek V4.1 Flash	OpenRouter	output	$0.663	$0.20	−69.8%	price-sanity check: outside the 0.2x-5x band: input 0.12x the median of 60 direct rows, output 0.07x the median of 60 direct rows
2026-10-19	DeepSeek V4.1 Flash	OpenRouter	output	$0.20	$0.08	−60%	price-sanity check: outside the 0.2x-5x band: input 0.12x the median of 60 direct rows, output 0.07x the median of 60 direct rows
2026-10-16	Llama 3.3 70b Instruct	OpenRouter	output	$0.79	$0.32	−59.5%	price-sanity check: outside the 0.2x-5x band: input 0.17x the median of 44 direct rows
2026-10-16	DeepSeek V4.1 Flash	OpenRouter	input	$0.0238	$0.036	+51.5%	price-sanity check: outside the 0.2x-5x band: input 0.12x the median of 60 direct rows, output 0.07x the median of 60 direct rows
2026-10-19	GPT-6.1 Sol Pro	OpenAI	input	$1.00	$0.50	−50%	price-sanity check: not listed by the vendor, no pricing entry and the model page returns 404; "pro" is a reasoning mode of the base model (https://developers.openai.com/api/docs/deprecations)
2026-10-19	GPT-6.1 Sol Pro	OpenAI	output	$5.00	$2.50	−50%	price-sanity check: not listed by the vendor, no pricing entry and the model page returns 404; "pro" is a reasoning mode of the base model (https://developers.openai.com/api/docs/deprecations)
2026-10-19	GPT-6 Astra Pro	OpenAI	input	$5.00	$2.50	−50%	price-sanity check: not listed by the vendor, no pricing entry and the model page returns 404; "pro" is a reasoning mode of the base model (https://developers.openai.com/api/docs/deprecations)
2026-10-19	GPT-6 Astra Pro	OpenAI	output	$25	$12.50	−50%	price-sanity check: not listed by the vendor, no pricing entry and the model page returns 404; "pro" is a reasoning mode of the base model (https://developers.openai.com/api/docs/deprecations)
2026-10-19	GPT-6 Luna Pro	OpenAI	input	$0.05	$0.025	−50%	price-sanity check: not listed by the vendor, no pricing entry and the model page returns 404; "pro" is a reasoning mode of the base model (https://developers.openai.com/api/docs/deprecations)
2026-10-19	GPT-6 Luna Pro	OpenAI	output	$0.25	$0.125	−50%	price-sanity check: not listed by the vendor, no pricing entry and the model page returns 404; "pro" is a reasoning mode of the base model (https://developers.openai.com/api/docs/deprecations)
2026-10-19	GPT-6 Sol Pro	OpenAI	input	$1.00	$0.50	−50%	price-sanity check: not listed by the vendor, no pricing entry and the model page returns 404; "pro" is a reasoning mode of the base model (https://developers.openai.com/api/docs/deprecations)
2026-10-19	GPT-6 Sol Pro	OpenAI	output	$5.00	$2.50	−50%	price-sanity check: not listed by the vendor, no pricing entry and the model page returns 404; "pro" is a reasoning mode of the base model (https://developers.openai.com/api/docs/deprecations)
2026-10-19	MiniMax-M2.7	AIHubMix	input	$0.30	$0.20	−33.3%	price-sanity check: outside the 0.2x-5x band: output 0.17x the median of 18 direct rows
2026-10-16	Kimi K3	OpenRouter	input	$0.45	$0.304	−32.4%	price-sanity check: outside the 0.2x-5x band: input 0.08x the median of 58 direct rows
2026-10-16	DeepSeek V4 Pro 0813	NanoGPT	input	$0.896	$1.10	+22.8%	price-sanity check: outside the 0.2x-5x band: input 0.11x the median of 38 direct rows, output 0.11x the median of 38 direct rows
2026-10-19	Kimi K3	OpenRouter	input	$0.304	$0.239	−21.4%	price-sanity check: outside the 0.2x-5x band: input 0.08x the median of 58 direct rows
2026-10-16	Kimi K3	OpenRouter	output	$15	$12.53	−16.4%	price-sanity check: outside the 0.2x-5x band: input 0.08x the median of 58 direct rows
2026-10-17	DeepSeek V4.1 Flash	OpenRouter	input	$0.036	$0.032	−11.1%	price-sanity check: outside the 0.2x-5x band: input 0.12x the median of 60 direct rows, output 0.07x the median of 60 direct rows
2026-10-16	DeepSeek V4.1 Flash	OpenRouter	output	$0.72	$0.663	−7.9%	price-sanity check: outside the 0.2x-5x band: input 0.12x the median of 60 direct rows, output 0.07x the median of 60 direct rows
2026-10-17	Kimi K3	OpenRouter	output	$12.53	$11.94	−4.8%	price-sanity check: outside the 0.2x-5x band: input 0.08x the median of 58 direct rows
2026-10-19	DeepSeek V4.1 Flash	OpenRouter	input	$0.032	$0.0328	+2.5%	price-sanity check: outside the 0.2x-5x band: input 0.12x the median of 60 direct rows, output 0.07x the median of 60 direct rows
2026-10-19	Llama 3.2 3B Instruct	OpenRouter	input	$0.05	$0.0509	+1.8%	price-sanity check: outside the 0.2x-5x band: output 6.7x the median of 7 direct rows
2026-10-19	Llama 3.2 3B Instruct	OpenRouter	output	$0.33	$0.335	+1.5%	price-sanity check: outside the 0.2x-5x band: output 6.7x the median of 7 direct rows

2026-10-20

5 deprecations · 0 endpoints added, 0 removed

Deprecations (5)

Gemini 2.5 Flash-LiteOpenRouter retires 2026-10-20
Gemini 2.5 FlashOpenRouter retires 2026-10-20
Gemini 2.5 FlashOpenRouter retires 2026-10-20
Gemini 2.5 ProOpenRouter retires 2026-10-20
Gemini 2.5 ProOpenRouter retires 2026-10-20

2026-10-19

362 price changes · 83 models added · 178 deprecations · 62 plan changes · 5 models no longer listed · 31 flagged as possible errors · 149 endpoints added, 771 removed

Price changes (362)

Model	Provider	Price	Was	Now	Change
DeepSeek V4 Flash	OpenInference	output per 1M tokens	$0.0363	$0.136	+274.8% increase
GLM-5.3-Flash	Morph	input per 1M tokens	$0.05	$0.177	+254% increase
GLM-5.2	Baidu	input per 1M tokens	$0.189	$0.619	+227.4% increase
GLM-5.2	Baidu	output per 1M tokens	$0.594	$1.94	+227.4% increase
DeepSeek V4 Flash Latest	Relace	output per 1M tokens	$0.14	$0.45	+221.4% increase
MiMo-V2.5	AIHubMix	output per 1M tokens	$0.16	$0.40	+150% increase
DeepSeek V4 Flash	StreamLake	input per 1M tokens	$0.028	$0.07	+150% increase
DeepSeek V4 Flash	StreamLake	output per 1M tokens	$0.056	$0.14	+150% increase
DeepSeek V4 Flash Latest	Cortecs	output per 1M tokens	$0.17	$0.413	+142.9% increase
GLM-5.3	Baidu	input per 1M tokens	$0.599	$1.40	+133.6% increase
GLM-5.3	Baidu	output per 1M tokens	$1.88	$4.40	+133.6% increase
moonshotai/kimi-k3-batch	Relace	input per 1M tokens	$0.35	$0.80	+128.6% increase
Kimi K3	Relace	input per 1M tokens	$0.35	$0.80	+128.6% increase
Ministral 3 14B	Eden AI	output per 1M tokens	$0.20	$0.45	+125.1% increase
DeepSeek V4 Flash Latest	Baidu	input per 1M tokens	$0.0598	$0.13	+116.9% increase
DeepSeek V4 Flash Latest	Baidu	output per 1M tokens	$0.18	$0.389	+116.9% increase
DeepSeek V4 Flash Latest	OpenRouter	input per 1M tokens	$0.07	$0.15	+114.3% increase
DeepSeek V4 Pro 0813	Relace	output per 1M tokens	$3.80	$8.00	+110.5% increase
DeepSeek V4 Pro	OpenRouter	input per 1M tokens	$0.209	$0.434	+108% increase
DeepSeek V4 Pro	OpenRouter	output per 1M tokens	$0.418	$0.869	+108% increase
DeepSeek V4 Pro	Baidu	input per 1M tokens	$0.215	$0.433	+101.6% increase
DeepSeek V4 Pro	Baidu	output per 1M tokens	$0.429	$0.865	+101.6% increase
DeepSeek V4 Pro	StreamLake	input per 1M tokens	$0.216	$0.434	+101% increase
DeepSeek V4 Pro	StreamLake	output per 1M tokens	$0.432	$0.869	+101% increase
DeepSeek V4.1 Flash 1017	DeepSeek	input per 1M tokens	$0.15	$0.30	+100% increase
DeepSeek V4.1 Flash 1017	DeepSeek	output per 1M tokens	$0.60	$1.20	+100% increase
DeepSeek V4 Flash	DeepSeek	input per 1M tokens	$0.15	$0.30	+100% increase
DeepSeek V4 Flash	DeepSeek	output per 1M tokens	$0.60	$1.20	+100% increase
DeepSeek V4 Pro 0813	DeepSeek	input per 1M tokens	$0.66	$1.32	+100% increase
DeepSeek V4 Pro 0813	DeepSeek	output per 1M tokens	$1.98	$3.96	+100% increase
Gemini 3.1 Flash Lite	Vertex	input per 1M tokens	$0.125	$0.25	+100% increase
Gemini 3.1 Flash Lite	Vertex	output per 1M tokens	$0.75	$1.50	+100% increase
Gemini 3.1 Pro Preview	Vertex	input per 1M tokens	$1.00	$2.00	+100% increase
Gemini 3.1 Pro Preview	Vertex	output per 1M tokens	$6.00	$12	+100% increase
Gemini 3.5 Flash Lite	Vertex	input per 1M tokens	$0.15	$0.30	+100% increase
Gemini 3.5 Flash Lite	Vertex	output per 1M tokens	$1.25	$2.50	+100% increase
Gemini 3.5 Flash	Vertex	input per 1M tokens	$0.75	$1.50	+100% increase
Gemini 3.5 Flash	Vertex	output per 1M tokens	$4.50	$9.00	+100% increase
Gemini 3.6 Flash	Vertex	input per 1M tokens	$0.375	$0.75	+100% increase
Gemini 3.6 Flash	Vertex	output per 1M tokens	$1.88	$3.75	+100% increase
Gemini 3.7 Flash	Vertex	input per 1M tokens	$0.375	$0.75	+100% increase
Gemini 3.7 Flash	Vertex	output per 1M tokens	$1.88	$3.75	+100% increase
Gemini 3.8 Flash	Vertex	input per 1M tokens	$0.375	$0.75	+100% increase
Gemini 3.8 Flash	Vertex	output per 1M tokens	$1.88	$3.75	+100% increase
Gemini 3 Flash Preview	Vertex	input per 1M tokens	$0.25	$0.50	+100% increase
DeepSeek V4 Pro 0813	Sail Research	input per 1M tokens	$0.448	$0.896	+100% increase
DeepSeek V4 Pro 0813	Sail Research	input per 1M tokens	$0.448	$0.896	+100% increase
Solar Mini 4	Upstage	input per 1M tokens	$0.05	$0.10	+100% increase
Solar Mini 4	Upstage	output per 1M tokens	$0.20	$0.40	+100% increase
Clef Flash	OpenRouter	input per 1M tokens	$0.021	$0.038	+81% increase
DeepSeek V4.1 Flash	Vercel AI Gateway	input per 1M tokens	$0.30	$0.075	−75% decrease
DeepSeek V4.1 Flash	Vercel AI Gateway	output per 1M tokens	$1.20	$0.30	−75% decrease
Nemotron 3 Super 120B	Eden AI	input per 1M tokens	$0.30	$0.085	−71.7% decrease
Qwen3 235B-A22B	NanoGPT	input per 1M tokens	$0.30	$0.0875	−70.8% decrease
GLM-5.3	Wafer	output per 1M tokens	$4.80	$1.40	−70.8% decrease
GLM-5.3	Wafer	output per 1M tokens	$4.80	$1.40	−70.8% decrease
DeepSeek V4 Pro	Alibaba	input per 1M tokens	$1.42	$2.40	+69.5% increase
DeepSeek V4 Pro	Alibaba	output per 1M tokens	$2.83	$4.80	+69.5% increase
DeepSeek V4 Flash Latest	OpenInference	input per 1M tokens	$0.0168	$0.0052	−69% decrease
Ministral 3 14B	Eden AI	input per 1M tokens	$0.20	$0.338	+68.8% increase
GPT-OSS 120B	DigitalOcean	input per 1M tokens	$0.06	$0.10	+66.7% increase
GPT-OSS 120B	DigitalOcean	output per 1M tokens	$0.42	$0.70	+66.7% increase
GPT OSS 20B	NanoGPT	output per 1M tokens	$0.30	$0.10	−66.7% decrease
GLM-5.3-Flash	GMI Cloud	input per 1M tokens	$0.09	$0.15	+66.7% increase
GLM-5.3-Flash	GMI Cloud	output per 1M tokens	$0.30	$0.50	+66.7% increase
GLM-5.3	Morph	input per 1M tokens	$0.153	$0.053	−65.4% decrease
DeepSeek V4 Flash	Relace	output per 1M tokens	$1.28	$0.45	−64.8% decrease
moonshotai/kimi-k3-batch	Morph	input per 1M tokens	$1.00	$0.358	−64.2% decrease
Qwen3.8-27B	Wafer	output per 1M tokens	$6.00	$2.30	−61.7% decrease
DeepSeek V4.1 Flash	OpenInference	output per 1M tokens	$0.20	$0.08	−60% decrease
GLM-5.3-Flash	Wafer	output per 1M tokens	$0.50	$0.20	−60% decrease
Grok 4.20 Multi-Agent	NanoGPT	output per 1M tokens	$6.00	$2.50	−58.3% decrease
Grok 4.20	NanoGPT	output per 1M tokens	$6.00	$2.50	−58.3% decrease
Nemotron 3 Super 120B	Eden AI	output per 1M tokens	$0.90	$0.40	−55.6% decrease
Qwen3.8-27B	Ionstream	input per 1M tokens	$0.0893	$0.04	−55.2% decrease
moonshotai/kimi-k3-batch	Wafer	output per 1M tokens	$28	$13	−53.6% decrease
Kimi K3	Morph	input per 1M tokens	$0.75	$0.358	−52.3% decrease
GLM-5.3-Flash	NextBit	input per 1M tokens	$0.25	$0.12	−52% decrease
Qwen3.6 35B-A3B	Alibaba	output per 1M tokens	$1.49	$2.25	+51.5% increase
Qwen3.6 35B-A3B	Alibaba	input per 1M tokens	$0.248	$0.375	+51.2% increase
Codestral 25.08	Mistral	input per 1M tokens	$0.30	$0.15	−50% decrease
Codestral 25.08	Mistral	output per 1M tokens	$0.90	$0.45	−50% decrease
Codestral 25.08	Mistral	input per 1M tokens	$0.33	$0.165	−50% decrease
Codestral 25.08	Mistral	output per 1M tokens	$0.99	$0.495	−50% decrease
Ministral 3 8B	Mistral	input per 1M tokens	$0.15	$0.075	−50% decrease
Ministral 3 8B	Mistral	output per 1M tokens	$0.15	$0.075	−50% decrease
Ministral 3 8B	Mistral	input per 1M tokens	$0.165	$0.0825	−50% decrease
Ministral 3 8B	Mistral	output per 1M tokens	$0.165	$0.0825	−50% decrease
Mistral Large 3 675B Instruct 2512	Mistral	input per 1M tokens	$0.50	$0.25	−50% decrease
Mistral Large 3 675B Instruct 2512	Mistral	output per 1M tokens	$1.50	$0.75	−50% decrease
Mistral Large 3 675B Instruct 2512	Mistral	input per 1M tokens	$0.55	$0.275	−50% decrease
Mistral Large 3 675B Instruct 2512	Mistral	output per 1M tokens	$1.65	$0.825	−50% decrease
Mistral Medium 3.1	Mistral	input per 1M tokens	$0.40	$0.20	−50% decrease
Mistral Medium 3.1	Mistral	output per 1M tokens	$2.00	$1.00	−50% decrease
Mistral Medium 3.1	Mistral	input per 1M tokens	$0.44	$0.22	−50% decrease
Mistral Medium 3.1	Mistral	output per 1M tokens	$2.20	$1.10	−50% decrease
Mistral Medium 3.5	Mistral	input per 1M tokens	$1.50	$0.75	−50% decrease
Mistral Medium 3.5	Mistral	output per 1M tokens	$7.50	$3.75	−50% decrease
Mistral Medium 3.5	Mistral	input per 1M tokens	$1.65	$0.825	−50% decrease
Mistral Medium 3.5	Mistral	output per 1M tokens	$8.25	$4.13	−50% decrease
Mistral Small 4	Mistral	input per 1M tokens	$0.15	$0.075	−50% decrease
Mistral Small 4	Mistral	output per 1M tokens	$0.60	$0.30	−50% decrease
Mistral Small 4	Mistral	input per 1M tokens	$0.165	$0.0825	−50% decrease
Mistral Small 4	Mistral	output per 1M tokens	$0.66	$0.33	−50% decrease
Mistral Small 4	Mistral	input per 1M tokens	$0.165	$0.0825	−50% decrease
Mistral Small 4	Mistral	output per 1M tokens	$0.66	$0.33	−50% decrease
DeepSeek V4.1 Flash 1017	DeepSeek	input per 1M tokens	$0.30	$0.15	−50% decrease
DeepSeek V4.1 Flash 1017	DeepSeek	output per 1M tokens	$1.20	$0.60	−50% decrease
DeepSeek V4 Flash Vision Exp	DeepSeek	input per 1M tokens	$0.30	$0.15	−50% decrease
DeepSeek V4 Flash Vision Exp	DeepSeek	output per 1M tokens	$1.20	$0.60	−50% decrease
DeepSeek V4 Flash	DeepSeek	input per 1M tokens	$0.30	$0.15	−50% decrease
DeepSeek V4 Flash	DeepSeek	output per 1M tokens	$1.20	$0.60	−50% decrease
Llama 3.1 8B Instruct	Deep Infra	input per 1M tokens	$0.02	$0.03	+50% increase
MiMo-V2.5-Pro	AIHubMix	output per 1M tokens	$0.40	$0.60	+50% increase
Claude Fable 5.1	Anthropic	input per 1M tokens	$10	$5.00	−50% decrease
Claude Fable 5.1	Anthropic	output per 1M tokens	$50	$25	−50% decrease
Claude Fable 5	Anthropic	input per 1M tokens	$10	$5.00	−50% decrease
Claude Fable 5	Anthropic	output per 1M tokens	$50	$25	−50% decrease
Claude Haiku 4.5	Anthropic	input per 1M tokens	$1.00	$0.50	−50% decrease
Claude Haiku 4.5	Anthropic	output per 1M tokens	$5.00	$2.50	−50% decrease
Claude Haiku 5.5	Anthropic	input per 1M tokens	$0.10	$0.05	−50% decrease
Claude Haiku 5.5	Anthropic	output per 1M tokens	$0.50	$0.25	−50% decrease
Claude Opus 4.5	Anthropic	input per 1M tokens	$5.00	$2.50	−50% decrease
Claude Opus 4.5	Anthropic	output per 1M tokens	$25	$12.50	−50% decrease
Claude Opus 4.6	Anthropic	input per 1M tokens	$5.00	$2.50	−50% decrease
Claude Opus 4.6	Anthropic	output per 1M tokens	$25	$12.50	−50% decrease
Claude Opus 4.7	Anthropic	input per 1M tokens	$5.00	$2.50	−50% decrease
Claude Opus 4.7	Anthropic	output per 1M tokens	$25	$12.50	−50% decrease
Claude Opus 4.8	Anthropic	input per 1M tokens	$5.00	$2.50	−50% decrease
Claude Opus 4.8	Anthropic	output per 1M tokens	$25	$12.50	−50% decrease
Claude Opus 5.5	Anthropic	input per 1M tokens	$4.00	$2.00	−50% decrease
Claude Opus 5.5	Anthropic	output per 1M tokens	$20	$10	−50% decrease
Claude Opus 5	Anthropic	input per 1M tokens	$5.00	$2.50	−50% decrease
Claude Opus 5	Anthropic	output per 1M tokens	$25	$12.50	−50% decrease
Claude Sonnet 4.5	Anthropic	input per 1M tokens	$3.00	$1.50	−50% decrease
Claude Sonnet 4.5	Anthropic	output per 1M tokens	$15	$7.50	−50% decrease
Claude Sonnet 4.6	Anthropic	input per 1M tokens	$3.00	$1.50	−50% decrease
Claude Sonnet 4.6	Anthropic	output per 1M tokens	$15	$7.50	−50% decrease
Claude Sonnet 5.5	Anthropic	input per 1M tokens	$2.00	$1.00	−50% decrease
Claude Sonnet 5.5	Anthropic	output per 1M tokens	$10	$5.00	−50% decrease
Claude Sonnet 5	Anthropic	input per 1M tokens	$2.00	$1.00	−50% decrease
Claude Sonnet 5	Anthropic	output per 1M tokens	$10	$5.00	−50% decrease
Gemini 3.6 Flash	Vertex	input per 1M tokens	$0.825	$0.413	−50% decrease
Gemini 3.6 Flash	Vertex	output per 1M tokens	$4.13	$2.06	−50% decrease
Gemini 3.7 Flash	Vertex	input per 1M tokens	$0.825	$0.413	−50% decrease
Gemini 3.7 Flash	Vertex	output per 1M tokens	$4.13	$2.06	−50% decrease
Gemini 3.8 Flash	Vertex	input per 1M tokens	$0.825	$0.413	−50% decrease
Gemini 3.8 Flash	Vertex	output per 1M tokens	$4.13	$2.06	−50% decrease
Gemini 4 Argon	Vertex	input per 1M tokens	$2.00	$1.00	−50% decrease
Gemini 4 Argon	Vertex	output per 1M tokens	$10	$5.00	−50% decrease
Gemini 4 Argon	Vertex	input per 1M tokens	$2.20	$1.10	−50% decrease
Gemini 4 Argon	Vertex	output per 1M tokens	$11	$5.50	−50% decrease
Gemini Embedding 2	Google	input per 1M tokens	$0.20	$0.10	−50% decrease
GPT-3.5-turbo	OpenAI	input per 1M tokens	$0.50	$0.25	−50% decrease
GPT-3.5-turbo	OpenAI	output per 1M tokens	$1.50	$0.75	−50% decrease
GPT-4.1 mini	OpenAI	input per 1M tokens	$0.40	$0.20	−50% decrease
GPT-4.1 mini	OpenAI	output per 1M tokens	$1.60	$0.80	−50% decrease
GPT-4.1 nano	OpenAI	input per 1M tokens	$0.10	$0.05	−50% decrease
GPT-4.1 nano	OpenAI	output per 1M tokens	$0.40	$0.20	−50% decrease
GPT-4.1	OpenAI	input per 1M tokens	$2.00	$1.00	−50% decrease
GPT-4.1	OpenAI	output per 1M tokens	$8.00	$4.00	−50% decrease
GPT-4 Turbo	OpenAI	input per 1M tokens	$10	$5.00	−50% decrease
GPT-4 Turbo	OpenAI	output per 1M tokens	$30	$15	−50% decrease
GPT-4o mini	OpenAI	input per 1M tokens	$0.15	$0.075	−50% decrease
GPT-4o mini	OpenAI	output per 1M tokens	$0.60	$0.30	−50% decrease
GPT-4o	OpenAI	input per 1M tokens	$2.50	$1.25	−50% decrease
GPT-4o	OpenAI	output per 1M tokens	$10	$5.00	−50% decrease
GPT-5.2 Pro	OpenAI	input per 1M tokens	$21	$10.50	−50% decrease
GPT-5.2 Pro	OpenAI	output per 1M tokens	$168	$84	−50% decrease
GPT-5 Pro	OpenAI	input per 1M tokens	$15	$7.50	−50% decrease
GPT-5 Pro	OpenAI	output per 1M tokens	$120	$60	−50% decrease
GPT-5	OpenAI	input per 1M tokens	$1.25	$0.625	−50% decrease
GPT-5	OpenAI	output per 1M tokens	$10	$5.00	−50% decrease
o3-mini	OpenAI	input per 1M tokens	$1.10	$0.55	−50% decrease
o3-mini	OpenAI	output per 1M tokens	$4.40	$2.20	−50% decrease
o3	OpenAI	input per 1M tokens	$2.00	$1.00	−50% decrease
o3	OpenAI	output per 1M tokens	$8.00	$4.00	−50% decrease
o4-mini	OpenAI	input per 1M tokens	$1.10	$0.55	−50% decrease
o4-mini	OpenAI	output per 1M tokens	$4.40	$2.20	−50% decrease
text-embedding-3-large	OpenAI	input per 1M tokens	$0.13	$0.065	−50% decrease
text-embedding-3-small	OpenAI	input per 1M tokens	$0.02	$0.01	−50% decrease
text-embedding-ada-002	OpenAI	input per 1M tokens	$0.10	$0.05	−50% decrease
DeepSeek V4.1 Flash	Sail Research	output per 1M tokens	$0.30	$0.15	−50% decrease
DeepSeek V4 Flash Latest	Sail Research	input per 1M tokens	$0.10	$0.15	+50% increase
DeepSeek V4 Flash Latest	Sail Research	output per 1M tokens	$0.30	$0.15	−50% decrease
DeepSeek V4 Flash Latest	Sail Research	input per 1M tokens	$0.10	$0.15	+50% increase
DeepSeek V4 Flash Latest	Sail Research	output per 1M tokens	$0.30	$0.15	−50% decrease
DeepSeek V4 Flash Latest	StreamLake	input per 1M tokens	$0.088	$0.132	+50% increase
DeepSeek V4 Flash Latest	StreamLake	output per 1M tokens	$0.264	$0.396	+50% increase
DeepSeek V4 Pro 0813	Sail Research	output per 1M tokens	$1.16	$0.582	−50% decrease
DeepSeek V4 Pro 0813	Sail Research	output per 1M tokens	$1.16	$0.582	−50% decrease
DeepSeek V4 Pro	Relace	output per 1M tokens	$3.00	$1.50	−50% decrease
GLM-5.3-Flash	Inceptron	input per 1M tokens	$0.10	$0.15	+50% increase
DeepSeek V4 Pro 0813	Alibaba	input per 1M tokens	$1.12	$0.581	−48.2% decrease
DeepSeek V4 Pro 0813	Alibaba	output per 1M tokens	$3.37	$1.74	−48.2% decrease
deepseek-v3.2	Kilo Gateway	output per 1M tokens	$0.80	$0.42	−47.5% decrease
deepseek-v3.2	OpenRouter	output per 1M tokens	$0.80	$0.42	−47.5% decrease
Kimi K3	Wafer	output per 1M tokens	$24	$13	−45.8% decrease
Macaron V1 Tall	Novita AI	input per 1M tokens	$0.45	$0.248	−45% decrease
Macaron V1 Tall	Novita AI	output per 1M tokens	$2.60	$1.43	−45% decrease
Macaron V1 Venti	Novita AI	input per 1M tokens	$1.50	$0.825	−45% decrease
Macaron V1 Venti	Novita AI	output per 1M tokens	$4.50	$2.48	−45% decrease
DeepSeek V4.1 Flash	Alibaba	input per 1M tokens	$0.30	$0.165	−45% decrease
DeepSeek V4.1 Flash	Alibaba	output per 1M tokens	$1.20	$0.66	−45% decrease
Qwen3.5 35B-A3B	NanoGPT	output per 1M tokens	$1.80	$1.00	−44.4% decrease
moonshotai/kimi-k3-batch	Sail Research	input per 1M tokens	$0.84	$1.20	+42.9% increase
Kimi K3	Sail Research	input per 1M tokens	$0.84	$1.20	+42.9% increase
GLM-5.3-Flash	NextBit	output per 1M tokens	$0.70	$0.40	−42.9% decrease
GLM-5.3	GMI Cloud	input per 1M tokens	$0.98	$1.40	+42.9% increase
GLM-5.3	GMI Cloud	output per 1M tokens	$3.08	$4.40	+42.9% increase
DeepSeek V4 Pro 0813	Baidu	input per 1M tokens	$0.249	$0.145	−41.8% decrease
DeepSeek V4 Pro 0813	Baidu	output per 1M tokens	$0.748	$0.436	−41.8% decrease
GLM-5.3	Cortecs	input per 1M tokens	$0.873	$0.511	−41.5% decrease
Qwen3.7 Max	NanoGPT	input per 1M tokens	$2.50	$1.48	−41% decrease
Qwen3.7 Max	NanoGPT	output per 1M tokens	$7.50	$4.43	−41% decrease
Qwen3.5 122B-A10B	NanoGPT	input per 1M tokens	$0.437	$0.26	−40.5% decrease
Qwen3.5 122B-A10B	NanoGPT	output per 1M tokens	$3.50	$2.08	−40.5% decrease
DeepSeek V4 Flash Latest	OpenInference	output per 1M tokens	$0.20	$0.12	−40% decrease
Gemma-4-31B-IT	NanoGPT	input per 1M tokens	$0.10	$0.14	+40% increase
GLM-5.3-Flash	Wafer	input per 1M tokens	$0.12	$0.074	−38.3% decrease
GLM-5.3	Cortecs	output per 1M tokens	$3.31	$2.05	−38.1% decrease
Qwen3.5 35B-A3B	NanoGPT	input per 1M tokens	$0.225	$0.14	−37.8% decrease
Grok 4.20 Multi-Agent	NanoGPT	input per 1M tokens	$2.00	$1.25	−37.5% decrease
Grok 4.20	NanoGPT	input per 1M tokens	$2.00	$1.25	−37.5% decrease
DeepSeek V4 Pro	NanoGPT	input per 1M tokens	$1.10	$0.70	−36.4% decrease
DeepSeek V4 Pro	NanoGPT	output per 1M tokens	$2.20	$1.40	−36.4% decrease
Qwen3.5 397B-A17B	NanoGPT	input per 1M tokens	$0.60	$0.39	−35% decrease
Qwen3.5 397B-A17B	NanoGPT	output per 1M tokens	$3.60	$2.34	−35% decrease
DeepSeek V4 Pro 0813	Phala	input per 1M tokens	$1.45	$0.957	−34% decrease
DeepSeek V4 Pro 0813	Phala	output per 1M tokens	$4.36	$2.88	−34% decrease
DeepSeek V4 Flash	OpenInference	input per 1M tokens	$0.0172	$0.0114	−33.5% decrease
DeepSeek V4 Flash	Relace	input per 1M tokens	$0.0215	$0.0143	−33.5% decrease
DeepSeek V4 Flash	Alibaba	input per 1M tokens	$0.15	$0.20	+33.3% increase
DeepSeek V4 Flash	Alibaba	output per 1M tokens	$0.30	$0.40	+33.3% increase
Nemotron 3.5 Lightning 30B A3B	Deep Infra	input per 1M tokens	$0.06	$0.08	+33.3% increase
DeepSeek V4 Flash	Baidu	input per 1M tokens	$0.0227	$0.0151	−33.3% decrease
DeepSeek V4 Flash	Baidu	output per 1M tokens	$0.0454	$0.0302	−33.3% decrease
Gemma 4 26B A4B IT	NextBit	input per 1M tokens	$0.0675	$0.09	+33.3% increase
Gemma 4 26B A4B IT	NextBit	output per 1M tokens	$0.225	$0.30	+33.3% increase
Gemma 4 26B A4B IT	OpenRouter	input per 1M tokens	$0.0675	$0.09	+33.3% increase
Gemma 4 26B A4B IT	OpenRouter	output per 1M tokens	$0.225	$0.30	+33.3% increase
MiniMax-M2.7	NanoGPT	input per 1M tokens	$0.315	$0.21	−33.3% decrease
MiniMax-M2.7	NanoGPT	output per 1M tokens	$1.26	$0.84	−33.3% decrease
moonshotai/kimi-k3-batch	Sail Research	output per 1M tokens	$13.50	$9.00	−33.3% decrease
Kimi K3	Sail Research	output per 1M tokens	$13.50	$9.00	−33.3% decrease
GLM-5.2	Morph	input per 1M tokens	$0.079	$0.053	−32.9% decrease
Qwen3 235B-A22B Instruct 2507	NanoGPT	input per 1M tokens	$0.13	$0.0875	−32.7% decrease
moonshotai/kimi-k3-batch	Wafer	output per 1M tokens	$17.50	$11.90	−32% decrease
DeepSeek V4.1 Flash	Ionstream	output per 1M tokens	$1.10	$0.75	−31.8% decrease
Qwen3 235B-A22B Instruct 2507	NanoGPT	output per 1M tokens	$0.50	$0.35	−30% decrease
Qwen3 235B-A22B	NanoGPT	output per 1M tokens	$0.50	$0.35	−30% decrease
DeepSeek V4 Flash Latest	Phala	input per 1M tokens	$0.44	$0.308	−30% decrease
DeepSeek V4 Flash Latest	Phala	output per 1M tokens	$1.32	$0.924	−30% decrease
Kimi K2.6	NanoGPT	output per 1M tokens	$2.60	$1.84	−29.4% decrease
DeepSeek R1 0528	Kilo Gateway	input per 1M tokens	$0.70	$0.50	−28.6% decrease
Llama 3.1 8B Instruct	Deep Infra	output per 1M tokens	$0.04	$0.05	+25% increase
Llama-4-Scout-17B-16E-Instruct-FP8	Deep Infra	input per 1M tokens	$0.08	$0.10	+25% increase
Llama-4-Scout-17B-16E-Instruct-FP8	Deep Infra	output per 1M tokens	$0.24	$0.30	+25% increase
Nemotron 3.5 Lightning 30B A3B	Deep Infra	output per 1M tokens	$0.16	$0.20	+25% increase
Nemotron 3 Ultra 550B A55B	Deep Infra	input per 1M tokens	$0.40	$0.50	+25% increase
Nemotron 3 Ultra 550B A55B	Deep Infra	output per 1M tokens	$1.76	$2.20	+25% increase
Gemma 4 26B A4B IT	NanoGPT	input per 1M tokens	$0.12	$0.09	−25% decrease
MiniMax-M3	NanoGPT	input per 1M tokens	$0.30	$0.23	−23.3% decrease
MiniMax Latest	NanoGPT	input per 1M tokens	$0.30	$0.23	−23.3% decrease
Gemma 3 27B	OpenRouter	output per 1M tokens	$0.45	$0.35	−22.2% decrease
moonshotai/kimi-k3-batch	Inference	input per 1M tokens	$0.304	$0.239	−21.4% decrease
Kimi K3	Inference	input per 1M tokens	$0.304	$0.239	−21.4% decrease
Gemma 4 26B A4B IT	NanoGPT	output per 1M tokens	$0.38	$0.30	−21.1% decrease
DeepSeek V4 Flash	Wafer	input per 1M tokens	$0.58	$0.70	+20.7% increase
Kimi K3	Wafer	output per 1M tokens	$14.90	$11.90	−20.1% decrease
Gemini 3.1 Flash Lite	Databricks	output per 1M tokens	$1.88	$1.50	−20% decrease
Gemini 3.1 Pro Preview	Databricks	input per 1M tokens	$2.50	$2.00	−20% decrease
Gemini 3.1 Pro Preview	Databricks	output per 1M tokens	$15	$12	−20% decrease
Qwen3.6 27B	Reka	output per 1M tokens	$2.50	$3.00	+20% increase
DeepSeek Chat	Deep Infra	input per 1M tokens	$0.32	$0.256	−20% decrease
DeepSeek Chat	Deep Infra	output per 1M tokens	$0.89	$0.712	−20% decrease
MiniMax-M3	NanoGPT	output per 1M tokens	$1.20	$0.96	−20% decrease
MiniMax Latest	NanoGPT	output per 1M tokens	$1.20	$0.96	−20% decrease
Beam 1.0 501B A23B	NanoGPT	output per 1M tokens	$1.25	$1.50	+20% increase
GLM-5.2	Wafer	output per 1M tokens	$10	$8.00	−20% decrease
GLM-5.3-Flash	OpenInference	input per 1M tokens	$0.04	$0.048	+20% increase
GLM-5.3-Flash	OpenInference	output per 1M tokens	$0.20	$0.16	−20% decrease
GLM-5.3-Flash	OpenRouter	input per 1M tokens	$0.04	$0.048	+20% increase
GLM-5.3-Flash	OpenRouter	output per 1M tokens	$0.20	$0.16	−20% decrease
Gemini 3.1 Flash Lite	Databricks	input per 1M tokens	$0.312	$0.25	−20% decrease
DeepSeek V4.1 Flash	NanoGPT	output per 1M tokens	$0.52	$0.42	−19.2% decrease
moonshotai/kimi-k3-batch	Wafer	input per 1M tokens	$0.294	$0.238	−19.1% decrease
Kimi K3	Wafer	input per 1M tokens	$0.294	$0.238	−19.1% decrease
Qwen3.8-27B	Alibaba	input per 1M tokens	$0.425	$0.50	+17.6% increase
Qwen3.8-27B	Alibaba	output per 1M tokens	$2.55	$3.00	+17.6% increase
Kimi K3	NanoGPT	input per 1M tokens	$2.00	$1.65	−17.5% decrease
Kimi K3	NanoGPT	output per 1M tokens	$10	$8.25	−17.5% decrease
Kimi Latest	NanoGPT	input per 1M tokens	$2.00	$1.65	−17.5% decrease
Kimi Latest	NanoGPT	output per 1M tokens	$10	$8.25	−17.5% decrease
Qwen3.8-27B	Ionstream	output per 1M tokens	$2.35	$1.95	−17% decrease
Qwen3.5 27B	OpenRouter	output per 1M tokens	$2.60	$2.16	−16.9% decrease
Qwen3 Coder Next	Eden AI	input per 1M tokens	$0.60	$0.50	−16.7% decrease
Qwen3 Coder Next	Eden AI	output per 1M tokens	$1.44	$1.20	−16.7% decrease
DeepSeek V4.1 Flash	Morph	output per 1M tokens	$0.70	$0.60	−14.3% decrease
Cydonia 24B V4.1	NanoGPT	input per 1M tokens	$0.35	$0.30	−14.3% decrease
DeepSeek R1 0528	Kilo Gateway	output per 1M tokens	$2.50	$2.15	−14% decrease
Kimi K2.6	NanoGPT	input per 1M tokens	$0.50	$0.436	−12.8% decrease
DeepSeek V4.1 Flash	Sail Research	input per 1M tokens	$0.09	$0.101	+12.2% increase
Gemma-4-31B-IT	NanoGPT	output per 1M tokens	$0.45	$0.40	−11.1% decrease
Beam 1.0 501B A23B	NanoGPT	input per 1M tokens	$0.45	$0.50	+11.1% increase
GLM-5.2	StreamLake	input per 1M tokens	$0.556	$0.613	+10.4% increase
GLM-5.2	StreamLake	output per 1M tokens	$1.75	$1.93	+10.4% increase
GLM-5.3	IO.NET	output per 1M tokens	$2.90	$2.60	−10.3% decrease
Nova 2 Lite	Amazon Bedrock	input per 1M tokens	$0.30	$0.33	+10% increase
Nova 2 Lite	Amazon Bedrock	output per 1M tokens	$2.50	$2.75	+10% increase
Claude Opus 4.6	Amazon Bedrock	input per 1M tokens	$5.00	$5.50	+10% increase
Claude Opus 4.6	Amazon Bedrock	output per 1M tokens	$25	$27.50	+10% increase
Qwen3 30B A3B Instruct 2507	Kilo Gateway	input per 1M tokens	$0.10	$0.09	−10% decrease
Qwen3 30B A3B Instruct 2507	OpenRouter	input per 1M tokens	$0.10	$0.09	−10% decrease
MiniMax-M2.5	NanoGPT	input per 1M tokens	$0.30	$0.27	−10% decrease
MiniMax-M2.5	NanoGPT	output per 1M tokens	$1.20	$1.08	−10% decrease
Inkling Small	NanoGPT	input per 1M tokens	$0.50	$0.45	−10% decrease
GLM-4.6	Kilo Gateway	input per 1M tokens	$0.50	$0.55	+10% increase
GLM-4.6	Kilo Gateway	output per 1M tokens	$2.00	$2.20	+10% increase
GLM-4.6	OpenRouter	input per 1M tokens	$0.50	$0.55	+10% increase
GLM-4.6	OpenRouter	output per 1M tokens	$2.00	$2.20	+10% increase
GLM-4.7	Kilo Gateway	input per 1M tokens	$0.60	$0.54	−10% decrease
GLM-4.7	Kilo Gateway	output per 1M tokens	$2.20	$1.98	−10% decrease
GLM-4.7	OpenRouter	input per 1M tokens	$0.60	$0.54	−10% decrease
GLM-4.7	OpenRouter	output per 1M tokens	$2.20	$1.98	−10% decrease
Cydonia 24B V4.1	NanoGPT	output per 1M tokens	$0.55	$0.50	−9.1% decrease
DeepSeek V4 Flash Latest	Cortecs	input per 1M tokens	$0.09	$0.082	−8.9% decrease
deepseek-v3.2	Kilo Gateway	input per 1M tokens	$0.259	$0.28	+8.1% increase
deepseek-v3.2	OpenRouter	input per 1M tokens	$0.259	$0.28	+8.1% increase
DeepSeek V4.1 Flash	NanoGPT	input per 1M tokens	$0.13	$0.14	+7.7% increase
DeepSeek V4 Flash Latest	Wafer	input per 1M tokens	$0.13	$0.14	+7.7% increase
Qwen3.5 27B	NanoGPT	input per 1M tokens	$0.27	$0.25	−7.4% decrease
Qwen3.5 27B	NanoGPT	output per 1M tokens	$2.16	$2.00	−7.4% decrease
DeepSeek V4 Flash Latest	OpenRouter	output per 1M tokens	$0.14	$0.15	+7.1% increase
GLM-5.3	Inceptron	output per 1M tokens	$1.51	$1.40	−7% decrease
GLM-5.3	Wafer	input per 1M tokens	$0.17	$0.179	+5.3% increase
GLM-5.1	Alibaba	input per 1M tokens	$1.33	$1.40	+5.3% increase
GLM-5.1	Alibaba	output per 1M tokens	$4.18	$4.40	+5.3% increase
Step 5 Preview	Vercel AI Gateway	input per 1M tokens	$0.95	$1.00	+5.3% increase
Step 5 Preview	Vercel AI Gateway	output per 1M tokens	$2.57	$2.70	+5.3% increase
Inkling	NanoGPT	input per 1M tokens	$1.00	$0.95	−5% decrease
moonshotai/kimi-k3-batch	Inference	output per 1M tokens	$12.53	$11.94	−4.8% decrease
Qwen3.5 27B	OpenRouter	input per 1M tokens	$0.26	$0.27	+3.9% increase
Qwen3.6 27B	Reka	input per 1M tokens	$0.29	$0.30	+3.5% increase
Seed 2.1 Pro	Volcengine Ark	input per 1M tokens	$0.863	$0.891	+3.3% increase
Seed 2.1 Pro	Volcengine Ark	output per 1M tokens	$4.31	$4.45	+3.3% increase
Seed 2.1 Turbo	Volcengine Ark	input per 1M tokens	$0.431	$0.445	+3.3% increase
Seed 2.1 Turbo	Volcengine Ark	output per 1M tokens	$2.16	$2.23	+3.3% increase
DeepSeek V4.1 Flash	Morph	input per 1M tokens	$0.04	$0.041	+2.5% increase
DeepSeek V4.1 Flash	OpenInference	input per 1M tokens	$0.032	$0.0328	+2.5% increase
DeepSeek V4 Flash Vision Exp	NanoGPT	input per 1M tokens	$0.22	$0.216	−2% decrease
DeepSeek V4 Flash Vision Exp	NanoGPT	output per 1M tokens	$0.66	$0.647	−2% decrease
Qwen2.5 72B Instruct	NanoGPT	output per 1M tokens	$0.408	$0.40	−2% decrease
GLM-5.3-Flash	StreamLake	input per 1M tokens	$0.075	$0.0738	−1.5% decrease
GLM-5.3-Flash	StreamLake	output per 1M tokens	$0.25	$0.246	−1.5% decrease
Qwen2.5 72B Instruct	NanoGPT	input per 1M tokens	$0.357	$0.36	+0.8% increase
GLM-5.3	Decart	output per 1M tokens	$2.66	$2.68	+0.8% increase
Kimi K2.6	Baidu	input per 1M tokens	$0.432	$0.434	+0.4% increase
Kimi K2.6	Baidu	output per 1M tokens	$1.82	$1.83	+0.4% increase
Claude Sonnet 4	Databricks	input per 1M tokens	$3.00	$3.00	−0% increase
Claude Sonnet 4	Databricks	output per 1M tokens	$15	$15	−0% increase
GLM-5.2	Databricks	output per 1M tokens	$4.40	$4.40	−0% increase

Deprecations (178)

Llama 3.3 70b InstructLlama deprecated
Llama-3.3-8B-InstructLlama deprecated
Llama 4 Maverick 17b 128e InstructLlama deprecated
Llama-4-Scout-17B-16E-Instruct-FP8Llama deprecated
Qwen3-Coder 30B-A3B InstructAmazon Bedrock retires 2027-03-30
Qwen3-Coder 480B-A35B InstructAmazon Bedrock retires 2027-03-30
DeepSeek R1Amazon Bedrock retires 2027-03-30
DeepSeek R1Amazon Bedrock retires 2027-03-30
DeepSeek V3.1Amazon Bedrock retires 2027-03-30
Gemini 2.5 FlashDatabricks retires 2026-10-02
Gemini 2.5 ProDatabricks retires 2026-10-02
Nemotron Nano 12B v2 VLAmazon Bedrock retires 2027-03-30
Grok 4.1 Fast Non-ReasoningVertex deprecated
Claude 2.0 / 2.1Anthropic retires 2025-07-21
Claude Haiku 3.5Anthropic retires 2026-02-19
Claude Sonnet 3.5Anthropic retires 2025-10-28
Claude Sonnet 3.7Anthropic retires 2026-02-19
Claude Haiku 3Anthropic retires 2026-04-20
Claude Opus 3Anthropic retires 2026-01-05
Claude 3 SonnetAnthropic retires 2025-07-21
Claude Fable 5.1Anthropic retires 2027-09-01
Claude Fable 5.1Anthropic retires 2027-09-01
Claude Fable 5.1Azure retires 2027-09-01
Claude Fable 5.1Azure Cognitive Services retires 2027-09-01
Claude Fable 5.1Azure retires 2027-09-01
Claude Fable 5Anthropic retires 2027-06-09
Claude Fable 5Anthropic retires 2027-06-09
Claude Fable 5Azure retires 2027-06-09
Claude Fable 5Azure Cognitive Services retires 2027-06-09
Claude Fable 5Azure retires 2027-06-09
Claude Fable 5Claude Platform on AWS retires 2027-06-09
Claude Fable 5Claude Platform on AWS retires 2027-06-09
Claude Haiku 4.5Anthropic retires 2026-10-15
Claude Haiku 4.5Anthropic retires 2026-10-15
Claude Haiku 4.5Azure retires 2026-10-15
Claude Haiku 4.5Azure Cognitive Services retires 2026-10-15
Claude Haiku 4.5Azure retires 2026-10-15
Claude Haiku 4.5Azure retires 2026-10-15
Claude Haiku 5.5Anthropic retires 2027-10-07
Claude Haiku 5.5Anthropic retires 2027-10-07
Claude Haiku 5.5Azure retires 2027-10-07
Claude Haiku 5.5Azure Cognitive Services retires 2027-10-07
Claude Haiku 5.5Azure retires 2027-10-07
Claude Haiku 5.5Azure retires 2027-10-07
Claude Haiku 5.5Azure retires 2027-10-07
Claude Haiku 5.5Azure retires 2027-10-07
Claude Haiku 5.5Claude Platform on AWS retires 2027-10-07
Claude Haiku 5.5Claude Platform on AWS retires 2027-10-07
claude-mythos-5-1Anthropic retires 2027-09-01
Claude Mythos 5Anthropic retires 2027-06-09
Claude Mythos 5Azure retires 2027-06-09
Claude Mythos 5Azure Cognitive Services retires 2027-06-09
anthropic/claude-opus-4-0Anthropic retires 2026-06-15
Claude Opus 4.1Anthropic retires 2026-08-05
Claude Opus 4.1Azure retires 2026-08-05
Claude Opus 4.1Azure Cognitive Services retires 2026-08-05
Claude Opus 4.5Anthropic retires 2026-11-24
Claude Opus 4.5Anthropic retires 2026-11-24
Claude Opus 4.5Azure Cognitive Services retires 2026-11-24
Claude Opus 4.5Azure retires 2026-11-24
Claude Opus 4.5Azure retires 2026-11-24
Claude Opus 4.5Claude Platform on AWS retires 2026-11-24
Claude Opus 4.5Claude Platform on AWS retires 2026-11-24
Claude Opus 4.6Anthropic retires 2027-02-05
Claude Opus 4.6Anthropic retires 2027-02-05
Claude Opus 4.6Azure retires 2027-02-05
Claude Opus 4.6Azure Cognitive Services retires 2027-02-05
Claude Opus 4.6Azure retires 2027-02-05
Claude Opus 4.6Azure retires 2027-02-05
Claude Opus 4.6Claude Platform on AWS retires 2027-02-05
Claude Opus 4.6Claude Platform on AWS retires 2027-02-05
Claude Opus 4.7Anthropic retires 2027-04-16
Claude Opus 4.7Anthropic retires 2027-04-16
Claude Opus 4.7Azure retires 2027-04-16
Claude Opus 4.7Azure Cognitive Services retires 2027-04-16
Claude Opus 4.7Azure retires 2027-04-16
Claude Opus 4.7Azure retires 2027-04-16
Claude Opus 4.7Claude Platform on AWS retires 2027-04-16
Claude Opus 4.7Claude Platform on AWS retires 2027-04-16
Claude Opus 4.8Anthropic retires 2027-05-28
Claude Opus 4.8Anthropic retires 2027-05-28
Claude Opus 4.8Azure retires 2027-05-28
Claude Opus 4.8Azure Cognitive Services retires 2027-05-28
Claude Opus 4.8Azure retires 2027-05-28
Claude Opus 4.8Azure retires 2027-05-28
Claude Opus 4.8Azure retires 2027-05-28
Claude Opus 4.8Azure retires 2027-05-28
Claude Opus 4.8Claude Platform on AWS retires 2027-05-28
Claude Opus 4.8Claude Platform on AWS retires 2027-05-28
Claude Opus 5.5Anthropic retires 2027-09-22
Claude Opus 5.5Anthropic retires 2027-09-22
Claude Opus 5.5Azure retires 2027-09-22
Claude Opus 5.5Azure Cognitive Services retires 2027-09-22
Claude Opus 5.5Azure retires 2027-09-22
Claude Opus 5.5Azure retires 2027-09-22
Claude Opus 5.5Azure retires 2027-09-22
Claude Opus 5.5Azure retires 2027-09-22
Claude Opus 5.5Claude Platform on AWS retires 2027-09-22
Claude Opus 5.5Claude Platform on AWS retires 2027-09-22
Claude Opus 5Anthropic retires 2027-07-24
Claude Opus 5Anthropic retires 2027-07-24
Claude Opus 5Azure retires 2027-07-24
Claude Opus 5Azure Cognitive Services retires 2027-07-24
Claude Opus 5Azure retires 2027-07-24
Claude Opus 5Azure retires 2027-07-24
Claude Opus 5Azure retires 2027-07-24
Claude Opus 5Azure retires 2027-07-24
Claude Opus 5Claude Platform on AWS retires 2027-07-24
Claude Opus 5Claude Platform on AWS retires 2027-07-24
anthropic/claude-sonnet-4-0Anthropic retires 2026-06-15
Claude Sonnet 4.5Anthropic retires 2026-11-30
Claude Sonnet 4.5Anthropic retires 2026-11-30
Claude Sonnet 4.5Azure retires 2026-11-30
Claude Sonnet 4.5Azure Cognitive Services retires 2026-11-30
Claude Sonnet 4.5Azure retires 2026-11-30
Claude Sonnet 4.5Azure retires 2026-11-30
Claude Sonnet 4.5Claude Platform on AWS retires 2026-11-30
Claude Sonnet 4.5Claude Platform on AWS retires 2026-11-30
Claude Sonnet 4.6Anthropic retires 2027-02-17
Claude Sonnet 4.6Anthropic retires 2027-02-17
Claude Sonnet 4.6Azure retires 2027-02-17
Claude Sonnet 4.6Azure Cognitive Services retires 2027-02-17
Claude Sonnet 4.6Azure retires 2027-02-17
Claude Sonnet 4.6Azure retires 2027-02-17
Claude Sonnet 4.6Claude Platform on AWS retires 2027-02-17
Claude Sonnet 4.6Claude Platform on AWS retires 2027-02-17
Claude Sonnet 5.5Anthropic retires 2027-09-28
Claude Sonnet 5.5Anthropic retires 2027-09-28
Claude Sonnet 5.5Azure retires 2027-09-28
Claude Sonnet 5.5Azure Cognitive Services retires 2027-09-28
Claude Sonnet 5.5Azure retires 2027-09-28
Claude Sonnet 5.5Azure retires 2027-09-28
Claude Sonnet 5.5Azure retires 2027-09-28
Claude Sonnet 5.5Azure retires 2027-09-28
Claude Sonnet 5.5Claude Platform on AWS retires 2027-09-28
Claude Sonnet 5.5Claude Platform on AWS retires 2027-09-28
Claude Sonnet 5Anthropic retires 2027-06-30
Claude Sonnet 5Anthropic retires 2027-06-30
Claude Sonnet 5Azure Cognitive Services retires 2027-06-30
Claude Sonnet 5Azure retires 2027-06-30
Claude Sonnet 5Azure retires 2027-06-30
Claude Sonnet 5Azure retires 2027-06-30
Claude Sonnet 5Azure retires 2027-06-30
Claude Sonnet 5Claude Platform on AWS retires 2027-06-30
Claude Sonnet 5Claude Platform on AWS retires 2027-06-30
claude-v1Anthropic retires 2024-11-06
deepseek-coderDeepSeek deprecated
DeepSeek R1DeepSeek deprecated
deepseek-v3.1-terminusDeepSeek deprecated
DeepSeek V3.2 ExpDeepSeek deprecated
deepseek-v3.2DeepSeek deprecated
DeepSeek V3DeepSeek deprecated
DeepSeek V4 Flash Vision ExpDeepSeek deprecated
DeepSeek V4 FlashDeepSeek deprecated
Mistral Small 3.2Mistral retires 2026-07-31
Gemini 2.5 Flash-LiteGoogle deprecated
Gemini 2.5 FlashGoogle deprecated
Gemini 2.5 ProGoogle deprecated
Claude Sonnet 4.6GitHub Copilot retires 2026-09-01
Gemini 3.8 LiveVertex retires 2027-09-25
Gemini 4 ArgonVertex retires 2027-10-13
Llama 3.1 405B Instruct TurboAmazon Bedrock retires 2026-07-07
Llama 3.1 405B Instruct TurboAmazon Bedrock retires 2026-07-07
Llama 3.2 1b InstructAmazon Bedrock retires 2026-07-07
Llama 3.2 1b InstructAmazon Bedrock retires 2026-07-07
Llama 3.2 1b InstructAmazon Bedrock retires 2026-07-07
Llama 3.2 3B InstructAmazon Bedrock retires 2026-07-07
Llama 3.2 3B InstructAmazon Bedrock retires 2026-07-07
Llama 3.2 3B InstructAmazon Bedrock retires 2026-07-07
Llama 3.2 11B InstructAmazon Bedrock retires 2026-07-07
Llama 3.2 11B InstructAmazon Bedrock retires 2026-07-07
Llama 3.2 90B InstructAmazon Bedrock retires 2026-07-07
Llama 3.2 90B InstructAmazon Bedrock retires 2026-07-07
Ministral 3BAzure retires 2026-12-09
Mistral Medium 3Azure retires 2026-12-09
Mistral Small 3.1Azure retires 2026-12-09
Space Bunny FreeOpenCode deprecated
Space BunnyOpenCode Go deprecated

New models (83)

Plans (62)

Models no longer listed (5)

meta-models/muse-spark-open-816b-a42b
unknown/databricks-gemini-3-flash
unknown/databricks-gemini-3-pro
perplexity/pplx-decider-v1-1-27b
unbiased/pareto-26-10-preview

2026-10-17

120 price changes · 6 models added · 3 deprecations · 17 flagged as possible errors · 22 endpoints added, 4 removed

Price changes (120)

Model	Provider	Price	Was	Now	Change
Beam 1.0 501B A23B	OpenRouter	input per 1M tokens	$0.25	$1.00	+300% increase
GLM-5.3	Sail Research	input per 1M tokens	$0.15	$0.50	+233.3% increase
DeepSeek V4 Flash Latest	OpenInference	input per 1M tokens	$0.00522	$0.0168	+221.8% increase
Beam 1.0 501B A23B	OpenRouter	output per 1M tokens	$1.00	$3.00	+200% increase
GLM-5.3-Flash	Relace	input per 1M tokens	$0.0308	$0.075	+143.5% increase
zhipuai/glm-5-3-flash-batch	Relace	input per 1M tokens	$0.0346	$0.075	+116.8% increase
deepseek/deepseek-v4-1-flash-batch	Alibaba	input per 1M tokens	$0.15	$0.30	+100% increase
deepseek/deepseek-v4-1-flash-batch	Alibaba	output per 1M tokens	$0.60	$1.20	+100% increase
DeepSeek V4.1 Flash	Alibaba	input per 1M tokens	$0.15	$0.30	+100% increase
DeepSeek V4.1 Flash	Alibaba	output per 1M tokens	$0.60	$1.20	+100% increase
DeepSeek V4 Pro 0813	Alibaba	input per 1M tokens	$0.581	$1.12	+93.2% increase
DeepSeek V4 Pro 0813	Alibaba	output per 1M tokens	$1.74	$3.37	+93.2% increase
zhipuai/glm-5-3-flash-batch	Sail Research	input per 1M tokens	$0.045	$0.0784	+74.1% increase
zhipuai/glm-5-3-flash-batch	Sail Research	input per 1M tokens	$0.045	$0.0784	+74.1% increase
GLM-5.3-Flash	Sail Research	input per 1M tokens	$0.045	$0.0784	+74.1% increase
GLM-5.3-Flash	Sail Research	input per 1M tokens	$0.045	$0.0784	+74.1% increase
GLM-5.3	Morph	input per 1M tokens	$0.088	$0.153	+73.9% increase
Beam 1.0 501B A23B	NanoGPT	output per 1M tokens	$4.30	$1.25	−70.9% decrease
deepseek/deepseek-v4-1-flash-batch	OpenInference	output per 1M tokens	$0.663	$0.20	−69.8% decrease
DeepSeek V4.1 Flash	OpenInference	output per 1M tokens	$0.663	$0.20	−69.8% decrease
GLM-5.2	Baidu	input per 1M tokens	$0.619	$0.189	−69.5% decrease
GLM-5.2	Baidu	output per 1M tokens	$1.94	$0.594	−69.5% decrease
Beam 1.0 501B A23B	NanoGPT	input per 1M tokens	$1.30	$0.45	−65.4% decrease
nvidia/nemotron-3-5-super-vl	Deep Infra	output per 1M tokens	$1.00	$0.40	−60% decrease
Hy3	Kilo Gateway	input per 1M tokens	$0.0825	$0.132	+60% increase
Hy3	Kilo Gateway	output per 1M tokens	$0.33	$0.528	+60% increase
Hy3	OpenRouter	input per 1M tokens	$0.0825	$0.132	+60% increase
Hy3	OpenRouter	output per 1M tokens	$0.33	$0.528	+60% increase
Hy3	Tencent	input per 1M tokens	$0.0825	$0.132	+60% increase
Hy3	Tencent	output per 1M tokens	$0.33	$0.528	+60% increase
GLM-5.3	Sail Research	output per 1M tokens	$3.40	$1.51	−55.7% decrease
deepseek/deepseek-v4-1-flash-batch	OpenRouter	input per 1M tokens	$0.112	$0.05	−55.4% decrease
deepseek/deepseek-v4-1-flash-batch	OpenRouter	output per 1M tokens	$0.336	$0.15	−55.4% decrease
DeepSeek V4 Flash	OpenInference	input per 1M tokens	$0.0378	$0.0172	−54.5% decrease
DeepSeek V4 Pro 0813	Phala	input per 1M tokens	$0.957	$1.45	+51.5% increase
DeepSeek V4 Pro 0813	Phala	output per 1M tokens	$2.88	$4.36	+51.5% increase
nvidia/nemotron-3-5-super-vl	Deep Infra	input per 1M tokens	$0.20	$0.10	−50% decrease
zhipuai/glm-5-3-flash-batch	Sail Research	output per 1M tokens	$0.60	$0.30	−50% decrease
zhipuai/glm-5-3-flash-batch	Sail Research	output per 1M tokens	$0.60	$0.30	−50% decrease
GLM-5.3-Flash	Sail Research	output per 1M tokens	$0.60	$0.30	−50% decrease
GLM-5.3-Flash	Sail Research	output per 1M tokens	$0.60	$0.30	−50% decrease
DeepSeek V4 Pro 0813	Sail Research	input per 1M tokens	$0.896	$0.448	−50% decrease
DeepSeek V4 Pro 0813	Sail Research	input per 1M tokens	$0.896	$0.448	−50% decrease
DeepSeek V4 Flash	Baidu	input per 1M tokens	$0.0449	$0.0227	−49.5% decrease
DeepSeek V4 Flash	Baidu	output per 1M tokens	$0.0899	$0.0454	−49.5% decrease
DeepSeek V4 Flash	Relace	input per 1M tokens	$0.042	$0.0215	−48.8% decrease
GLM-5.3	Relace	output per 1M tokens	$4.40	$2.40	−45.5% decrease
GLM-5.3-Flash	OpenInference	input per 1M tokens	$0.0277	$0.04	+44.3% increase
GLM-5.3-Flash	OpenRouter	input per 1M tokens	$0.0277	$0.04	+44.3% increase
DeepSeek V4 Flash Latest	Phala	input per 1M tokens	$0.308	$0.44	+42.9% increase
DeepSeek V4 Flash Latest	Phala	output per 1M tokens	$0.924	$1.32	+42.9% increase
zhipuai/glm-5-3-flash-batch	Morph	input per 1M tokens	$0.035	$0.05	+42.9% increase
GLM-5.3-Flash	Morph	input per 1M tokens	$0.035	$0.05	+42.9% increase
DeepSeek V4 Flash	StreamLake	input per 1M tokens	$0.0442	$0.028	−36.7% decrease
DeepSeek V4 Flash	StreamLake	output per 1M tokens	$0.0885	$0.056	−36.7% decrease
DeepSeek V4 Pro	OpenRouter	input per 1M tokens	$0.328	$0.209	−36.3% decrease
DeepSeek V4 Pro	OpenRouter	output per 1M tokens	$0.655	$0.418	−36.3% decrease
zhipuai/glm-5-3-flash-batch	Morph	output per 1M tokens	$1.00	$0.65	−35% decrease
GLM-5.3-Flash	Morph	output per 1M tokens	$1.00	$0.65	−35% decrease
DeepSeek V4 Pro	Baidu	input per 1M tokens	$0.326	$0.215	−34.2% decrease
DeepSeek V4 Pro	Baidu	output per 1M tokens	$0.652	$0.429	−34.2% decrease
DeepSeek V4 Pro	StreamLake	input per 1M tokens	$0.328	$0.216	−34% decrease
DeepSeek V4 Pro	StreamLake	output per 1M tokens	$0.655	$0.432	−34% decrease
Nemotron 3.5 Super VL 120B A12B	CoreWeave	output per 1M tokens	$0.75	$0.50	−33.3% decrease
nvidia/nemotron-3-5-super-vl	CoreWeave	output per 1M tokens	$0.75	$0.50	−33.3% decrease
nvidia/nemotron-3-5-super-vl	OpenRouter	input per 1M tokens	$0.15	$0.10	−33.3% decrease
GLM-5.2	Relace	output per 1M tokens	$6.00	$4.00	−33.3% decrease
GLM-5.3	Inceptron	output per 1M tokens	$2.20	$1.51	−31.4% decrease
DeepSeek V4 Flash Latest	Sail Research	output per 1M tokens	$0.42	$0.30	−28.6% decrease
zhipuai/glm-5-3-flash-batch	OpenInference	input per 1M tokens	$0.0311	$0.04	+28.4% increase
Gemma 4 26B A4B IT	NextBit	input per 1M tokens	$0.09	$0.0675	−25% decrease
Gemma 4 26B A4B IT	NextBit	output per 1M tokens	$0.30	$0.225	−25% decrease
Gemma 4 26B A4B IT	OpenRouter	input per 1M tokens	$0.09	$0.0675	−25% decrease
Gemma 4 26B A4B IT	OpenRouter	output per 1M tokens	$0.30	$0.225	−25% decrease
Kimi K3	Morph	input per 1M tokens	$1.00	$0.75	−25% decrease
DeepSeek V4 Pro	Merge Gateway	input per 1M tokens	$1.74	$1.32	−24.1% decrease
GLM-5.2	Wafer	output per 1M tokens	$9.00	$7.00	−22.2% decrease
nvidia/nemotron-3-5-super-vl	OpenRouter	output per 1M tokens	$0.50	$0.40	−20% decrease
zhipuai/glm-5-3-flash-batch	Inceptron	output per 1M tokens	$0.863	$0.69	−20% decrease
GLM-5.3-Flash	Inceptron	output per 1M tokens	$0.863	$0.69	−20% decrease
GLM-5.3-Flash	Relace	output per 1M tokens	$0.61	$0.50	−18.1% decrease
DeepSeek V4 Pro 0813	Sail Research	output per 1M tokens	$0.99	$1.16	+17.6% increase
DeepSeek V4 Pro 0813	Sail Research	output per 1M tokens	$0.99	$1.16	+17.6% increase
Kimi K3	Wafer	output per 1M tokens	$17.50	$14.90	−14.9% decrease
Kimi K3	Wafer	output per 1M tokens	$28	$24	−14.3% decrease
GLM-5.3	Baidu	input per 1M tokens	$0.699	$0.599	−14.2% decrease
GLM-5.3	Baidu	output per 1M tokens	$2.20	$1.88	−14.2% decrease
GPT-5 Mini	AI/ML API	input per 1M tokens	$0.378	$0.325	−14.1% decrease
GPT-5 Mini	AI/ML API	output per 1M tokens	$3.03	$2.60	−14.1% decrease
GPT-5 Nano	AI/ML API	input per 1M tokens	$0.0756	$0.065	−14.1% decrease
GPT-5 Nano	AI/ML API	output per 1M tokens	$0.605	$0.52	−14.1% decrease
GPT-5	AI/ML API	input per 1M tokens	$1.89	$1.63	−14.1% decrease
GPT-5	AI/ML API	output per 1M tokens	$15.13	$13	−14.1% decrease
DeepSeek V4 Pro	Merge Gateway	output per 1M tokens	$3.48	$3.96	+13.8% increase
deepseek/deepseek-v4-1-flash-batch	DigitalOcean	input per 1M tokens	$0.225	$0.195	−13.3% decrease
deepseek/deepseek-v4-1-flash-batch	DigitalOcean	output per 1M tokens	$0.90	$0.78	−13.3% decrease
zhipuai/glm-5-3-flash-batch	Phala	input per 1M tokens	$0.113	$0.128	+13.3% increase
zhipuai/glm-5-3-flash-batch	Phala	output per 1M tokens	$0.375	$0.425	+13.3% increase
GLM-5.3-Flash	Phala	input per 1M tokens	$0.113	$0.128	+13.3% increase
GLM-5.3-Flash	Phala	output per 1M tokens	$0.375	$0.425	+13.3% increase
DeepSeek V3.1	Merge Gateway	input per 1M tokens	$0.50	$0.56	+12% increase
DeepSeek V3.1	Merge Gateway	output per 1M tokens	$1.50	$1.68	+12% increase
zhipuai/glm-5-3-flash-batch	Relace	output per 1M tokens	$0.565	$0.50	−11.5% decrease
deepseek/deepseek-v4-1-flash-batch	OpenInference	input per 1M tokens	$0.036	$0.032	−11.1% decrease
DeepSeek V4.1 Flash	OpenInference	input per 1M tokens	$0.036	$0.032	−11.1% decrease
Hy4 preview	Kilo Gateway	input per 1M tokens	$0.751	$0.834	+11.1% increase
Hy4 preview	Kilo Gateway	output per 1M tokens	$2.25	$2.50	+11.1% increase
Hy4 preview	OpenRouter	input per 1M tokens	$0.751	$0.834	+11.1% increase
Hy4 preview	OpenRouter	output per 1M tokens	$2.25	$2.50	+11.1% increase
Hy4 preview	Tencent	input per 1M tokens	$0.751	$0.834	+11.1% increase
Hy4 preview	Tencent	output per 1M tokens	$2.25	$2.50	+11.1% increase
GLM-5.2	Wafer	input per 1M tokens	$0.037	$0.0341	−7.8% decrease
zhipuai/glm-5-3-flash-batch	Decart	input per 1M tokens	$0.093	$0.0885	−4.8% decrease
zhipuai/glm-5-3-flash-batch	Decart	output per 1M tokens	$0.31	$0.295	−4.8% decrease
GLM-5.3-Flash	Decart	input per 1M tokens	$0.093	$0.0885	−4.8% decrease
GLM-5.3-Flash	Decart	output per 1M tokens	$0.31	$0.295	−4.8% decrease
Kimi K3	Inference	output per 1M tokens	$12.53	$11.94	−4.8% decrease
deepseek/deepseek-v4-1-flash-batch	Inference	output per 1M tokens	$0.737	$0.715	−3% decrease
DeepSeek V4.1 Flash	Inference	output per 1M tokens	$0.737	$0.715	−3% decrease
GLM-5.3	Inference	output per 1M tokens	$4.52	$4.38	−3% decrease

Deprecations (3)

perplexity/pplx-decider-v1-1-27bOpenRouter retires 2026-10-17
LL Alpha FreeOpenCode deprecated
Muse Spark 1.3 FreeOpenCode deprecated

New models (6)

2026-10-16

297 price changes · 31 models added · 25 deprecations · 4 models no longer listed · 22 flagged as possible errors · 240 endpoints added, 55 removed

Price changes (297)

Model	Provider	Price	Was	Now	Change
zhipuai/glm-5-3-batch	Sail Research	input per 1M tokens	$0.15	$0.50	+233.3% increase
GLM-5.3	Sail Research	input per 1M tokens	$0.15	$0.50	+233.3% increase
DeepSeek V4 Pro 0813	Relace	input per 1M tokens	$0.225	$0.60	+166.7% increase
zhipuai/glm-5-3-flash-batch	Inference	output per 1M tokens	$0.15	$0.388	+158.7% increase
GLM-5.3-Flash	Inference	output per 1M tokens	$0.15	$0.388	+158.7% increase
DeepSeek Latest	NanoGPT	output per 1M tokens	$0.99	$2.50	+152.5% increase
GLM-5.3-Flash	OpenRouter	input per 1M tokens	$0.0113	$0.0277	+146.4% increase
DeepSeek V4 Flash Latest	OpenInference	output per 1M tokens	$0.576	$1.15	+100% increase
DeepSeek V4 Flash Latest	OpenRouter	output per 1M tokens	$0.64	$1.28	+100% increase
DeepSeek V4 Flash Latest	Relace	output per 1M tokens	$0.64	$1.28	+100% increase
Step 5 Preview	OpenCode Go	input per 1M tokens	$0	$1.00	+100% increase
Step 5 Preview	OpenCode Go	output per 1M tokens	$0	$2.70	+100% increase
Qwen3-Next 80B-A3B Instruct	Merge Gateway	output per 1M tokens	$0.574	$1.10	+91.6% increase
GLM-5.2	Relace	input per 1M tokens	$0.019	$0.0351	+84.7% increase
GLM-5.3-Flash	OpenRouter	output per 1M tokens	$0.50	$0.90	+80% increase
zhipuai/glm-5-3-flash-batch	StreamLake	input per 1M tokens	$0.0435	$0.075	+72.4% increase
zhipuai/glm-5-3-flash-batch	StreamLake	output per 1M tokens	$0.145	$0.25	+72.4% increase
GLM-5.3-Flash	StreamLake	input per 1M tokens	$0.0435	$0.075	+72.4% increase
GLM-5.3-Flash	StreamLake	output per 1M tokens	$0.145	$0.25	+72.4% increase
DeepSeek V4 Flash	Baidu	input per 1M tokens	$0.14	$0.0449	−67.9% decrease
DeepSeek V4 Flash	Baidu	output per 1M tokens	$0.28	$0.0899	−67.9% decrease
Qwen3 VL 235B A22B Instruct	Merge Gateway	output per 1M tokens	$1.15	$1.90	+65.7% increase
GLM-5.2	OpenRouter	output per 1M tokens	$7.00	$2.42	−65.4% decrease
DeepSeek V4 Pro	OpenRouter	input per 1M tokens	$0.955	$0.338	−64.6% decrease
DeepSeek V4 Pro	OpenRouter	output per 1M tokens	$1.91	$0.675	−64.6% decrease
DeepSeek V4 Pro	StreamLake	input per 1M tokens	$0.955	$0.338	−64.6% decrease
DeepSeek V4 Pro	StreamLake	output per 1M tokens	$1.91	$0.675	−64.6% decrease
DeepSeek V4 Flash Latest	OpenInference	input per 1M tokens	$0.0144	$0.00612	−57.5% decrease
DeepSeek V4 Flash Latest	OpenRouter	input per 1M tokens	$0.016	$0.0068	−57.5% decrease
DeepSeek V4 Flash Latest	Relace	input per 1M tokens	$0.016	$0.0068	−57.5% decrease
zhipuai/glm-5-3-flash-batch	Inceptron	output per 1M tokens	$0.55	$0.863	+56.8% increase
GLM-5.3-Flash	Inceptron	output per 1M tokens	$0.55	$0.863	+56.8% increase
GLM-5.2	Baidu	input per 1M tokens	$1.40	$0.619	−55.8% decrease
GLM-5.2	Baidu	output per 1M tokens	$4.40	$1.94	−55.8% decrease
zhipuai/glm-5-3-batch	Sail Research	output per 1M tokens	$3.40	$1.51	−55.7% decrease
GLM-5.3	Sail Research	output per 1M tokens	$3.40	$1.51	−55.7% decrease
Kimi K2.6	Baidu	input per 1M tokens	$0.95	$0.432	−54.5% decrease
Kimi K2.6	Baidu	output per 1M tokens	$4.00	$1.82	−54.5% decrease
GLM-5.3-Flash	Morph	input per 1M tokens	$0.074	$0.035	−52.7% decrease
DeepSeek V4 Pro 0813	Relace	output per 1M tokens	$8.00	$3.80	−52.5% decrease
deepseek/deepseek-v4-1-flash-batch	OpenInference	input per 1M tokens	$0.0238	$0.036	+51.5% increase
DeepSeek V4.1 Flash	OpenInference	input per 1M tokens	$0.0238	$0.036	+51.5% increase
zhipuai/glm-5-3-batch	Baidu	input per 1M tokens	$1.40	$0.699	−50.1% decrease
zhipuai/glm-5-3-batch	Baidu	output per 1M tokens	$4.40	$2.20	−50.1% decrease
GLM-5.3	Baidu	input per 1M tokens	$1.40	$0.699	−50.1% decrease
GLM-5.3	Baidu	output per 1M tokens	$4.40	$2.20	−50.1% decrease
deepseek/deepseek-v4-1-flash-batch	Alibaba	input per 1M tokens	$0.30	$0.15	−50% decrease
deepseek/deepseek-v4-1-flash-batch	Alibaba	output per 1M tokens	$1.20	$0.60	−50% decrease
DeepSeek V4.1 Flash	Alibaba	input per 1M tokens	$0.30	$0.15	−50% decrease
DeepSeek V4.1 Flash	Alibaba	output per 1M tokens	$1.20	$0.60	−50% decrease
DeepSeek V4.1 Flash	sail	output per 1M tokens	$0.60	$0.30	−50% decrease
Gemma-4-31B-IT	Deep Infra	input per 1M tokens	$0.09	$0.135	+50% increase
Gemma-4-31B-IT	Deep Infra	output per 1M tokens	$0.34	$0.51	+50% increase
GLM-5.2	Relace	output per 1M tokens	$4.00	$6.00	+50% increase
meta/llama-4-scout	OpenRouter	output per 1M tokens	$0.59	$0.30	−49.1% decrease
DeepSeek V4 Pro 0813	Alibaba	input per 1M tokens	$1.12	$0.581	−48.2% decrease
DeepSeek V4 Pro 0813	Alibaba	output per 1M tokens	$3.37	$1.74	−48.2% decrease
zhipuai/glm-5-3-flash-batch	Morph	input per 1M tokens	$0.066	$0.035	−47% decrease
DeepSeek V4 Flash	StreamLake	input per 1M tokens	$0.0826	$0.0442	−46.4% decrease
DeepSeek V4 Flash	StreamLake	output per 1M tokens	$0.165	$0.0885	−46.4% decrease
zhipuai/glm-5-3-flash-batch	Inference	input per 1M tokens	$0.083	$0.12	+44.6% increase
GLM-5.3-Flash	Inference	input per 1M tokens	$0.083	$0.12	+44.6% increase
meta/llama-4-scout	OpenRouter	input per 1M tokens	$0.18	$0.10	−44.4% decrease
DeepSeek V4.1 Flash	Ofox	input per 1M tokens	$0.21	$0.30	+42.9% increase
DeepSeek V4.1 Flash	Ofox	output per 1M tokens	$0.84	$1.20	+42.9% increase
DeepSeek V4 Flash Latest	Ofox	input per 1M tokens	$0.308	$0.44	+42.9% increase
DeepSeek V4 Flash Latest	Ofox	output per 1M tokens	$0.924	$1.32	+42.9% increase
DeepSeek V4 Pro 0813	Ofox	input per 1M tokens	$0.924	$1.32	+42.9% increase
DeepSeek V4 Pro 0813	Ofox	output per 1M tokens	$2.77	$3.96	+42.9% increase
DeepSeek V4.1 Flash	sail	input per 1M tokens	$0.15	$0.09	−40% decrease
zhipuai/glm-5-3-batch	Decart	output per 1M tokens	$4.40	$2.66	−39.5% decrease
GLM-5.3	Decart	output per 1M tokens	$4.40	$2.66	−39.5% decrease
Qwen3 VL 30B A3B Instruct	Merge Gateway	output per 1M tokens	$0.43	$0.60	+39.5% increase
Qwen3 VL 30B A3B Instruct	Merge Gateway	input per 1M tokens	$0.108	$0.15	+38.9% increase
Qwen3.6 27B	OpenRouter	output per 1M tokens	$3.20	$2.00	−37.5% decrease
Hy3	Kilo Gateway	input per 1M tokens	$0.132	$0.0825	−37.5% decrease
Hy3	Kilo Gateway	output per 1M tokens	$0.528	$0.33	−37.5% decrease
Hy3	OpenRouter	input per 1M tokens	$0.132	$0.0825	−37.5% decrease
Hy3	OpenRouter	output per 1M tokens	$0.528	$0.33	−37.5% decrease
Hy3	Tencent	input per 1M tokens	$0.132	$0.0825	−37.5% decrease
Hy3	Tencent	output per 1M tokens	$0.528	$0.33	−37.5% decrease
Gemma 4 26B A4B IT	Makora	output per 1M tokens	$0.28	$0.18	−35.7% decrease
Qwen3.6 35B-A3B	AtlasCloud	input per 1M tokens	$0.186	$0.25	+34.4% increase
DeepSeek V4 Flash Latest	StreamLake	input per 1M tokens	$0.132	$0.088	−33.3% decrease
DeepSeek V4 Flash Latest	StreamLake	output per 1M tokens	$0.396	$0.264	−33.3% decrease
moonshotai/kimi-k3-batch	Inference	input per 1M tokens	$0.45	$0.304	−32.4% decrease
Kimi K3	Inference	input per 1M tokens	$0.45	$0.304	−32.4% decrease
zhipuai/glm-5-3-flash-batch	NextBit	input per 1M tokens	$0.19	$0.25	+31.6% increase
GLM-5.3-Flash	NextBit	input per 1M tokens	$0.19	$0.25	+31.6% increase
GLM-5.1	Baidu	input per 1M tokens	$1.40	$0.965	−31.1% decrease
GLM-5.1	Baidu	output per 1M tokens	$4.40	$3.03	−31.1% decrease
Qwen3-Next 80B-A3B Instruct	Merge Gateway	input per 1M tokens	$0.144	$0.10	−30.6% decrease
deepseek/deepseek-v4-1-flash-batch	AtlasCloud	input per 1M tokens	$0.192	$0.135	−29.7% decrease
deepseek/deepseek-v4-1-flash-batch	AtlasCloud	output per 1M tokens	$0.768	$0.54	−29.7% decrease
DeepSeek V4.1 Flash	AtlasCloud	input per 1M tokens	$0.192	$0.135	−29.7% decrease
DeepSeek V4.1 Flash	AtlasCloud	output per 1M tokens	$0.768	$0.54	−29.7% decrease
GLM-5.3-Flash	IteraCompute	input per 1M tokens	$0.14	$0.099	−29.3% decrease
GLM-5.3-Flash	IteraCompute	output per 1M tokens	$0.49	$0.35	−28.6% decrease
Qwen3 VL 235B A22B Instruct	Merge Gateway	input per 1M tokens	$0.287	$0.21	−26.8% decrease
deepseek/deepseek-v4-1-flash-batch	Relace	output per 1M tokens	$0.80	$0.60	−25% decrease
moonshotai/kimi-k3-batch	Morph	input per 1M tokens	$0.80	$1.00	+25% increase
DeepSeek V4.1 Flash	Relace	output per 1M tokens	$0.80	$0.60	−25% decrease
mistral/mistral-small-3-2-24b-instruct	OpenRouter	input per 1M tokens	$0.075	$0.0938	+25% increase
mistral/mistral-small-3-2-24b-instruct	OpenRouter	output per 1M tokens	$0.20	$0.25	+25% increase
Kimi K3	Morph	input per 1M tokens	$0.80	$1.00	+25% increase
GPT-4.1 mini	Ofox	input per 1M tokens	$0.32	$0.40	+25% increase
GPT-4.1 mini	Ofox	output per 1M tokens	$1.28	$1.60	+25% increase
GPT-4.1	Ofox	input per 1M tokens	$1.60	$2.00	+25% increase
GPT-4.1	Ofox	output per 1M tokens	$6.40	$8.00	+25% increase
GPT-4o mini	Ofox	input per 1M tokens	$0.12	$0.15	+25% increase
GPT-4o mini	Ofox	output per 1M tokens	$0.48	$0.60	+25% increase
GPT-4o	Ofox	input per 1M tokens	$2.00	$2.50	+25% increase
GPT-4o	Ofox	output per 1M tokens	$8.00	$10	+25% increase
GPT-5.1 Codex Max	Ofox	input per 1M tokens	$1.00	$1.25	+25% increase
GPT-5.1 Codex Max	Ofox	output per 1M tokens	$8.00	$10	+25% increase
GPT-5.1 Codex Mini	Ofox	input per 1M tokens	$0.20	$0.25	+25% increase
GPT-5.1 Codex Mini	Ofox	output per 1M tokens	$1.60	$2.00	+25% increase
GPT-5.1	Ofox	input per 1M tokens	$1.00	$1.25	+25% increase
GPT-5.1	Ofox	output per 1M tokens	$8.00	$10	+25% increase
GPT-5.2 Codex	Ofox	input per 1M tokens	$1.40	$1.75	+25% increase
GPT-5.2 Codex	Ofox	output per 1M tokens	$11.20	$14	+25% increase
GPT-5.2	Ofox	input per 1M tokens	$1.40	$1.75	+25% increase
GPT-5.2	Ofox	output per 1M tokens	$11.20	$14	+25% increase
GPT-5.3 Codex	Ofox	input per 1M tokens	$1.40	$1.75	+25% increase
GPT-5.3 Codex	Ofox	output per 1M tokens	$11.20	$14	+25% increase
GPT-5.4 mini	Ofox	input per 1M tokens	$0.60	$0.75	+25% increase
GPT-5.4 mini	Ofox	output per 1M tokens	$3.60	$4.50	+25% increase
GPT-5.4 nano	Ofox	input per 1M tokens	$0.16	$0.20	+25% increase
GPT-5.4 nano	Ofox	output per 1M tokens	$1.00	$1.25	+25% increase
GPT-5.4 Pro	Ofox	input per 1M tokens	$24	$30	+25% increase
GPT-5.4 Pro	Ofox	output per 1M tokens	$144	$180	+25% increase
GPT-5.4	Ofox	input per 1M tokens	$2.00	$2.50	+25% increase
GPT-5.4	Ofox	output per 1M tokens	$12	$15	+25% increase
GPT-5.5	Ofox	input per 1M tokens	$4.00	$5.00	+25% increase
GPT-5.5	Ofox	output per 1M tokens	$24	$30	+25% increase
GPT-5 Mini	Ofox	input per 1M tokens	$0.20	$0.25	+25% increase
GPT-5 Mini	Ofox	output per 1M tokens	$1.60	$2.00	+25% increase
GPT-5 Nano	Ofox	input per 1M tokens	$0.04	$0.05	+25% increase
GPT-5 Nano	Ofox	output per 1M tokens	$0.32	$0.40	+25% increase
GPT-5	Ofox	input per 1M tokens	$1.00	$1.25	+25% increase
GPT-5	Ofox	output per 1M tokens	$8.00	$10	+25% increase
GPT-6 Astra	Ofox	input per 1M tokens	$8.00	$10	+25% increase
GPT-6 Astra	Ofox	output per 1M tokens	$40	$50	+25% increase
GPT-6 Luna	Ofox	input per 1M tokens	$0.08	$0.10	+25% increase
GPT-6 Luna	Ofox	output per 1M tokens	$0.40	$0.50	+25% increase
GPT-6 Sol	Ofox	input per 1M tokens	$1.60	$2.00	+25% increase
GPT-6 Sol	Ofox	output per 1M tokens	$8.00	$10	+25% increase
DeepSeek Latest	NanoGPT	input per 1M tokens	$0.896	$1.10	+22.8% increase
moonshotai/kimi-k3-batch	Decart	input per 1M tokens	$2.13	$1.65	−22.5% decrease
moonshotai/kimi-k3-batch	Decart	output per 1M tokens	$10.65	$8.25	−22.5% decrease
Kimi K3	Decart	input per 1M tokens	$2.13	$1.65	−22.5% decrease
Kimi K3	Decart	output per 1M tokens	$10.65	$8.25	−22.5% decrease
Qwen3.6 27B	OpenRouter	input per 1M tokens	$0.32	$0.25	−21.9% decrease
deepseek/deepseek-v4-1-flash-batch	Morph	input per 1M tokens	$0.033	$0.04	+21.2% increase
DeepSeek V4.1 Flash	Morph	input per 1M tokens	$0.033	$0.04	+21.2% increase
Kimi K3	IteraCompute	input per 1M tokens	$3.00	$2.39	−20.3% decrease
GPT-5.4	Venice AI	output per 1M tokens	$18.80	$15	−20.2% decrease
GPT-5.4	Venice AI	input per 1M tokens	$3.13	$2.50	−20.1% decrease
GPT-5.2	Venice AI	input per 1M tokens	$2.19	$1.75	−20.1% decrease
GPT-5.3 Codex	Venice AI	input per 1M tokens	$2.19	$1.75	−20.1% decrease
deepseek/deepseek-v4-1-flash-batch	Deep Infra	input per 1M tokens	$0.14	$0.112	−20% decrease
deepseek/deepseek-v4-1-flash-batch	Deep Infra	output per 1M tokens	$0.42	$0.336	−20% decrease
Gemma 3 12B IT	Kilo Gateway	input per 1M tokens	$0.05	$0.04	−20% decrease
Gemma 3 12B IT	Kilo Gateway	output per 1M tokens	$0.15	$0.12	−20% decrease
Gemma-4-31B-IT	Deep Infra	input per 1M tokens	$0.20	$0.16	−20% decrease
Gemma-4-31B-IT	Deep Infra	output per 1M tokens	$0.40	$0.32	−20% decrease
meta/llama-4-scout	Deep Infra	input per 1M tokens	$0.10	$0.08	−20% decrease
meta/llama-4-scout	Deep Infra	output per 1M tokens	$0.30	$0.24	−20% decrease
meta/llama-4-scout	Kilo Gateway	input per 1M tokens	$0.10	$0.08	−20% decrease
meta/llama-4-scout	Kilo Gateway	output per 1M tokens	$0.30	$0.24	−20% decrease
Llama Guard 4 12B	Kilo Gateway	input per 1M tokens	$0.18	$0.144	−20% decrease
Llama Guard 4 12B	Kilo Gateway	output per 1M tokens	$0.18	$0.144	−20% decrease
Phi-4	Kilo Gateway	input per 1M tokens	$0.07	$0.056	−20% decrease
Phi-4	Kilo Gateway	output per 1M tokens	$0.14	$0.112	−20% decrease
Nemotron 3 Ultra 550B A55B	Deep Infra	input per 1M tokens	$0.50	$0.40	−20% decrease
Nemotron 3 Ultra 550B A55B	Deep Infra	output per 1M tokens	$2.20	$1.76	−20% decrease
Nemotron 3 Ultra 550B A55B	Kilo Gateway	input per 1M tokens	$0.50	$0.40	−20% decrease
Nemotron 3 Ultra 550B A55B	Kilo Gateway	output per 1M tokens	$2.20	$1.76	−20% decrease
GPT-4o mini	Venice AI	input per 1M tokens	$0.188	$0.15	−20% decrease
GPT-4o mini	Venice AI	output per 1M tokens	$0.75	$0.60	−20% decrease
GPT-4o	Venice AI	input per 1M tokens	$3.13	$2.50	−20% decrease
GPT-4o	Venice AI	output per 1M tokens	$12.50	$10	−20% decrease
GPT-5.2	Venice AI	output per 1M tokens	$17.50	$14	−20% decrease
GPT-5.3 Codex	Venice AI	output per 1M tokens	$17.50	$14	−20% decrease
GPT-5.4 mini	Venice AI	input per 1M tokens	$0.938	$0.75	−20% decrease
GPT-5.4 mini	Venice AI	output per 1M tokens	$5.63	$4.50	−20% decrease
GPT-5.4 Pro	Venice AI	input per 1M tokens	$37.50	$30	−20% decrease
GPT-5.4 Pro	Venice AI	output per 1M tokens	$225	$180	−20% decrease
GPT-5.5 Pro	Venice AI	input per 1M tokens	$37.50	$30	−20% decrease
GPT-5.5 Pro	Venice AI	output per 1M tokens	$225	$180	−20% decrease
GPT-5.5	Venice AI	input per 1M tokens	$6.25	$5.00	−20% decrease
GPT-5.5	Venice AI	output per 1M tokens	$37.50	$30	−20% decrease
GPT-5.6 Luna	Venice AI	input per 1M tokens	$0.25	$0.20	−20% decrease
GPT-5.6 Luna	Venice AI	output per 1M tokens	$1.50	$1.20	−20% decrease
GPT-5.6 Sol	Venice AI	input per 1M tokens	$5.00	$4.00	−20% decrease
GPT-5.6 Sol	Venice AI	output per 1M tokens	$25	$20	−20% decrease
GPT-5.6 Terra	Venice AI	input per 1M tokens	$2.50	$2.00	−20% decrease
GPT-5.6 Terra	Venice AI	output per 1M tokens	$15	$12	−20% decrease
GPT-6.1 Sol	Venice AI	input per 1M tokens	$2.50	$2.00	−20% decrease
GPT-6.1 Sol	Venice AI	output per 1M tokens	$12.50	$10	−20% decrease
GPT-6 Luna	Venice AI	input per 1M tokens	$0.125	$0.10	−20% decrease
GPT-6 Luna	Venice AI	output per 1M tokens	$0.625	$0.50	−20% decrease
GPT-6 Sol	Venice AI	input per 1M tokens	$2.50	$2.00	−20% decrease
GPT-6 Sol	Venice AI	output per 1M tokens	$12.50	$10	−20% decrease
unknown/openai-gpt-6-astra-pro	Venice AI	input per 1M tokens	$12.50	$10	−20% decrease
unknown/openai-gpt-6-astra-pro	Venice AI	output per 1M tokens	$62.50	$50	−20% decrease
unknown/openai-gpt-61-sol-ultrafast	Venice AI	input per 1M tokens	$15	$12	−20% decrease
unknown/openai-gpt-61-sol-ultrafast	Venice AI	output per 1M tokens	$75	$60	−20% decrease
Kimi K3	IteraCompute	output per 1M tokens	$14.90	$11.99	−19.5% decrease
DeepSeek V4 Pro 0813	IteraCompute	input per 1M tokens	$1.10	$0.89	−19.1% decrease
DeepSeek V4 Pro 0813	IteraCompute	output per 1M tokens	$3.30	$2.69	−18.5% decrease
Gemma 4 26B A4B IT	IO.NET	input per 1M tokens	$0.11	$0.09	−18.2% decrease
GLM-5.3	IteraCompute	input per 1M tokens	$1.20	$0.99	−17.5% decrease
deepseek/deepseek-v4-1-flash-batch	Morph	output per 1M tokens	$0.60	$0.70	+16.7% increase
moonshotai/kimi-k3-batch	Relace	input per 1M tokens	$0.30	$0.35	+16.7% increase
DeepSeek V4.1 Flash	Morph	output per 1M tokens	$0.60	$0.70	+16.7% increase
Kimi K3	Relace	input per 1M tokens	$0.30	$0.35	+16.7% increase
zhipuai/glm-5-3-flash-batch	NextBit	output per 1M tokens	$0.60	$0.70	+16.7% increase
zhipuai/glm-5-3-flash-batch	OpenRouter	input per 1M tokens	$0.06	$0.05	−16.7% decrease
GLM-5.3-Flash	NextBit	output per 1M tokens	$0.60	$0.70	+16.7% increase
moonshotai/kimi-k3-batch	Inference	output per 1M tokens	$15	$12.53	−16.4% decrease
Kimi K3	Inference	output per 1M tokens	$15	$12.53	−16.4% decrease
DeepSeek V4 Flash	OpenInference	input per 1M tokens	$0.045	$0.0378	−16% decrease
DeepSeek V4 Flash	Relace	input per 1M tokens	$0.05	$0.042	−16% decrease
moonshotai/kimi-k3-batch	Parasail	input per 1M tokens	$2.60	$3.00	+15.4% increase
moonshotai/kimi-k3-batch	Parasail	output per 1M tokens	$13	$15	+15.4% increase
Kimi K3	Parasail	input per 1M tokens	$2.60	$3.00	+15.4% increase
Kimi K3	Parasail	output per 1M tokens	$13	$15	+15.4% increase
DeepSeek V4 Flash Latest	OpenInference	input per 1M tokens	$0.00612	$0.00522	−14.7% decrease
DeepSeek V4 Flash Latest	OpenRouter	input per 1M tokens	$0.0068	$0.0058	−14.7% decrease
DeepSeek V4 Flash Latest	Relace	input per 1M tokens	$0.0068	$0.0058	−14.7% decrease
zhipuai/glm-5-3-flash-batch	OpenInference	input per 1M tokens	$0.036	$0.0311	−13.5% decrease
zhipuai/glm-5-3-flash-batch	Relace	input per 1M tokens	$0.04	$0.0346	−13.5% decrease
GLM-5.3-Flash	OpenInference	input per 1M tokens	$0.036	$0.0311	−13.5% decrease
GLM-5.3-Flash	Relace	input per 1M tokens	$0.04	$0.0346	−13.5% decrease
Kimi K2.6	NanoGPT	input per 1M tokens	$0.441	$0.50	+13.4% increase
zhipuai/glm-5-3-flash-batch	Relace	output per 1M tokens	$0.50	$0.565	+13% increase
GLM-5.3-Flash	Relace	output per 1M tokens	$0.50	$0.565	+13% increase
Qwen3.6 35B-A3B	AtlasCloud	output per 1M tokens	$1.11	$1.25	+12.2% increase
deepseek/deepseek-v4-1-flash-batch	Inference	output per 1M tokens	$0.66	$0.737	+11.7% increase
DeepSeek V4.1 Flash	Inference	output per 1M tokens	$0.66	$0.737	+11.7% increase
Qwen3-Next 80B-A3B Instruct	NanoGPT	input per 1M tokens	$0.09	$0.10	+11.1% increase
Gemma-4-31B-IT	Kilo Gateway	input per 1M tokens	$0.09	$0.10	+11.1% increase
GLM-5.3-Flash	OpenInference	input per 1M tokens	$0.0311	$0.0277	−11% decrease
GLM-5.3-Flash	Relace	input per 1M tokens	$0.0346	$0.0308	−11% decrease
Qwen3-Next 80B-A3B Instruct	Kilo Gateway	input per 1M tokens	$0.10	$0.09	−10% decrease
Qwen3-Next 80B-A3B Instruct	OpenRouter	input per 1M tokens	$0.10	$0.09	−10% decrease
Gemini 3.8 Flash	OpenRouter	input per 1M tokens	$0.75	$0.825	+10% increase
Gemini 3.8 Flash	OpenRouter	output per 1M tokens	$3.75	$4.13	+10% increase
Hy4 preview	Kilo Gateway	output per 1M tokens	$2.50	$2.25	−10% decrease
Hy4 preview	OpenRouter	input per 1M tokens	$0.834	$0.751	−10% decrease
Hy4 preview	OpenRouter	output per 1M tokens	$2.50	$2.25	−10% decrease
Hy4 preview	Tencent	input per 1M tokens	$0.834	$0.751	−10% decrease
Hy4 preview	Tencent	output per 1M tokens	$2.50	$2.25	−10% decrease
zhipuai/glm-5-3-batch	Morph	input per 1M tokens	$0.08	$0.088	+10% increase
zhipuai/glm-5-3-flash-batch	OpenRouter	output per 1M tokens	$0.20	$0.18	−10% decrease
GLM-5.3	Morph	input per 1M tokens	$0.08	$0.088	+10% increase
Hy4 preview	Kilo Gateway	input per 1M tokens	$0.83	$0.751	−9.6% decrease
GLM-5.2	StreamLake	input per 1M tokens	$0.613	$0.556	−9.4% decrease
GLM-5.2	StreamLake	output per 1M tokens	$1.93	$1.75	−9.4% decrease
GLM-5.3-Flash	Relace	output per 1M tokens	$0.565	$0.61	+8.1% increase
deepseek/deepseek-v4-1-flash-batch	OpenInference	output per 1M tokens	$0.72	$0.663	−7.9% decrease
DeepSeek V4.1 Flash	OpenInference	output per 1M tokens	$0.72	$0.663	−7.9% decrease
zhipuai/glm-5-3-flash-batch	Inceptron	input per 1M tokens	$0.108	$0.10	−7.4% decrease
GLM-5.3-Flash	Inceptron	input per 1M tokens	$0.108	$0.10	−7.4% decrease
moonshotai/kimi-k3-batch	Wafer	input per 1M tokens	$0.29	$0.31	+6.9% increase
moonshotai/kimi-k3-batch	Relace	input per 1M tokens	$0.32	$0.30	−6.3% decrease
Kimi K2.6	NanoGPT	output per 1M tokens	$2.45	$2.60	+6.1% increase
zhipuai/glm-5-3-batch	Inference	output per 1M tokens	$4.80	$4.52	−5.9% decrease
GLM-5.3	Inference	output per 1M tokens	$4.80	$4.52	−5.9% decrease
DeepSeek V4 Pro	Baidu	input per 1M tokens	$0.346	$0.326	−5.8% decrease
DeepSeek V4 Pro	Baidu	output per 1M tokens	$0.693	$0.652	−5.8% decrease
Step 5 Preview	Vercel AI Gateway	input per 1M tokens	$1.00	$0.95	−5% decrease
Step 5 Preview	Vercel AI Gateway	output per 1M tokens	$2.70	$2.57	−5% decrease
Qwen3.8 2.4T A95B (NVFP4)	IteraCompute	output per 1M tokens	$5.95	$5.70	−4.2% decrease
zhipuai/glm-5-3-batch	Relace	input per 1M tokens	$0.063	$0.0608	−3.5% decrease
GLM-5.3	Relace	input per 1M tokens	$0.063	$0.0608	−3.5% decrease
Gemma 4 26B A4B IT	IO.NET	output per 1M tokens	$0.32	$0.31	−3.1% decrease
MiniMax-M3	IteraCompute	input per 1M tokens	$0.29	$0.299	+3.1% increase
deepseek/deepseek-v4-1-flash-batch	Inference	input per 1M tokens	$0.10	$0.103	+3% increase
DeepSeek V4.1 Flash	Inference	input per 1M tokens	$0.10	$0.103	+3% increase
DeepSeek V4 Pro	OpenRouter	input per 1M tokens	$0.338	$0.328	−3% decrease
DeepSeek V4 Pro	OpenRouter	output per 1M tokens	$0.675	$0.655	−3% decrease
DeepSeek V4 Pro	StreamLake	input per 1M tokens	$0.338	$0.328	−3% decrease
DeepSeek V4 Pro	StreamLake	output per 1M tokens	$0.675	$0.655	−3% decrease
deepseek/deepseek-v4-1-flash-batch	StreamLake	input per 1M tokens	$0.147	$0.15	+1.8% increase
deepseek/deepseek-v4-1-flash-batch	StreamLake	output per 1M tokens	$0.588	$0.599	+1.8% increase
DeepSeek V4.1 Flash	StreamLake	input per 1M tokens	$0.147	$0.15	+1.8% increase
DeepSeek V4.1 Flash	StreamLake	output per 1M tokens	$0.588	$0.599	+1.8% increase
GLM-5.3	IteraCompute	output per 1M tokens	$3.50	$3.45	−1.4% decrease
MiniMax-M3	IteraCompute	output per 1M tokens	$1.20	$1.19	−0.8% decrease
Qwen3-Coder 30B-A3B Instruct	Eden AI	input per 1M tokens	$0.224	$0.225	+0.5% increase
Qwen3-Coder 30B-A3B Instruct	Eden AI	output per 1M tokens	$0.896	$0.90	+0.5% increase
mistral/ministral-3-14b-instruct-2512	Eden AI	input per 1M tokens	$0.336	$0.338	+0.5% increase
mistral/ministral-3-14b-instruct-2512	Eden AI	output per 1M tokens	$0.448	$0.45	+0.5% increase
zhipuai/glm-5-3-batch	Inceptron	output per 1M tokens	$2.20	$2.20	−0.2% decrease
GLM-5.3	Inceptron	output per 1M tokens	$2.20	$2.20	−0.2% decrease

Deprecations (25)

Claude Opus 5GitHub Copilot retires 2026-11-16
Gemini 2.5 Flash-LiteGoogle deprecated
Gemini 2.5 FlashGoogle deprecated
Gemini 2.5 ProGoogle deprecated
MiniMax-M2.7OpenCode Go deprecated
ft-gpt-4-1-miniOpenAI retires 2027-01-14
ft-gpt-4-1OpenAI retires 2027-01-14
ft-gpt-4o-miniOpenAI retires 2027-01-14
ft-gpt-4oOpenAI retires 2027-01-14
GPT-5.6 TerraGitHub Copilot retires 2026-11-16
GPT Chat LatestAzure retires 2027-05-18
GPT Chat LatestAzure retires 2027-05-18
Step 5 PreviewOpenCode deprecated
Cat Jam FreeOpenCode deprecated
Cat Jam FreeOpenCode Go deprecated
unknown/cohere-command-a-plus-05-2026Azure retires 2026-10-16
MiMo-V2.5-Pro-UltraSpeedXiaomi deprecated
MiMo-V2.5-ProXiaomi Token Plan (Europe) deprecated
MiMo-V2.5-ProXiaomi Token Plan (China) deprecated
MiMo-V2.5-ProXiaomi Token Plan (Singapore) deprecated
MiMo-V2.5-ProXiaomi deprecated
MiMo-V2.5Xiaomi Token Plan (Europe) deprecated
MiMo-V2.5Xiaomi Token Plan (China) deprecated
MiMo-V2.5Xiaomi Token Plan (Singapore) deprecated
MiMo-V2.5Xiaomi deprecated

New models (31)

qwen3-vl
qwen3-vl-235b
claude-opus-5-5-fast
FLUX 3 Image Klein
doubao-seedance-2-0-260128
doubao-seedance-2-0-fast-260128
doubao-seedance-2-0-mini-260615
doubao-seedance-2-5-260628
deepseek-v4-1-flash-maas
Qwen 3.8 27B Uncensored Fast by Heabsy
K3 Edit
d1-ultra
muse-spark-open
muse-spark-open-816b-a42b
Muse Spark Open
Moondream 3.1 9B A2B
Moondream 3 Preview
Nvidia Nemotron 3.5 Super VL
nvidia-nemotron-3-5-super-vl
nvidia-nemotron-3-5-super-vl-120b-a12b
gpt-5-5-cyber-preview
Beam 1.0
Beam 1.0 501B A23B
Reflection: Beam 1.0 501B A23B
Beam 1.0 (Free)
Reka Edge 2603
Span-02
Orion 26B A4B v1.1
Stealth: Cat Jam (free)
LL Alpha Free
Prism

Models no longer listed (4)

deepseek/deepseek-v4-flash-vision-exp-cybersecurity
quiverai/arrow-1-1
stepfun/step-5-preview-free
unknown/reka-edge-2603