# FactQuire full dataset

## alibaba
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
qwen3-max	1.2	6.0	256000	-	ga
qwen3-max-2026-01-23	1.2	6.0	256000	-	ga
qwen3.6-flash	0.25	1.5	1000000	64000	ga
qwen3.6-flash-2026-04-16	0.25	1.5	1000000	64000	ga
qwen3.6-max-preview	1.3	7.8	256000	-	preview
qwen3.6-plus	0.5	3.0	1000000	64000	ga
qwen3.6-plus-2026-04-02	0.5	3.0	1000000	64000	ga
qwen3.7-max	2.5	7.5	1000000	-	ga
qwen3.7-max-2026-05-17	2.5	7.5	1000000	-	ga
qwen3.7-max-2026-05-20	2.5	7.5	1000000	-	ga
qwen3.7-max-preview	2.5	7.5	1000000	-	preview
qwen3.7-plus	0.4	1.6	1000000	64000	ga
qwen3.7-plus-2026-05-26	0.4	1.6	1000000	64000	ga

## amazon
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
amazon.nova-lite-v1:0	0.06	0.24	300000	10000	ga
amazon.nova-micro-v1:0	0.035	0.14	128000	10000	ga
amazon.nova-premier-v1:0	2.5	12.5	1000000	10000	ga
amazon.nova-pro-v1:0	0.8	3.2	300000	10000	ga
anthropic.claude-3-5-sonnet-20241022-v2:0	6.0	30.0	200000	-	deprecated

## anthropic
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
claude-fable-5	10	50	1000000	128000	ga
claude-haiku-4-5-20251001	1	5	200000	64000	ga
claude-opus-4-6	5	25	1000000	-	ga
claude-opus-4-7	5	25	1000000	-	ga
claude-opus-4-8	5	25	1000000	128000	ga
claude-sonnet-5	2	10	1000000	128000	ga

## cohere
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
c4ai-aya-expanse-32b	0.5	1.5	128000	4000	ga
command	1.0	2.0	4000	4000	deprecated
command-a-03-2025	-	-	256000	8000	ga
command-a-plus-05-2026	-	-	128000	64000	ga
command-a-reasoning-08-2025	-	-	256000	32000	ga
command-a-translate-08-2025	-	-	8000	8000	ga
command-a-vision-07-2025	-	-	128000	8000	ga
command-light	0.3	0.6	4000	4000	deprecated
command-r-03-2024	0.5	1.5	128000	4000	deprecated
command-r-08-2024	-	-	128000	4000	ga
command-r-plus-04-2024	3.0	15.0	128000	4000	deprecated
command-r-plus-08-2024	2.5	10.0	128000	4000	ga
command-r7b-12-2024	0.0375	0.15	128000	4000	ga
tiny-aya-global	-	-	8000	8000	ga

## deepseek
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
deepseek-v4-flash	0.14	0.28	1000000	384000	ga
deepseek-v4-pro	0.435	0.87	1000000	384000	ga

## fireworks
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
deepseek-v4-flash	0.14	0.28	-	-	ga
deepseek-v4-pro	1.74	3.48	-	-	ga
glm-5.1	1.4	4.4	-	-	ga
glm-5.1-fast	2.8	8.8	-	-	ga
glm-5.2	1.4	4.4	-	-	ga
glm-5.2-fast	2.1	6.6	-	-	ga
kimi-k2.6	0.95	4.0	-	-	ga
kimi-k2.6-fast	2.0	8.0	-	-	ga
kimi-k2.7-code	0.95	4.0	-	-	ga
kimi-k2.7-code-fast	1.9	8.0	-	-	ga
llama-v3p3-70b-instruct	0.9	0.9	131072	-	ga
minimax-m2.7	0.3	1.2	-	-	ga
minimax-m3	0.3	1.2	-	-	ga
openai-gpt-oss-120b	0.15	0.6	-	-	ga
openai-gpt-oss-20b	0.07	0.3	-	-	ga
qwen-3.7-plus	0.4	1.6	-	-	ga
qwen2p5-vl-32b-instruct	0.9	0.9	128000	-	ga

## google
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
gemini-2.5-flash	0.3	2.5	1048576	-	ga
gemini-2.5-flash-lite	0.1	0.4	-	-	ga
gemini-2.5-flash-lite-preview-09-2025	0.1	0.4	-	-	preview
gemini-2.5-flash-native-audio-preview-12-2025	0.5	2.0	-	-	preview
gemini-2.5-flash-preview-tts	0.5	10.0	-	-	preview
gemini-2.5-pro	1.25	10.0	-	-	ga
gemini-3-flash-preview	0.5	3.0	-	-	preview
gemini-3.1-flash-lite	0.25	1.5	-	-	ga
gemini-3.1-flash-live-preview	0.75	4.5	-	-	preview
gemini-3.1-pro-preview	2.0	12.0	-	-	preview

## groq
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
llama-3.1-8b-instant	0.05	0.08	131072	131072	ga
llama-3.3-70b-versatile	0.59	0.79	131072	32768	ga
openai/gpt-oss-120b	0.15	0.6	131072	65536	ga
openai/gpt-oss-20b	0.075	0.3	131072	65536	ga

## minimax
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
minimax-m2	0.3	1.2	-	-	deprecated
minimax-m2.1	0.3	1.2	-	-	deprecated
minimax-m2.5	0.3	1.2	-	-	deprecated
minimax-m2.7	0.3	1.2	-	-	ga
minimax-m3	0.3	1.2	-	-	ga

## mistral
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
codestral-latest	0.3	0.9	-	-	ga
devstral-medium-latest	0.4	2.0	-	-	ga
devstral-small-latest	0.1	0.3	-	-	ga
magistral-medium-latest	2.0	5.0	-	-	ga
mistral-large-latest	0.5	1.5	-	-	ga
mistral-medium-latest	1.5	7.5	-	-	ga
mistral-small-latest	0.15	0.6	-	-	ga
voxtral-small-latest	0.1	0.4	-	-	ga

## moonshot
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
kimi-k2.5	0.6	3.0	256000	-	ga
kimi-k2.6	0.95	4.0	256000	-	ga
kimi-k2.7-code	0.95	4.0	256000	-	ga

## openai
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
gpt-5.4	2.5	15.0	1050000	128000	ga
gpt-5.5	5.0	30.0	1050000	128000	ga
gpt-5.5-pro	30.0	180.0	1050000	128000	ga

## perplexity
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
perplexity/sonar	0.25	2.5	-	-	ga
sonar-pro	3.0	15.0	200000	-	ga
sonar-reasoning-pro	2.0	8.0	128000	-	ga

## together
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
Qwen/Qwen2.5-7B-Instruct-Turbo	0.3	0.3	32768	-	ga
cogito-v2.1-671b	1.25	1.25	-	-	ga
deepseek-v4-pro	1.74	3.48	-	-	ga
gemma-3n-e4b-instruct	0.06	0.12	-	-	ga
gemma-4-31b	0.39	0.97	-	-	ga
gemma-4-31b-it-pearl	0.28	0.86	-	-	ga
glm-5.1	1.4	4.4	-	-	ga
glm-5.2	1.4	4.4	-	-	ga
gpt-oss-120b	0.15	0.6	-	-	ga
gpt-oss-20b	0.05	0.2	-	-	ga
kimi-k2.6	1.2	4.5	-	-	ga
kimi-k2.7-code	0.95	4.0	-	-	ga
lfm2-24b-a2b	0.03	0.12	-	-	ga
llama-3.3-70b	1.04	1.04	-	-	ga
minimax-m2.5	0.3	1.2	-	-	ga
minimax-m2.7	0.3	1.2	-	-	ga
minimax-m3	0.3	1.2	-	-	ga
nvidia-nemotron-3-ultra	0.6	3.6	-	-	ga
qwen3-235b-a22b-fp8-throughput	0.2	0.6	-	-	ga
qwen3.5-397b-a17b	0.6	3.6	-	-	ga
qwen3.5-9b	0.17	0.25	-	-	ga
qwen3.6-plus	0.5	3.0	-	-	ga
qwen3.7-max	1.25	3.75	-	-	ga
qwen3.7-plus	0.32	1.28	-	-	ga
rnj-1-instruct	0.15	0.15	-	-	ga

## xai
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
grok-4.20-0309-non-reasoning	1.25	2.5	1000000	-	ga
grok-4.20-0309-reasoning	1.25	2.5	1000000	-	ga
grok-4.20-multi-agent-0309	1.25	2.5	1000000	-	ga
grok-4.3	1.25	2.5	1000000	-	ga
grok-build-0.1	1.0	2.0	256000	-	ga

## zhipu
model_id	input_usd_per_1m	output_usd_per_1m	context	max_output	status
glm-4-32b-0414-128k	0.1	0.1	-	-	ga
glm-4.5	0.6	2.2	-	-	ga
glm-4.5-air	0.2	1.1	-	-	ga
glm-4.5-airx	1.1	4.5	-	-	ga
glm-4.5-x	2.2	8.9	-	-	ga
glm-4.6	0.6	2.2	-	-	ga
glm-4.7	0.6	2.2	-	-	ga
glm-4.7-flashx	0.07	0.4	-	-	ga
glm-5	1.0	3.2	-	-	ga
glm-5-turbo	1.2	4.0	-	-	ga
glm-5.1	1.4	4.4	-	-	ga
glm-5.2	1.4	4.4	-	-	ga

## Changelog
2026-07-04	v0.5	Logic audit triage
2026-07-04	v0.4	Wave-2 gap fill
2026-07-04	v0.3	Coverage expansion
2026-07-04	v0.2	External dataset audit self-correction: Gemini 2.5 Flash exact context limit
2026-07-04	v0.1	Initial dataset: 40 models across 7 providers